open-webui/backend/open_webui/main.py

2301 lines
80 KiB
Python
Raw Normal View History

2024-10-16 14:32:57 +00:00
import asyncio
2024-08-27 22:10:27 +00:00
import inspect
2024-02-23 08:30:26 +00:00
import json
import logging
import mimetypes
2024-08-27 22:10:27 +00:00
import os
2024-06-05 20:57:48 +00:00
import shutil
2024-08-27 22:10:27 +00:00
import sys
import time
2024-10-22 10:16:48 +00:00
import random
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
import re
2025-06-08 16:58:31 +00:00
from uuid import uuid4
2024-12-12 02:36:59 +00:00
2024-08-27 22:10:27 +00:00
from contextlib import asynccontextmanager
2024-12-10 08:54:13 +00:00
from urllib.parse import urlencode, parse_qs, urlparse
from pydantic import BaseModel
from sqlalchemy import text
2024-02-23 08:30:26 +00:00
2024-12-10 08:54:13 +00:00
from typing import Optional
2024-11-16 12:41:07 +00:00
from aiocache import cached
2024-08-27 22:10:27 +00:00
import aiohttp
2025-04-18 13:30:34 +00:00
import anyio.to_thread
2024-08-27 22:10:27 +00:00
import requests
from redis import Redis
2024-12-17 21:52:57 +00:00
2024-10-16 14:58:03 +00:00
from fastapi import (
Depends,
FastAPI,
File,
Form,
HTTPException,
Request,
UploadFile,
status,
2024-12-17 21:51:29 +00:00
applications,
2024-12-19 09:00:32 +00:00
BackgroundTasks,
2024-10-16 14:58:03 +00:00
)
2024-12-16 18:00:51 +00:00
from fastapi.openapi.docs import get_swagger_ui_html
2024-12-17 21:52:57 +00:00
2024-10-16 14:58:03 +00:00
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import FileResponse, JSONResponse, RedirectResponse
2024-10-16 14:58:03 +00:00
from fastapi.staticfiles import StaticFiles
2024-12-10 08:54:13 +00:00
from starlette_compress import CompressMiddleware
2024-10-16 14:58:03 +00:00
from starlette.exceptions import HTTPException as StarletteHTTPException
from starlette.middleware.base import BaseHTTPMiddleware
from starlette.middleware.sessions import SessionMiddleware
from starlette.responses import Response, StreamingResponse
2025-06-28 11:12:31 +00:00
from starlette.datastructures import Headers
from starsessions import (
SessionMiddleware as StarSessionsMiddleware,
SessionAutoloadMiddleware,
)
from starsessions.stores.redis import RedisStore
2024-12-10 08:54:13 +00:00
from open_webui.utils import logger
from open_webui.utils.audit import AuditLevel, AuditLoggingMiddleware
from open_webui.utils.logger import start_logger
2024-12-12 02:46:29 +00:00
from open_webui.socket.main import (
app as socket_app,
periodic_usage_pool_cleanup,
2025-08-18 21:24:53 +00:00
get_event_emitter,
2025-06-16 06:42:34 +00:00
get_models_in_use,
get_active_user_ids,
)
2024-12-10 08:54:13 +00:00
from open_webui.routers import (
audio,
images,
ollama,
openai,
retrieval,
pipelines,
tasks,
2024-12-11 10:41:25 +00:00
auths,
2024-12-22 10:42:19 +00:00
channels,
2024-12-11 10:41:25 +00:00
chats,
2025-05-03 14:16:32 +00:00
notes,
2024-12-11 10:41:25 +00:00
folders,
configs,
groups,
files,
functions,
memories,
models,
knowledge,
prompts,
evaluations,
tools,
users,
user_models,
2024-12-11 10:41:25 +00:00
utils,
scim,
)
2024-12-12 04:39:55 +00:00
2024-12-12 02:08:55 +00:00
from open_webui.routers.retrieval import (
get_embedding_function,
get_reranking_function,
2024-12-12 02:46:29 +00:00
get_ef,
get_rf,
2024-12-12 02:08:55 +00:00
)
2024-12-10 08:54:13 +00:00
from open_webui.internal.db import Session, engine
2024-12-10 08:54:13 +00:00
from open_webui.models.functions import Functions
from open_webui.models.models import Models
from open_webui.models.users import UserModel, Users
2025-03-28 07:52:13 +00:00
from open_webui.models.chats import Chats
2024-12-10 08:54:13 +00:00
from open_webui.config import (
2024-12-10 08:54:13 +00:00
# Ollama
2024-08-27 22:10:27 +00:00
ENABLE_OLLAMA_API,
2024-12-10 08:54:13 +00:00
OLLAMA_BASE_URLS,
OLLAMA_API_CONFIGS,
# OpenAI
2024-08-27 22:10:27 +00:00
ENABLE_OPENAI_API,
2024-12-10 08:54:13 +00:00
OPENAI_API_BASE_URLS,
OPENAI_API_KEYS,
OPENAI_API_CONFIGS,
2025-02-12 07:12:00 +00:00
# Direct Connections
ENABLE_DIRECT_CONNECTIONS,
2025-06-28 11:12:31 +00:00
# Model list
ENABLE_BASE_MODELS_CACHE,
# Thread pool size for FastAPI/AnyIO
THREAD_POOL_SIZE,
2025-04-05 10:05:52 +00:00
# Tool Server Configs
TOOL_SERVER_CONNECTIONS,
2025-02-18 00:25:50 +00:00
# Code Execution
ENABLE_CODE_EXECUTION,
2025-02-18 00:25:50 +00:00
CODE_EXECUTION_ENGINE,
CODE_EXECUTION_JUPYTER_URL,
CODE_EXECUTION_JUPYTER_AUTH,
CODE_EXECUTION_JUPYTER_AUTH_TOKEN,
CODE_EXECUTION_JUPYTER_AUTH_PASSWORD,
CODE_EXECUTION_JUPYTER_TIMEOUT,
2025-02-10 10:25:02 +00:00
ENABLE_CODE_INTERPRETER,
CODE_INTERPRETER_ENGINE,
2025-02-12 05:36:16 +00:00
CODE_INTERPRETER_PROMPT_TEMPLATE,
2025-02-10 10:25:02 +00:00
CODE_INTERPRETER_JUPYTER_URL,
CODE_INTERPRETER_JUPYTER_AUTH,
CODE_INTERPRETER_JUPYTER_AUTH_TOKEN,
CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD,
CODE_INTERPRETER_JUPYTER_TIMEOUT,
2024-12-10 08:54:13 +00:00
# Image
AUTOMATIC1111_API_AUTH,
AUTOMATIC1111_BASE_URL,
AUTOMATIC1111_CFG_SCALE,
AUTOMATIC1111_SAMPLER,
AUTOMATIC1111_SCHEDULER,
COMFYUI_BASE_URL,
2024-12-17 07:29:00 +00:00
COMFYUI_API_KEY,
2024-12-10 08:54:13 +00:00
COMFYUI_WORKFLOW,
COMFYUI_WORKFLOW_NODES,
ENABLE_IMAGE_GENERATION,
2025-01-16 08:13:02 +00:00
ENABLE_IMAGE_PROMPT_GENERATION,
2024-12-10 08:54:13 +00:00
IMAGE_GENERATION_ENGINE,
IMAGE_GENERATION_MODEL,
IMAGE_SIZE,
IMAGE_STEPS,
IMAGES_OPENAI_API_BASE_URL,
IMAGES_OPENAI_API_VERSION,
2024-12-10 08:54:13 +00:00
IMAGES_OPENAI_API_KEY,
IMAGES_GEMINI_API_BASE_URL,
IMAGES_GEMINI_API_KEY,
2024-12-10 08:54:13 +00:00
# Audio
AUDIO_STT_ENGINE,
AUDIO_STT_MODEL,
AUDIO_STT_SUPPORTED_CONTENT_TYPES,
2024-12-10 08:54:13 +00:00
AUDIO_STT_OPENAI_API_BASE_URL,
AUDIO_STT_OPENAI_API_KEY,
AUDIO_STT_AZURE_API_KEY,
AUDIO_STT_AZURE_REGION,
AUDIO_STT_AZURE_LOCALES,
AUDIO_STT_AZURE_BASE_URL,
2025-05-01 12:39:36 +00:00
AUDIO_STT_AZURE_MAX_SPEAKERS,
2024-12-10 08:54:13 +00:00
AUDIO_TTS_ENGINE,
AUDIO_TTS_MODEL,
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
AUDIO_TTS_VOICE,
2024-12-10 08:54:13 +00:00
AUDIO_TTS_OPENAI_API_BASE_URL,
AUDIO_TTS_OPENAI_API_KEY,
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
AUDIO_TTS_OPENAI_PARAMS,
AUDIO_TTS_API_KEY,
2024-12-10 08:54:13 +00:00
AUDIO_TTS_SPLIT_ON,
AUDIO_TTS_AZURE_SPEECH_REGION,
2025-05-06 02:08:48 +00:00
AUDIO_TTS_AZURE_SPEECH_BASE_URL,
2024-12-10 08:54:13 +00:00
AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT,
2025-04-12 23:33:36 +00:00
PLAYWRIGHT_WS_URL,
2025-03-20 21:01:47 +00:00
PLAYWRIGHT_TIMEOUT,
FIRECRAWL_API_BASE_URL,
FIRECRAWL_API_KEY,
2025-04-12 23:33:36 +00:00
WEB_LOADER_ENGINE,
WEB_LOADER_CONCURRENT_REQUESTS,
2024-12-10 08:54:13 +00:00
WHISPER_MODEL,
2025-04-14 06:39:38 +00:00
WHISPER_VAD_FILTER,
WHISPER_LANGUAGE,
2025-02-02 13:58:59 +00:00
DEEPGRAM_API_KEY,
2024-12-10 08:54:13 +00:00
WHISPER_MODEL_AUTO_UPDATE,
WHISPER_MODEL_DIR,
2024-12-11 10:41:25 +00:00
# Retrieval
RAG_TEMPLATE,
DEFAULT_RAG_TEMPLATE,
2025-02-19 05:14:58 +00:00
RAG_FULL_CONTEXT,
2025-02-26 23:42:19 +00:00
BYPASS_EMBEDDING_AND_RETRIEVAL,
2024-12-11 10:41:25 +00:00
RAG_EMBEDDING_MODEL,
RAG_EMBEDDING_MODEL_AUTO_UPDATE,
RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
RAG_RERANKING_ENGINE,
2024-12-11 10:41:25 +00:00
RAG_RERANKING_MODEL,
RAG_EXTERNAL_RERANKER_URL,
RAG_EXTERNAL_RERANKER_API_KEY,
2024-12-11 10:41:25 +00:00
RAG_RERANKING_MODEL_AUTO_UPDATE,
RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
RAG_EMBEDDING_ENGINE,
RAG_EMBEDDING_BATCH_SIZE,
RAG_TOP_K,
RAG_TOP_K_RERANKER,
2024-12-11 10:41:25 +00:00
RAG_RELEVANCE_THRESHOLD,
RAG_HYBRID_BM25_WEIGHT,
2025-05-14 19:06:33 +00:00
RAG_ALLOWED_FILE_EXTENSIONS,
2024-12-11 10:41:25 +00:00
RAG_FILE_MAX_COUNT,
RAG_FILE_MAX_SIZE,
2025-06-16 12:52:57 +00:00
FILE_IMAGE_COMPRESSION_WIDTH,
FILE_IMAGE_COMPRESSION_HEIGHT,
2024-12-11 10:41:25 +00:00
RAG_OPENAI_API_BASE_URL,
RAG_OPENAI_API_KEY,
2025-05-20 02:58:04 +00:00
RAG_AZURE_OPENAI_BASE_URL,
RAG_AZURE_OPENAI_API_KEY,
RAG_AZURE_OPENAI_API_VERSION,
2024-12-11 10:41:25 +00:00
RAG_OLLAMA_BASE_URL,
RAG_OLLAMA_API_KEY,
CHUNK_OVERLAP,
CHUNK_SIZE,
CONTENT_EXTRACTION_ENGINE,
DATALAB_MARKER_API_KEY,
2025-07-23 00:49:28 +00:00
DATALAB_MARKER_API_BASE_URL,
DATALAB_MARKER_ADDITIONAL_CONFIG,
DATALAB_MARKER_SKIP_CACHE,
DATALAB_MARKER_FORCE_OCR,
DATALAB_MARKER_PAGINATE,
DATALAB_MARKER_STRIP_EXISTING_OCR,
DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION,
2025-07-23 01:06:29 +00:00
DATALAB_MARKER_FORMAT_LINES,
DATALAB_MARKER_OUTPUT_FORMAT,
MINERU_API_MODE,
MINERU_API_URL,
MINERU_API_KEY,
MINERU_PARAMS,
DATALAB_MARKER_USE_LLM,
2025-05-14 18:28:40 +00:00
EXTERNAL_DOCUMENT_LOADER_URL,
EXTERNAL_DOCUMENT_LOADER_API_KEY,
2024-12-11 10:41:25 +00:00
TIKA_SERVER_URL,
DOCLING_SERVER_URL,
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
DOCLING_PARAMS,
DOCLING_DO_OCR,
DOCLING_FORCE_OCR,
DOCLING_OCR_ENGINE,
DOCLING_OCR_LANG,
DOCLING_PDF_BACKEND,
DOCLING_TABLE_MODE,
DOCLING_PIPELINE,
DOCLING_DO_PICTURE_DESCRIPTION,
DOCLING_PICTURE_DESCRIPTION_MODE,
2025-06-08 16:02:14 +00:00
DOCLING_PICTURE_DESCRIPTION_LOCAL,
DOCLING_PICTURE_DESCRIPTION_API,
DOCUMENT_INTELLIGENCE_ENDPOINT,
DOCUMENT_INTELLIGENCE_KEY,
MISTRAL_OCR_API_KEY,
2024-12-11 10:41:25 +00:00
RAG_TEXT_SPLITTER,
TIKTOKEN_ENCODING_NAME,
PDF_EXTRACT_IMAGES,
YOUTUBE_LOADER_LANGUAGE,
YOUTUBE_LOADER_PROXY_URL,
# Retrieval (Web Search)
2025-04-12 23:33:36 +00:00
ENABLE_WEB_SEARCH,
WEB_SEARCH_ENGINE,
2025-02-26 23:42:19 +00:00
BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
BYPASS_WEB_SEARCH_WEB_LOADER,
2025-04-12 23:33:36 +00:00
WEB_SEARCH_RESULT_COUNT,
WEB_SEARCH_CONCURRENT_REQUESTS,
WEB_SEARCH_TRUST_ENV,
WEB_SEARCH_DOMAIN_FILTER_LIST,
2025-09-24 20:19:05 +00:00
OLLAMA_CLOUD_WEB_SEARCH_API_KEY,
2024-12-11 10:41:25 +00:00
JINA_API_KEY,
SEARCHAPI_API_KEY,
SEARCHAPI_ENGINE,
2025-02-14 04:24:58 +00:00
SERPAPI_API_KEY,
SERPAPI_ENGINE,
2024-12-11 10:41:25 +00:00
SEARXNG_QUERY_URL,
YACY_QUERY_URL,
YACY_USERNAME,
YACY_PASSWORD,
2024-12-11 10:41:25 +00:00
SERPER_API_KEY,
SERPLY_API_KEY,
SERPSTACK_API_KEY,
SERPSTACK_HTTPS,
TAVILY_API_KEY,
TAVILY_EXTRACT_DEPTH,
2024-12-11 10:41:25 +00:00
BING_SEARCH_V7_ENDPOINT,
BING_SEARCH_V7_SUBSCRIPTION_KEY,
BRAVE_SEARCH_API_KEY,
EXA_API_KEY,
PERPLEXITY_API_KEY,
PERPLEXITY_MODEL,
PERPLEXITY_SEARCH_CONTEXT_USAGE,
SOUGOU_API_SID,
SOUGOU_API_SK,
2024-12-11 10:41:25 +00:00
KAGI_SEARCH_API_KEY,
MOJEEK_SEARCH_API_KEY,
2025-02-10 08:44:47 +00:00
BOCHA_SEARCH_API_KEY,
2024-12-11 10:41:25 +00:00
GOOGLE_PSE_API_KEY,
GOOGLE_PSE_ENGINE_ID,
2024-12-18 17:04:55 +00:00
GOOGLE_DRIVE_CLIENT_ID,
GOOGLE_DRIVE_API_KEY,
2025-09-17 17:18:23 +00:00
ENABLE_ONEDRIVE_INTEGRATION,
ONEDRIVE_CLIENT_ID_PERSONAL,
ONEDRIVE_CLIENT_ID_BUSINESS,
2025-04-14 15:27:59 +00:00
ONEDRIVE_SHAREPOINT_URL,
ONEDRIVE_SHAREPOINT_TENANT_ID,
2025-09-17 17:18:23 +00:00
ENABLE_ONEDRIVE_PERSONAL,
ENABLE_ONEDRIVE_BUSINESS,
2024-12-11 10:41:25 +00:00
ENABLE_RAG_HYBRID_SEARCH,
ENABLE_RAG_LOCAL_WEB_FETCH,
2025-04-12 23:33:36 +00:00
ENABLE_WEB_LOADER_SSL_VERIFICATION,
2024-12-19 02:04:56 +00:00
ENABLE_GOOGLE_DRIVE_INTEGRATION,
2024-12-11 10:41:25 +00:00
UPLOAD_DIR,
EXTERNAL_WEB_SEARCH_URL,
EXTERNAL_WEB_SEARCH_API_KEY,
EXTERNAL_WEB_LOADER_URL,
EXTERNAL_WEB_LOADER_API_KEY,
2024-12-10 08:54:13 +00:00
# WebUI
WEBUI_AUTH,
WEBUI_NAME,
WEBUI_BANNERS,
WEBHOOK_URL,
ADMIN_EMAIL,
SHOW_ADMIN_DETAILS,
JWT_EXPIRES_IN,
ENABLE_SIGNUP,
ENABLE_LOGIN_FORM,
ENABLE_API_KEY,
ENABLE_API_KEY_ENDPOINT_RESTRICTIONS,
API_KEY_ALLOWED_ENDPOINTS,
2024-12-23 04:02:14 +00:00
ENABLE_CHANNELS,
2025-05-01 12:39:36 +00:00
ENABLE_NOTES,
2024-12-10 08:54:13 +00:00
ENABLE_COMMUNITY_SHARING,
ENABLE_MESSAGE_RATING,
2025-03-31 04:31:16 +00:00
ENABLE_USER_WEBHOOKS,
2024-12-10 08:54:13 +00:00
ENABLE_EVALUATION_ARENA_MODELS,
BYPASS_ADMIN_ACCESS_CONTROL,
2024-12-10 08:54:13 +00:00
USER_PERMISSIONS,
DEFAULT_USER_ROLE,
2025-05-14 17:39:17 +00:00
PENDING_USER_OVERLAY_CONTENT,
PENDING_USER_OVERLAY_TITLE,
2024-12-10 08:54:13 +00:00
DEFAULT_PROMPT_SUGGESTIONS,
DEFAULT_MODELS,
DEFAULT_ARENA_MODEL,
MODEL_ORDER_LIST,
EVALUATION_ARENA_MODELS,
# WebUI (OAuth)
ENABLE_OAUTH_ROLE_MANAGEMENT,
OAUTH_ROLES_CLAIM,
OAUTH_EMAIL_CLAIM,
OAUTH_PICTURE_CLAIM,
OAUTH_USERNAME_CLAIM,
OAUTH_ALLOWED_ROLES,
OAUTH_ADMIN_ROLES,
# WebUI (LDAP)
ENABLE_LDAP,
LDAP_SERVER_LABEL,
LDAP_SERVER_HOST,
LDAP_SERVER_PORT,
LDAP_ATTRIBUTE_FOR_MAIL,
2024-12-10 08:54:13 +00:00
LDAP_ATTRIBUTE_FOR_USERNAME,
LDAP_SEARCH_FILTERS,
LDAP_SEARCH_BASE,
LDAP_APP_DN,
LDAP_APP_PASSWORD,
LDAP_USE_TLS,
LDAP_CA_CERT_FILE,
LDAP_VALIDATE_CERT,
2024-12-10 08:54:13 +00:00
LDAP_CIPHERS,
# LDAP Group Management
ENABLE_LDAP_GROUP_MANAGEMENT,
ENABLE_LDAP_GROUP_CREATION,
LDAP_ATTRIBUTE_FOR_GROUPS,
2024-12-10 08:54:13 +00:00
# Misc
2024-08-27 22:10:27 +00:00
ENV,
2024-12-10 08:54:13 +00:00
CACHE_DIR,
STATIC_DIR,
2024-08-27 22:10:27 +00:00
FRONTEND_BUILD_DIR,
2024-12-10 08:54:13 +00:00
CORS_ALLOW_ORIGIN,
DEFAULT_LOCALE,
2024-08-27 22:10:27 +00:00
OAUTH_PROVIDERS,
2024-12-25 16:50:57 +00:00
WEBUI_URL,
2025-05-14 19:53:28 +00:00
RESPONSE_WATERMARK,
2024-12-10 08:54:13 +00:00
# Admin
ENABLE_ADMIN_CHAT_ACCESS,
BYPASS_ADMIN_ACCESS_CONTROL,
2024-12-10 08:54:13 +00:00
ENABLE_ADMIN_EXPORT,
# Tasks
2024-06-09 21:53:10 +00:00
TASK_MODEL,
TASK_MODEL_EXTERNAL,
2024-12-10 08:54:13 +00:00
ENABLE_TAGS_GENERATION,
ENABLE_TITLE_GENERATION,
2025-06-03 14:07:29 +00:00
ENABLE_FOLLOW_UP_GENERATION,
2024-11-19 10:24:32 +00:00
ENABLE_SEARCH_QUERY_GENERATION,
ENABLE_RETRIEVAL_QUERY_GENERATION,
2024-12-10 08:54:13 +00:00
ENABLE_AUTOCOMPLETE_GENERATION,
2024-06-09 21:25:31 +00:00
TITLE_GENERATION_PROMPT_TEMPLATE,
2025-06-03 14:07:29 +00:00
FOLLOW_UP_GENERATION_PROMPT_TEMPLATE,
TAGS_GENERATION_PROMPT_TEMPLATE,
2025-01-16 08:06:37 +00:00
IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE,
2024-06-11 06:40:27 +00:00
TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
2024-12-10 08:54:13 +00:00
QUERY_GENERATION_PROMPT_TEMPLATE,
AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE,
AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH,
2024-08-27 22:10:27 +00:00
AppConfig,
2024-09-24 23:06:11 +00:00
reset_config,
2024-08-27 22:10:27 +00:00
)
from open_webui.env import (
2025-07-29 19:45:25 +00:00
LICENSE_KEY,
AUDIT_EXCLUDED_PATHS,
AUDIT_LOG_LEVEL,
2024-08-27 22:10:27 +00:00
CHANGELOG,
2025-03-08 17:59:15 +00:00
REDIS_URL,
2025-08-04 10:15:08 +00:00
REDIS_CLUSTER,
REDIS_KEY_PREFIX,
2025-03-27 07:51:55 +00:00
REDIS_SENTINEL_HOSTS,
REDIS_SENTINEL_PORT,
2024-08-27 22:10:27 +00:00
GLOBAL_LOG_LEVEL,
MAX_BODY_LOG_SIZE,
2024-06-24 02:28:33 +00:00
SAFE_MODE,
2024-08-27 22:10:27 +00:00
SRC_LOG_LEVELS,
VERSION,
2025-06-08 17:21:51 +00:00
INSTANCE_ID,
2024-08-27 22:10:27 +00:00
WEBUI_BUILD_HASH,
WEBUI_SECRET_KEY,
WEBUI_SESSION_COOKIE_SAME_SITE,
2024-06-07 08:13:42 +00:00
WEBUI_SESSION_COOKIE_SECURE,
2025-07-31 12:43:37 +00:00
ENABLE_SIGNUP_PASSWORD_CONFIRMATION,
EMAIL_SMTP_SERVER,
EMAIL_SMTP_PORT,
EMAIL_SMTP_USERNAME,
EMAIL_SMTP_PASSWORD,
EMAIL_SMTP_FROM,
EMAIL_VERIFICATION_CODE_TTL,
EMAIL_VERIFICATION_SEND_INTERVAL,
EMAIL_VERIFICATION_MAX_ATTEMPTS,
2024-12-10 08:54:13 +00:00
WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
WEBUI_AUTH_TRUSTED_NAME_HEADER,
2025-04-19 06:58:37 +00:00
WEBUI_AUTH_SIGNOUT_REDIRECT_URL,
2025-08-06 10:25:42 +00:00
# SCIM
SCIM_ENABLED,
SCIM_TOKEN,
ENABLE_COMPRESSION_MIDDLEWARE,
ENABLE_WEBSOCKET_SUPPORT,
2024-12-02 02:25:44 +00:00
BYPASS_MODEL_ACCESS_CONTROL,
2024-09-24 23:06:11 +00:00
RESET_CONFIG_ON_START,
ENABLE_VERSION_UPDATE_CHECK,
2025-03-11 18:55:30 +00:00
ENABLE_OTEL,
2025-04-10 17:35:43 +00:00
EXTERNAL_PWA_MANIFEST_URL,
2025-05-14 19:33:52 +00:00
AIOHTTP_CLIENT_SESSION_SSL,
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
ENABLE_STAR_SESSIONS_MIDDLEWARE,
2024-08-27 22:10:27 +00:00
)
2024-12-10 08:54:13 +00:00
2024-12-13 04:22:17 +00:00
2024-12-13 06:28:42 +00:00
from open_webui.utils.models import (
get_all_models,
get_all_base_models,
check_model_access,
2025-09-17 04:19:21 +00:00
get_filtered_models,
2024-10-16 14:32:57 +00:00
)
from open_webui.utils.email_utils import EmailVerificationManager
2024-12-13 04:22:17 +00:00
from open_webui.utils.chat import (
generate_chat_completion as chat_completion_handler,
chat_completed as chat_completed_handler,
chat_action as chat_action_handler,
2024-08-27 22:10:27 +00:00
)
from open_webui.utils.misc import get_message_list
2025-06-04 14:13:53 +00:00
from open_webui.utils.embeddings import generate_embeddings
2024-12-13 06:28:42 +00:00
from open_webui.utils.middleware import process_chat_payload, process_chat_response
2024-12-10 08:54:13 +00:00
from open_webui.utils.access_control import has_access
2024-12-09 00:01:56 +00:00
from open_webui.utils.auth import (
2025-02-17 02:35:09 +00:00
get_license_data,
2025-04-05 10:05:52 +00:00
get_http_authorization_cred,
2024-08-27 22:10:27 +00:00
decode_token,
get_admin_user,
get_verified_user,
2024-03-10 05:47:01 +00:00
)
2025-04-30 12:01:23 +00:00
from open_webui.utils.plugin import install_tool_and_function_dependencies
2025-09-25 06:49:16 +00:00
from open_webui.utils.oauth import (
OAuthManager,
OAuthClientManager,
decrypt_data,
OAuthClientInformationFull,
)
2024-12-10 08:54:13 +00:00
from open_webui.utils.security_headers import SecurityHeadersMiddleware
2025-06-08 16:58:31 +00:00
from open_webui.utils.redis import get_redis_connection
2024-12-10 08:54:13 +00:00
2025-04-13 03:51:02 +00:00
from open_webui.tasks import (
redis_task_command_listener,
2025-07-11 14:14:48 +00:00
list_task_ids_by_item_id,
2025-08-18 21:24:53 +00:00
create_task,
2025-04-13 03:51:02 +00:00
stop_task,
list_tasks,
) # Import from tasks.py
2025-03-18 08:28:47 +00:00
from open_webui.utils.redis import get_sentinels_from_env
2025-08-09 17:10:12 +00:00
from open_webui.constants import ERROR_MESSAGES
2024-06-24 02:28:33 +00:00
if SAFE_MODE:
print("SAFE MODE ENABLED")
Functions.deactivate_all_functions()
logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["MAIN"])
2023-11-15 00:28:51 +00:00
2024-03-28 09:45:56 +00:00
2023-11-15 00:28:51 +00:00
class SPAStaticFiles(StaticFiles):
async def get_response(self, path: str, scope):
try:
return await super().get_response(path, scope)
except (HTTPException, StarletteHTTPException) as ex:
if ex.status_code == 404:
2025-02-11 13:21:27 +00:00
if path.endswith(".js"):
# Return 404 for javascript files
2025-02-11 10:49:36 +00:00
raise ex
2025-02-11 13:21:27 +00:00
else:
return await super().get_response("index.html", scope)
2023-11-15 00:28:51 +00:00
else:
raise ex
2024-04-02 10:03:55 +00:00
print(
2024-05-03 21:23:38 +00:00
rf"""
2024-04-02 10:03:55 +00:00
2025-05-06 16:15:09 +00:00
v{VERSION} - building the best AI user interface.
2024-05-26 07:49:30 +00:00
{f"Commit: {WEBUI_BUILD_HASH}" if WEBUI_BUILD_HASH != "dev-build" else ""}
2024-04-02 10:03:55 +00:00
https://github.com/open-webui/open-webui
"""
)
2023-11-15 00:28:51 +00:00
@asynccontextmanager
async def lifespan(app: FastAPI):
2025-06-08 17:21:51 +00:00
app.state.instance_id = INSTANCE_ID
start_logger()
2025-06-08 16:58:31 +00:00
2024-09-24 23:06:11 +00:00
if RESET_CONFIG_ON_START:
reset_config()
2025-03-04 08:32:27 +00:00
if LICENSE_KEY:
get_license_data(app, LICENSE_KEY)
2025-02-16 08:11:18 +00:00
2025-04-30 12:01:23 +00:00
# This should be blocking (sync) so functions are not deactivated on first /get_models calls
# when the first user lands on the / route.
log.info("Installing external dependencies of functions and tools...")
install_tool_and_function_dependencies()
2025-06-08 16:58:31 +00:00
app.state.redis = get_redis_connection(
redis_url=REDIS_URL,
redis_sentinels=get_sentinels_from_env(
REDIS_SENTINEL_HOSTS, REDIS_SENTINEL_PORT
),
2025-08-04 10:15:08 +00:00
redis_cluster=REDIS_CLUSTER,
2025-06-09 11:37:05 +00:00
async_mode=True,
2025-06-08 16:58:31 +00:00
)
app.state.email_verification_manager = EmailVerificationManager(app.state.redis)
2025-06-08 16:58:31 +00:00
2025-06-09 13:21:10 +00:00
if app.state.redis is not None:
app.state.redis_task_command_listener = asyncio.create_task(
redis_task_command_listener(app)
)
2025-05-08 16:47:41 +00:00
if THREAD_POOL_SIZE and THREAD_POOL_SIZE > 0:
2025-04-18 13:30:34 +00:00
limiter = anyio.to_thread.current_default_thread_limiter()
2025-05-08 16:47:41 +00:00
limiter.total_tokens = THREAD_POOL_SIZE
2024-09-24 15:43:43 +00:00
asyncio.create_task(periodic_usage_pool_cleanup())
if app.state.config.ENABLE_BASE_MODELS_CACHE:
2025-06-28 11:13:21 +00:00
await get_all_models(
2025-06-28 11:12:31 +00:00
Request(
# Creating a mock request object to pass to get_all_models
{
"type": "http",
"asgi.version": "3.0",
"asgi.spec_version": "2.0",
"method": "GET",
"path": "/internal",
"query_string": b"",
"headers": Headers({}).raw,
"client": ("127.0.0.1", 12345),
"server": ("127.0.0.1", 80),
"scheme": "http",
"app": app,
}
),
None,
)
yield
if hasattr(app.state, "redis_task_command_listener"):
app.state.redis_task_command_listener.cancel()
app = FastAPI(
title="CyberLover",
2024-11-13 11:09:46 +00:00
docs_url="/docs" if ENV == "dev" else None,
openapi_url="/openapi.json" if ENV == "dev" else None,
redoc_url=None,
lifespan=lifespan,
)
2023-11-15 00:28:51 +00:00
# For CyberLover OIDC/OAuth2
2025-02-16 08:11:18 +00:00
oauth_manager = OAuthManager(app)
app.state.oauth_manager = oauth_manager
2025-02-16 08:11:18 +00:00
2025-09-25 06:49:16 +00:00
# For Integrations
oauth_client_manager = OAuthClientManager(app)
app.state.oauth_client_manager = oauth_client_manager
2025-06-08 16:58:31 +00:00
app.state.instance_id = None
2025-03-28 07:52:13 +00:00
app.state.config = AppConfig(
redis_url=REDIS_URL,
redis_sentinels=get_sentinels_from_env(REDIS_SENTINEL_HOSTS, REDIS_SENTINEL_PORT),
2025-08-04 10:15:08 +00:00
redis_cluster=REDIS_CLUSTER,
redis_key_prefix=REDIS_KEY_PREFIX,
2025-03-28 07:52:13 +00:00
)
2025-06-08 16:58:31 +00:00
app.state.redis = None
2024-05-24 08:40:48 +00:00
2025-02-16 08:11:18 +00:00
app.state.WEBUI_NAME = WEBUI_NAME
2025-03-04 09:16:08 +00:00
app.state.LICENSE_METADATA = None
2024-05-17 03:49:28 +00:00
2025-03-10 14:27:31 +00:00
########################################
#
# OPENTELEMETRY
#
########################################
2025-03-11 20:12:28 +00:00
if ENABLE_OTEL:
2025-03-11 19:30:09 +00:00
from open_webui.utils.telemetry.setup import setup as setup_opentelemetry
2025-03-11 18:55:30 +00:00
setup_opentelemetry(app=app, db_engine=engine)
2025-03-10 14:27:31 +00:00
2024-12-10 08:54:13 +00:00
########################################
2024-06-20 08:51:39 +00:00
#
2024-12-10 08:54:13 +00:00
# OLLAMA
2024-06-20 08:51:39 +00:00
#
2024-12-10 08:54:13 +00:00
########################################
2024-09-28 17:51:28 +00:00
2024-10-08 01:19:13 +00:00
2024-05-24 08:40:48 +00:00
app.state.config.ENABLE_OLLAMA_API = ENABLE_OLLAMA_API
2024-12-10 08:54:13 +00:00
app.state.config.OLLAMA_BASE_URLS = OLLAMA_BASE_URLS
app.state.config.OLLAMA_API_CONFIGS = OLLAMA_API_CONFIGS
2024-07-12 01:41:00 +00:00
2024-12-11 11:38:45 +00:00
app.state.OLLAMA_MODELS = {}
2024-07-12 01:41:00 +00:00
2024-12-10 08:54:13 +00:00
########################################
2024-06-20 08:51:39 +00:00
#
2024-12-10 08:54:13 +00:00
# OPENAI
2024-06-20 08:51:39 +00:00
#
2024-12-10 08:54:13 +00:00
########################################
2024-06-09 21:53:10 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_OPENAI_API = ENABLE_OPENAI_API
app.state.config.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
app.state.config.OPENAI_API_KEYS = OPENAI_API_KEYS
app.state.config.OPENAI_API_CONFIGS = OPENAI_API_CONFIGS
2024-10-20 03:34:17 +00:00
2024-12-11 11:38:45 +00:00
app.state.OPENAI_MODELS = {}
2024-06-12 20:34:34 +00:00
2025-04-05 10:05:52 +00:00
########################################
#
# TOOL SERVERS
#
########################################
app.state.config.TOOL_SERVER_CONNECTIONS = TOOL_SERVER_CONNECTIONS
app.state.TOOL_SERVERS = []
2025-02-12 06:29:45 +00:00
########################################
#
2025-02-12 07:12:00 +00:00
# DIRECT CONNECTIONS
2025-02-12 06:29:45 +00:00
#
########################################
2025-02-12 07:12:00 +00:00
app.state.config.ENABLE_DIRECT_CONNECTIONS = ENABLE_DIRECT_CONNECTIONS
2025-02-12 06:29:45 +00:00
########################################
#
# SCIM
#
########################################
2025-08-06 10:27:07 +00:00
app.state.SCIM_ENABLED = SCIM_ENABLED
app.state.SCIM_TOKEN = SCIM_TOKEN
2025-06-28 11:12:31 +00:00
########################################
#
# MODELS
2025-06-28 11:12:31 +00:00
#
########################################
app.state.config.ENABLE_BASE_MODELS_CACHE = ENABLE_BASE_MODELS_CACHE
app.state.BASE_MODELS = []
2025-06-28 11:12:31 +00:00
2024-12-10 08:54:13 +00:00
########################################
#
# WEBUI
#
########################################
2024-07-02 02:33:58 +00:00
2024-12-25 16:50:57 +00:00
app.state.config.WEBUI_URL = WEBUI_URL
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_SIGNUP = ENABLE_SIGNUP
app.state.config.ENABLE_LOGIN_FORM = ENABLE_LOGIN_FORM
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_API_KEY = ENABLE_API_KEY
app.state.config.ENABLE_API_KEY_ENDPOINT_RESTRICTIONS = (
ENABLE_API_KEY_ENDPOINT_RESTRICTIONS
)
app.state.config.API_KEY_ALLOWED_ENDPOINTS = API_KEY_ALLOWED_ENDPOINTS
2024-06-09 21:25:31 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
2024-06-09 21:25:31 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.SHOW_ADMIN_DETAILS = SHOW_ADMIN_DETAILS
app.state.config.ADMIN_EMAIL = ADMIN_EMAIL
2024-06-09 22:19:36 +00:00
app.state.email_verification_enabled = True
app.state.email_verification_config = {
"ttl": EMAIL_VERIFICATION_CODE_TTL,
"send_interval": EMAIL_VERIFICATION_SEND_INTERVAL,
"max_attempts": EMAIL_VERIFICATION_MAX_ATTEMPTS,
"smtp": {
"server": EMAIL_SMTP_SERVER,
"port": EMAIL_SMTP_PORT,
"username": EMAIL_SMTP_USERNAME,
"password": EMAIL_SMTP_PASSWORD,
"from_email": EMAIL_SMTP_FROM,
},
}
2024-06-09 21:53:10 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.DEFAULT_MODELS = DEFAULT_MODELS
app.state.config.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
2025-05-14 19:53:28 +00:00
2025-05-14 17:39:17 +00:00
app.state.config.PENDING_USER_OVERLAY_CONTENT = PENDING_USER_OVERLAY_CONTENT
app.state.config.PENDING_USER_OVERLAY_TITLE = PENDING_USER_OVERLAY_TITLE
2024-06-09 21:53:10 +00:00
2025-05-14 19:53:28 +00:00
app.state.config.RESPONSE_WATERMARK = RESPONSE_WATERMARK
2024-12-10 08:54:13 +00:00
app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
app.state.config.WEBHOOK_URL = WEBHOOK_URL
2024-12-10 08:54:13 +00:00
app.state.config.BANNERS = WEBUI_BANNERS
app.state.config.MODEL_ORDER_LIST = MODEL_ORDER_LIST
2024-12-23 04:02:14 +00:00
app.state.config.ENABLE_CHANNELS = ENABLE_CHANNELS
2025-05-01 12:39:36 +00:00
app.state.config.ENABLE_NOTES = ENABLE_NOTES
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
app.state.config.ENABLE_MESSAGE_RATING = ENABLE_MESSAGE_RATING
2025-03-31 04:31:16 +00:00
app.state.config.ENABLE_USER_WEBHOOKS = ENABLE_USER_WEBHOOKS
2024-09-07 03:50:29 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_EVALUATION_ARENA_MODELS = ENABLE_EVALUATION_ARENA_MODELS
app.state.config.EVALUATION_ARENA_MODELS = EVALUATION_ARENA_MODELS
2024-09-07 23:51:12 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.OAUTH_USERNAME_CLAIM = OAUTH_USERNAME_CLAIM
app.state.config.OAUTH_PICTURE_CLAIM = OAUTH_PICTURE_CLAIM
app.state.config.OAUTH_EMAIL_CLAIM = OAUTH_EMAIL_CLAIM
2024-09-08 00:17:02 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_OAUTH_ROLE_MANAGEMENT = ENABLE_OAUTH_ROLE_MANAGEMENT
app.state.config.OAUTH_ROLES_CLAIM = OAUTH_ROLES_CLAIM
app.state.config.OAUTH_ALLOWED_ROLES = OAUTH_ALLOWED_ROLES
app.state.config.OAUTH_ADMIN_ROLES = OAUTH_ADMIN_ROLES
2024-06-09 21:53:10 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_LDAP = ENABLE_LDAP
app.state.config.LDAP_SERVER_LABEL = LDAP_SERVER_LABEL
app.state.config.LDAP_SERVER_HOST = LDAP_SERVER_HOST
app.state.config.LDAP_SERVER_PORT = LDAP_SERVER_PORT
app.state.config.LDAP_ATTRIBUTE_FOR_MAIL = LDAP_ATTRIBUTE_FOR_MAIL
2024-12-10 08:54:13 +00:00
app.state.config.LDAP_ATTRIBUTE_FOR_USERNAME = LDAP_ATTRIBUTE_FOR_USERNAME
app.state.config.LDAP_APP_DN = LDAP_APP_DN
app.state.config.LDAP_APP_PASSWORD = LDAP_APP_PASSWORD
app.state.config.LDAP_SEARCH_BASE = LDAP_SEARCH_BASE
app.state.config.LDAP_SEARCH_FILTERS = LDAP_SEARCH_FILTERS
app.state.config.LDAP_USE_TLS = LDAP_USE_TLS
app.state.config.LDAP_CA_CERT_FILE = LDAP_CA_CERT_FILE
app.state.config.LDAP_VALIDATE_CERT = LDAP_VALIDATE_CERT
2024-12-10 08:54:13 +00:00
app.state.config.LDAP_CIPHERS = LDAP_CIPHERS
2024-06-09 21:53:10 +00:00
# For LDAP Group Management
app.state.config.ENABLE_LDAP_GROUP_MANAGEMENT = ENABLE_LDAP_GROUP_MANAGEMENT
app.state.config.ENABLE_LDAP_GROUP_CREATION = ENABLE_LDAP_GROUP_CREATION
app.state.config.LDAP_ATTRIBUTE_FOR_GROUPS = LDAP_ATTRIBUTE_FOR_GROUPS
2024-09-07 03:50:29 +00:00
2024-12-10 08:54:13 +00:00
app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
app.state.AUTH_TRUSTED_NAME_HEADER = WEBUI_AUTH_TRUSTED_NAME_HEADER
2025-04-19 06:58:37 +00:00
app.state.WEBUI_AUTH_SIGNOUT_REDIRECT_URL = WEBUI_AUTH_SIGNOUT_REDIRECT_URL
2025-04-10 17:35:43 +00:00
app.state.EXTERNAL_PWA_MANIFEST_URL = EXTERNAL_PWA_MANIFEST_URL
2024-06-13 04:18:53 +00:00
2025-02-16 08:11:18 +00:00
app.state.USER_COUNT = None
2025-05-27 10:39:35 +00:00
2024-12-10 08:54:13 +00:00
app.state.TOOLS = {}
2025-05-27 10:39:35 +00:00
app.state.TOOL_CONTENTS = {}
2024-12-10 08:54:13 +00:00
app.state.FUNCTIONS = {}
2025-05-27 10:39:35 +00:00
app.state.FUNCTION_CONTENTS = {}
2024-07-02 02:33:58 +00:00
2024-12-10 08:54:13 +00:00
########################################
#
# RETRIEVAL
#
########################################
2024-06-13 04:18:53 +00:00
2024-12-11 10:41:25 +00:00
app.state.config.TOP_K = RAG_TOP_K
2025-03-06 09:47:57 +00:00
app.state.config.TOP_K_RERANKER = RAG_TOP_K_RERANKER
2024-12-11 10:41:25 +00:00
app.state.config.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
app.state.config.HYBRID_BM25_WEIGHT = RAG_HYBRID_BM25_WEIGHT
2025-06-16 12:52:57 +00:00
2025-05-14 19:06:33 +00:00
app.state.config.ALLOWED_FILE_EXTENSIONS = RAG_ALLOWED_FILE_EXTENSIONS
2024-12-11 10:41:25 +00:00
app.state.config.FILE_MAX_SIZE = RAG_FILE_MAX_SIZE
app.state.config.FILE_MAX_COUNT = RAG_FILE_MAX_COUNT
2025-06-16 12:52:57 +00:00
app.state.config.FILE_IMAGE_COMPRESSION_WIDTH = FILE_IMAGE_COMPRESSION_WIDTH
app.state.config.FILE_IMAGE_COMPRESSION_HEIGHT = FILE_IMAGE_COMPRESSION_HEIGHT
2024-06-13 04:18:53 +00:00
2025-02-19 05:14:58 +00:00
app.state.config.RAG_FULL_CONTEXT = RAG_FULL_CONTEXT
2025-02-26 23:42:19 +00:00
app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL = BYPASS_EMBEDDING_AND_RETRIEVAL
2024-12-11 10:41:25 +00:00
app.state.config.ENABLE_RAG_HYBRID_SEARCH = ENABLE_RAG_HYBRID_SEARCH
2025-04-12 23:33:36 +00:00
app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION = ENABLE_WEB_LOADER_SSL_VERIFICATION
2024-06-13 04:18:53 +00:00
2024-12-11 10:41:25 +00:00
app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
app.state.config.DATALAB_MARKER_API_KEY = DATALAB_MARKER_API_KEY
2025-07-23 00:49:28 +00:00
app.state.config.DATALAB_MARKER_API_BASE_URL = DATALAB_MARKER_API_BASE_URL
app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG = DATALAB_MARKER_ADDITIONAL_CONFIG
app.state.config.DATALAB_MARKER_SKIP_CACHE = DATALAB_MARKER_SKIP_CACHE
app.state.config.DATALAB_MARKER_FORCE_OCR = DATALAB_MARKER_FORCE_OCR
app.state.config.DATALAB_MARKER_PAGINATE = DATALAB_MARKER_PAGINATE
app.state.config.DATALAB_MARKER_STRIP_EXISTING_OCR = DATALAB_MARKER_STRIP_EXISTING_OCR
2025-05-28 22:36:33 +00:00
app.state.config.DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION = (
DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION
)
2025-07-23 01:06:29 +00:00
app.state.config.DATALAB_MARKER_FORMAT_LINES = DATALAB_MARKER_FORMAT_LINES
app.state.config.DATALAB_MARKER_USE_LLM = DATALAB_MARKER_USE_LLM
app.state.config.DATALAB_MARKER_OUTPUT_FORMAT = DATALAB_MARKER_OUTPUT_FORMAT
2025-05-14 18:28:40 +00:00
app.state.config.EXTERNAL_DOCUMENT_LOADER_URL = EXTERNAL_DOCUMENT_LOADER_URL
app.state.config.EXTERNAL_DOCUMENT_LOADER_API_KEY = EXTERNAL_DOCUMENT_LOADER_API_KEY
2024-12-11 10:41:25 +00:00
app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
app.state.config.DOCLING_SERVER_URL = DOCLING_SERVER_URL
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
app.state.config.DOCLING_PARAMS = DOCLING_PARAMS
app.state.config.DOCLING_DO_OCR = DOCLING_DO_OCR
app.state.config.DOCLING_FORCE_OCR = DOCLING_FORCE_OCR
app.state.config.DOCLING_OCR_ENGINE = DOCLING_OCR_ENGINE
app.state.config.DOCLING_OCR_LANG = DOCLING_OCR_LANG
app.state.config.DOCLING_PDF_BACKEND = DOCLING_PDF_BACKEND
app.state.config.DOCLING_TABLE_MODE = DOCLING_TABLE_MODE
app.state.config.DOCLING_PIPELINE = DOCLING_PIPELINE
app.state.config.DOCLING_DO_PICTURE_DESCRIPTION = DOCLING_DO_PICTURE_DESCRIPTION
app.state.config.DOCLING_PICTURE_DESCRIPTION_MODE = DOCLING_PICTURE_DESCRIPTION_MODE
2025-06-08 16:02:14 +00:00
app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL = DOCLING_PICTURE_DESCRIPTION_LOCAL
app.state.config.DOCLING_PICTURE_DESCRIPTION_API = DOCLING_PICTURE_DESCRIPTION_API
app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
app.state.config.MINERU_API_MODE = MINERU_API_MODE
app.state.config.MINERU_API_URL = MINERU_API_URL
app.state.config.MINERU_API_KEY = MINERU_API_KEY
app.state.config.MINERU_PARAMS = MINERU_PARAMS
2024-12-11 10:41:25 +00:00
app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME
app.state.config.CHUNK_SIZE = CHUNK_SIZE
app.state.config.CHUNK_OVERLAP = CHUNK_OVERLAP
app.state.config.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
app.state.config.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
app.state.config.RAG_EMBEDDING_BATCH_SIZE = RAG_EMBEDDING_BATCH_SIZE
app.state.config.RAG_RERANKING_ENGINE = RAG_RERANKING_ENGINE
2024-12-11 10:41:25 +00:00
app.state.config.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
app.state.config.RAG_EXTERNAL_RERANKER_URL = RAG_EXTERNAL_RERANKER_URL
app.state.config.RAG_EXTERNAL_RERANKER_API_KEY = RAG_EXTERNAL_RERANKER_API_KEY
2024-12-11 10:41:25 +00:00
app.state.config.RAG_TEMPLATE = RAG_TEMPLATE
app.state.config.RAG_OPENAI_API_BASE_URL = RAG_OPENAI_API_BASE_URL
app.state.config.RAG_OPENAI_API_KEY = RAG_OPENAI_API_KEY
2025-05-20 02:58:04 +00:00
app.state.config.RAG_AZURE_OPENAI_BASE_URL = RAG_AZURE_OPENAI_BASE_URL
app.state.config.RAG_AZURE_OPENAI_API_KEY = RAG_AZURE_OPENAI_API_KEY
app.state.config.RAG_AZURE_OPENAI_API_VERSION = RAG_AZURE_OPENAI_API_VERSION
2025-05-20 02:58:04 +00:00
2024-12-11 10:41:25 +00:00
app.state.config.RAG_OLLAMA_BASE_URL = RAG_OLLAMA_BASE_URL
app.state.config.RAG_OLLAMA_API_KEY = RAG_OLLAMA_API_KEY
app.state.config.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
app.state.config.YOUTUBE_LOADER_LANGUAGE = YOUTUBE_LOADER_LANGUAGE
app.state.config.YOUTUBE_LOADER_PROXY_URL = YOUTUBE_LOADER_PROXY_URL
2025-04-12 23:33:36 +00:00
app.state.config.ENABLE_WEB_SEARCH = ENABLE_WEB_SEARCH
app.state.config.WEB_SEARCH_ENGINE = WEB_SEARCH_ENGINE
app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST = WEB_SEARCH_DOMAIN_FILTER_LIST
app.state.config.WEB_SEARCH_RESULT_COUNT = WEB_SEARCH_RESULT_COUNT
app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS = WEB_SEARCH_CONCURRENT_REQUESTS
2025-04-12 23:33:36 +00:00
app.state.config.WEB_LOADER_ENGINE = WEB_LOADER_ENGINE
app.state.config.WEB_LOADER_CONCURRENT_REQUESTS = WEB_LOADER_CONCURRENT_REQUESTS
2025-04-12 23:33:36 +00:00
app.state.config.WEB_SEARCH_TRUST_ENV = WEB_SEARCH_TRUST_ENV
2025-02-26 23:42:19 +00:00
app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
)
app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER = BYPASS_WEB_SEARCH_WEB_LOADER
2024-12-11 10:41:25 +00:00
2024-12-19 02:04:56 +00:00
app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = ENABLE_GOOGLE_DRIVE_INTEGRATION
2025-02-24 14:14:10 +00:00
app.state.config.ENABLE_ONEDRIVE_INTEGRATION = ENABLE_ONEDRIVE_INTEGRATION
2025-09-24 20:19:05 +00:00
app.state.config.OLLAMA_CLOUD_WEB_SEARCH_API_KEY = OLLAMA_CLOUD_WEB_SEARCH_API_KEY
2024-12-11 10:41:25 +00:00
app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
app.state.config.YACY_QUERY_URL = YACY_QUERY_URL
app.state.config.YACY_USERNAME = YACY_USERNAME
app.state.config.YACY_PASSWORD = YACY_PASSWORD
2024-12-11 10:41:25 +00:00
app.state.config.GOOGLE_PSE_API_KEY = GOOGLE_PSE_API_KEY
app.state.config.GOOGLE_PSE_ENGINE_ID = GOOGLE_PSE_ENGINE_ID
app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY
app.state.config.KAGI_SEARCH_API_KEY = KAGI_SEARCH_API_KEY
app.state.config.MOJEEK_SEARCH_API_KEY = MOJEEK_SEARCH_API_KEY
2025-02-10 08:44:47 +00:00
app.state.config.BOCHA_SEARCH_API_KEY = BOCHA_SEARCH_API_KEY
2024-12-11 10:41:25 +00:00
app.state.config.SERPSTACK_API_KEY = SERPSTACK_API_KEY
app.state.config.SERPSTACK_HTTPS = SERPSTACK_HTTPS
app.state.config.SERPER_API_KEY = SERPER_API_KEY
app.state.config.SERPLY_API_KEY = SERPLY_API_KEY
app.state.config.TAVILY_API_KEY = TAVILY_API_KEY
app.state.config.SEARCHAPI_API_KEY = SEARCHAPI_API_KEY
app.state.config.SEARCHAPI_ENGINE = SEARCHAPI_ENGINE
2025-02-14 04:24:58 +00:00
app.state.config.SERPAPI_API_KEY = SERPAPI_API_KEY
app.state.config.SERPAPI_ENGINE = SERPAPI_ENGINE
2024-12-11 10:41:25 +00:00
app.state.config.JINA_API_KEY = JINA_API_KEY
app.state.config.BING_SEARCH_V7_ENDPOINT = BING_SEARCH_V7_ENDPOINT
app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY = BING_SEARCH_V7_SUBSCRIPTION_KEY
app.state.config.EXA_API_KEY = EXA_API_KEY
app.state.config.PERPLEXITY_API_KEY = PERPLEXITY_API_KEY
app.state.config.PERPLEXITY_MODEL = PERPLEXITY_MODEL
app.state.config.PERPLEXITY_SEARCH_CONTEXT_USAGE = PERPLEXITY_SEARCH_CONTEXT_USAGE
app.state.config.SOUGOU_API_SID = SOUGOU_API_SID
app.state.config.SOUGOU_API_SK = SOUGOU_API_SK
app.state.config.EXTERNAL_WEB_SEARCH_URL = EXTERNAL_WEB_SEARCH_URL
app.state.config.EXTERNAL_WEB_SEARCH_API_KEY = EXTERNAL_WEB_SEARCH_API_KEY
app.state.config.EXTERNAL_WEB_LOADER_URL = EXTERNAL_WEB_LOADER_URL
app.state.config.EXTERNAL_WEB_LOADER_API_KEY = EXTERNAL_WEB_LOADER_API_KEY
2024-12-11 10:41:25 +00:00
2025-04-12 23:33:36 +00:00
app.state.config.PLAYWRIGHT_WS_URL = PLAYWRIGHT_WS_URL
2025-03-20 21:01:47 +00:00
app.state.config.PLAYWRIGHT_TIMEOUT = PLAYWRIGHT_TIMEOUT
app.state.config.FIRECRAWL_API_BASE_URL = FIRECRAWL_API_BASE_URL
app.state.config.FIRECRAWL_API_KEY = FIRECRAWL_API_KEY
app.state.config.TAVILY_EXTRACT_DEPTH = TAVILY_EXTRACT_DEPTH
2024-12-11 10:41:25 +00:00
2024-12-12 02:05:42 +00:00
app.state.EMBEDDING_FUNCTION = None
app.state.RERANKING_FUNCTION = None
2024-12-12 02:46:29 +00:00
app.state.ef = None
app.state.rf = None
2024-12-11 10:41:25 +00:00
app.state.YOUTUBE_LOADER_TRANSLATION = None
2024-12-12 02:05:42 +00:00
2024-12-11 10:41:25 +00:00
2024-12-25 02:39:53 +00:00
try:
app.state.ef = get_ef(
app.state.config.RAG_EMBEDDING_ENGINE,
app.state.config.RAG_EMBEDDING_MODEL,
RAG_EMBEDDING_MODEL_AUTO_UPDATE,
)
2025-08-21 11:40:56 +00:00
if (
app.state.config.ENABLE_RAG_HYBRID_SEARCH
and not app.state.config.BYPASS_EMBEDDING_AND_RETRIEVAL
):
app.state.rf = get_rf(
app.state.config.RAG_RERANKING_ENGINE,
app.state.config.RAG_RERANKING_MODEL,
app.state.config.RAG_EXTERNAL_RERANKER_URL,
app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
RAG_RERANKING_MODEL_AUTO_UPDATE,
)
else:
app.state.rf = None
2024-12-25 02:39:53 +00:00
except Exception as e:
log.error(f"Error updating models: {e}")
pass
2024-12-12 02:08:55 +00:00
app.state.EMBEDDING_FUNCTION = get_embedding_function(
app.state.config.RAG_EMBEDDING_ENGINE,
app.state.config.RAG_EMBEDDING_MODEL,
embedding_function=app.state.ef,
url=(
2024-12-12 02:46:29 +00:00
app.state.config.RAG_OPENAI_API_BASE_URL
2024-12-12 02:08:55 +00:00
if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
2025-05-20 02:58:04 +00:00
else (
app.state.config.RAG_OLLAMA_BASE_URL
if app.state.config.RAG_EMBEDDING_ENGINE == "ollama"
else app.state.config.RAG_AZURE_OPENAI_BASE_URL
)
2024-12-12 02:08:55 +00:00
),
key=(
2024-12-12 02:46:29 +00:00
app.state.config.RAG_OPENAI_API_KEY
2024-12-12 02:08:55 +00:00
if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
2025-05-20 02:58:04 +00:00
else (
app.state.config.RAG_OLLAMA_API_KEY
if app.state.config.RAG_EMBEDDING_ENGINE == "ollama"
else app.state.config.RAG_AZURE_OPENAI_API_KEY
)
2024-12-12 02:08:55 +00:00
),
embedding_batch_size=app.state.config.RAG_EMBEDDING_BATCH_SIZE,
azure_api_version=(
app.state.config.RAG_AZURE_OPENAI_API_VERSION
2025-05-20 02:58:04 +00:00
if app.state.config.RAG_EMBEDDING_ENGINE == "azure_openai"
else None
),
2024-12-12 02:08:55 +00:00
)
app.state.RERANKING_FUNCTION = get_reranking_function(
app.state.config.RAG_RERANKING_ENGINE,
app.state.config.RAG_RERANKING_MODEL,
reranking_function=app.state.rf,
)
2025-02-10 10:25:02 +00:00
########################################
#
2025-02-18 00:25:50 +00:00
# CODE EXECUTION
2025-02-10 10:25:02 +00:00
#
########################################
app.state.config.ENABLE_CODE_EXECUTION = ENABLE_CODE_EXECUTION
2025-02-18 00:25:50 +00:00
app.state.config.CODE_EXECUTION_ENGINE = CODE_EXECUTION_ENGINE
app.state.config.CODE_EXECUTION_JUPYTER_URL = CODE_EXECUTION_JUPYTER_URL
app.state.config.CODE_EXECUTION_JUPYTER_AUTH = CODE_EXECUTION_JUPYTER_AUTH
app.state.config.CODE_EXECUTION_JUPYTER_AUTH_TOKEN = CODE_EXECUTION_JUPYTER_AUTH_TOKEN
app.state.config.CODE_EXECUTION_JUPYTER_AUTH_PASSWORD = (
CODE_EXECUTION_JUPYTER_AUTH_PASSWORD
)
app.state.config.CODE_EXECUTION_JUPYTER_TIMEOUT = CODE_EXECUTION_JUPYTER_TIMEOUT
2025-02-18 00:25:50 +00:00
2025-02-10 10:25:02 +00:00
app.state.config.ENABLE_CODE_INTERPRETER = ENABLE_CODE_INTERPRETER
app.state.config.CODE_INTERPRETER_ENGINE = CODE_INTERPRETER_ENGINE
2025-02-12 05:36:16 +00:00
app.state.config.CODE_INTERPRETER_PROMPT_TEMPLATE = CODE_INTERPRETER_PROMPT_TEMPLATE
2025-02-10 10:25:02 +00:00
app.state.config.CODE_INTERPRETER_JUPYTER_URL = CODE_INTERPRETER_JUPYTER_URL
app.state.config.CODE_INTERPRETER_JUPYTER_AUTH = CODE_INTERPRETER_JUPYTER_AUTH
app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_TOKEN = (
CODE_INTERPRETER_JUPYTER_AUTH_TOKEN
)
app.state.config.CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD = (
CODE_INTERPRETER_JUPYTER_AUTH_PASSWORD
)
app.state.config.CODE_INTERPRETER_JUPYTER_TIMEOUT = CODE_INTERPRETER_JUPYTER_TIMEOUT
2024-06-12 20:34:34 +00:00
2024-12-10 08:54:13 +00:00
########################################
#
# IMAGES
#
########################################
2024-07-02 02:33:58 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.IMAGE_GENERATION_ENGINE = IMAGE_GENERATION_ENGINE
app.state.config.ENABLE_IMAGE_GENERATION = ENABLE_IMAGE_GENERATION
2025-01-16 08:13:02 +00:00
app.state.config.ENABLE_IMAGE_PROMPT_GENERATION = ENABLE_IMAGE_PROMPT_GENERATION
2024-06-09 21:53:10 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.IMAGES_OPENAI_API_BASE_URL = IMAGES_OPENAI_API_BASE_URL
app.state.config.IMAGES_OPENAI_API_VERSION = IMAGES_OPENAI_API_VERSION
2024-12-10 08:54:13 +00:00
app.state.config.IMAGES_OPENAI_API_KEY = IMAGES_OPENAI_API_KEY
2024-06-09 21:53:10 +00:00
app.state.config.IMAGES_GEMINI_API_BASE_URL = IMAGES_GEMINI_API_BASE_URL
app.state.config.IMAGES_GEMINI_API_KEY = IMAGES_GEMINI_API_KEY
2024-12-10 08:54:13 +00:00
app.state.config.IMAGE_GENERATION_MODEL = IMAGE_GENERATION_MODEL
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
app.state.config.AUTOMATIC1111_API_AUTH = AUTOMATIC1111_API_AUTH
app.state.config.AUTOMATIC1111_CFG_SCALE = AUTOMATIC1111_CFG_SCALE
app.state.config.AUTOMATIC1111_SAMPLER = AUTOMATIC1111_SAMPLER
app.state.config.AUTOMATIC1111_SCHEDULER = AUTOMATIC1111_SCHEDULER
app.state.config.COMFYUI_BASE_URL = COMFYUI_BASE_URL
2024-12-17 07:29:00 +00:00
app.state.config.COMFYUI_API_KEY = COMFYUI_API_KEY
2024-12-10 08:54:13 +00:00
app.state.config.COMFYUI_WORKFLOW = COMFYUI_WORKFLOW
app.state.config.COMFYUI_WORKFLOW_NODES = COMFYUI_WORKFLOW_NODES
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.IMAGE_SIZE = IMAGE_SIZE
app.state.config.IMAGE_STEPS = IMAGE_STEPS
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
########################################
#
# AUDIO
#
########################################
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
app.state.config.STT_MODEL = AUDIO_STT_MODEL
app.state.config.STT_SUPPORTED_CONTENT_TYPES = AUDIO_STT_SUPPORTED_CONTENT_TYPES
app.state.config.STT_OPENAI_API_BASE_URL = AUDIO_STT_OPENAI_API_BASE_URL
app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.WHISPER_MODEL = WHISPER_MODEL
2025-04-14 06:39:38 +00:00
app.state.config.WHISPER_VAD_FILTER = WHISPER_VAD_FILTER
2025-02-02 13:58:59 +00:00
app.state.config.DEEPGRAM_API_KEY = DEEPGRAM_API_KEY
2024-08-18 18:59:59 +00:00
app.state.config.AUDIO_STT_AZURE_API_KEY = AUDIO_STT_AZURE_API_KEY
app.state.config.AUDIO_STT_AZURE_REGION = AUDIO_STT_AZURE_REGION
app.state.config.AUDIO_STT_AZURE_LOCALES = AUDIO_STT_AZURE_LOCALES
app.state.config.AUDIO_STT_AZURE_BASE_URL = AUDIO_STT_AZURE_BASE_URL
app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS = AUDIO_STT_AZURE_MAX_SPEAKERS
2024-12-10 08:54:13 +00:00
app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.TTS_MODEL = AUDIO_TTS_MODEL
app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
app.state.config.TTS_OPENAI_PARAMS = AUDIO_TTS_OPENAI_PARAMS
2024-12-10 08:54:13 +00:00
app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
app.state.config.TTS_SPLIT_ON = AUDIO_TTS_SPLIT_ON
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.TTS_AZURE_SPEECH_REGION = AUDIO_TTS_AZURE_SPEECH_REGION
2025-05-06 02:08:48 +00:00
app.state.config.TTS_AZURE_SPEECH_BASE_URL = AUDIO_TTS_AZURE_SPEECH_BASE_URL
2024-12-10 08:54:13 +00:00
app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
app.state.faster_whisper_model = None
app.state.speech_synthesiser = None
app.state.speech_speaker_embeddings_dataset = None
2024-08-18 18:59:59 +00:00
2024-12-10 08:54:13 +00:00
########################################
2024-06-20 08:51:39 +00:00
#
2024-12-10 08:54:13 +00:00
# TASKS
2024-06-20 08:51:39 +00:00
#
2024-12-10 08:54:13 +00:00
########################################
2024-05-30 09:04:29 +00:00
2024-06-09 21:53:10 +00:00
app.state.config.TASK_MODEL = TASK_MODEL
app.state.config.TASK_MODEL_EXTERNAL = TASK_MODEL_EXTERNAL
2024-05-30 09:04:29 +00:00
2024-05-30 05:41:51 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.ENABLE_SEARCH_QUERY_GENERATION = ENABLE_SEARCH_QUERY_GENERATION
app.state.config.ENABLE_RETRIEVAL_QUERY_GENERATION = ENABLE_RETRIEVAL_QUERY_GENERATION
2024-12-01 02:30:59 +00:00
app.state.config.ENABLE_AUTOCOMPLETE_GENERATION = ENABLE_AUTOCOMPLETE_GENERATION
app.state.config.ENABLE_TAGS_GENERATION = ENABLE_TAGS_GENERATION
app.state.config.ENABLE_TITLE_GENERATION = ENABLE_TITLE_GENERATION
2025-06-03 14:07:29 +00:00
app.state.config.ENABLE_FOLLOW_UP_GENERATION = ENABLE_FOLLOW_UP_GENERATION
2024-12-10 08:54:13 +00:00
app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE = TITLE_GENERATION_PROMPT_TEMPLATE
app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE = TAGS_GENERATION_PROMPT_TEMPLATE
2025-01-16 08:06:37 +00:00
app.state.config.IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE = (
IMAGE_PROMPT_GENERATION_PROMPT_TEMPLATE
)
2025-06-03 14:07:29 +00:00
app.state.config.FOLLOW_UP_GENERATION_PROMPT_TEMPLATE = (
FOLLOW_UP_GENERATION_PROMPT_TEMPLATE
)
2025-01-16 08:06:37 +00:00
2024-12-10 08:54:13 +00:00
app.state.config.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = (
TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE
)
2024-11-19 10:24:32 +00:00
app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE = QUERY_GENERATION_PROMPT_TEMPLATE
2024-11-29 07:53:52 +00:00
app.state.config.AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE = (
AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE
)
2024-12-10 08:54:13 +00:00
app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = (
AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH
2024-06-11 06:40:27 +00:00
)
2024-06-05 20:57:48 +00:00
2024-12-11 11:38:45 +00:00
########################################
#
# WEBUI
#
########################################
2024-06-05 20:57:48 +00:00
2024-12-11 11:38:45 +00:00
app.state.MODELS = {}
2024-06-05 20:57:48 +00:00
2024-10-08 01:19:13 +00:00
class RedirectMiddleware(BaseHTTPMiddleware):
async def dispatch(self, request: Request, call_next):
# Check if the request is a GET request
if request.method == "GET":
path = request.url.path
query_params = dict(parse_qs(urlparse(str(request.url)).query))
2024-06-05 20:57:48 +00:00
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
redirect_params = {}
2024-10-08 01:19:13 +00:00
# Check for the specific watch path and the presence of 'v' parameter
if path.endswith("/watch") and "v" in query_params:
# Extract the first 'v' parameter
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
youtube_video_id = query_params["v"][0]
redirect_params["youtube"] = youtube_video_id
if "shared" in query_params and len(query_params["shared"]) > 0:
# PWA share_target support
text = query_params["shared"][0]
if text:
urls = re.match(r"https://\S+", text)
if urls:
from open_webui.retrieval.loaders.youtube import _parse_video_id
if youtube_video_id := _parse_video_id(urls[0]):
redirect_params["youtube"] = youtube_video_id
else:
redirect_params["load-url"] = urls[0]
else:
redirect_params["q"] = text
if redirect_params:
redirect_url = f"/?{urlencode(redirect_params)}"
2024-10-08 01:19:13 +00:00
return RedirectResponse(url=redirect_url)
2024-06-05 20:57:48 +00:00
2024-10-08 01:19:13 +00:00
# Proceed with the normal flow of other requests
response = await call_next(request)
return response
2024-06-05 20:57:48 +00:00
2024-10-08 01:19:13 +00:00
# Add the middleware to the app
if ENABLE_COMPRESSION_MIDDLEWARE:
app.add_middleware(CompressMiddleware)
2024-10-08 01:19:13 +00:00
app.add_middleware(RedirectMiddleware)
2024-09-17 00:53:30 +00:00
app.add_middleware(SecurityHeadersMiddleware)
2024-06-05 20:57:48 +00:00
@app.middleware("http")
2024-06-24 11:45:33 +00:00
async def commit_session_after_request(request: Request, call_next):
response = await call_next(request)
2024-11-23 04:11:46 +00:00
# log.debug("Commit session after request")
Session.commit()
return response
2024-06-05 20:57:48 +00:00
2024-05-30 05:03:22 +00:00
2023-11-15 00:28:51 +00:00
@app.middleware("http")
async def check_url(request: Request, call_next):
start_time = int(time.time())
2025-04-05 10:05:52 +00:00
request.state.token = get_http_authorization_cred(
request.headers.get("Authorization")
)
2024-12-12 02:53:38 +00:00
request.state.enable_api_key = app.state.config.ENABLE_API_KEY
2023-11-15 00:28:51 +00:00
response = await call_next(request)
process_time = int(time.time()) - start_time
response.headers["X-Process-Time"] = str(process_time)
return response
2024-05-30 05:03:22 +00:00
@app.middleware("http")
async def inspect_websocket(request: Request, call_next):
if (
2024-10-21 01:38:06 +00:00
"/ws/socket.io" in request.url.path
and request.query_params.get("transport") == "websocket"
):
upgrade = (request.headers.get("Upgrade") or "").lower()
connection = (request.headers.get("Connection") or "").lower().split(",")
# Check that there's the correct headers for an upgrade, else reject the connection
# This is to work around this upstream issue: https://github.com/miguelgrinberg/python-engineio/issues/367
if upgrade != "websocket" or "upgrade" not in connection:
return JSONResponse(
status_code=status.HTTP_400_BAD_REQUEST,
content={"detail": "Invalid WebSocket upgrade request"},
)
return await call_next(request)
2024-05-30 05:03:22 +00:00
2024-12-10 08:54:13 +00:00
app.add_middleware(
CORSMiddleware,
allow_origins=CORS_ALLOW_ORIGIN,
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
2024-05-30 05:03:22 +00:00
2024-06-04 06:39:52 +00:00
app.mount("/ws", socket_app)
2024-05-30 05:03:22 +00:00
2024-12-12 02:36:59 +00:00
app.include_router(ollama.router, prefix="/ollama", tags=["ollama"])
app.include_router(openai.router, prefix="/openai", tags=["openai"])
2024-05-30 05:03:22 +00:00
2024-12-13 04:22:17 +00:00
app.include_router(pipelines.router, prefix="/api/v1/pipelines", tags=["pipelines"])
app.include_router(tasks.router, prefix="/api/v1/tasks", tags=["tasks"])
2024-12-12 01:50:48 +00:00
app.include_router(images.router, prefix="/api/v1/images", tags=["images"])
2025-02-10 10:25:02 +00:00
2024-12-12 01:50:48 +00:00
app.include_router(audio.router, prefix="/api/v1/audio", tags=["audio"])
app.include_router(retrieval.router, prefix="/api/v1/retrieval", tags=["retrieval"])
2024-05-30 05:03:22 +00:00
2024-12-11 10:41:25 +00:00
app.include_router(configs.router, prefix="/api/v1/configs", tags=["configs"])
2024-05-30 05:03:22 +00:00
2024-12-11 10:41:25 +00:00
app.include_router(auths.router, prefix="/api/v1/auths", tags=["auths"])
app.include_router(users.router, prefix="/api/v1/users", tags=["users"])
2024-05-30 05:03:22 +00:00
app.include_router(
user_models.router, prefix="/api/v1/user/models", tags=["user_models"]
)
2024-12-22 10:42:19 +00:00
app.include_router(channels.router, prefix="/api/v1/channels", tags=["channels"])
2024-12-11 10:41:25 +00:00
app.include_router(chats.router, prefix="/api/v1/chats", tags=["chats"])
2025-05-03 14:16:32 +00:00
app.include_router(notes.router, prefix="/api/v1/notes", tags=["notes"])
2024-05-30 05:03:22 +00:00
2024-12-11 10:41:25 +00:00
app.include_router(models.router, prefix="/api/v1/models", tags=["models"])
app.include_router(knowledge.router, prefix="/api/v1/knowledge", tags=["knowledge"])
app.include_router(prompts.router, prefix="/api/v1/prompts", tags=["prompts"])
app.include_router(tools.router, prefix="/api/v1/tools", tags=["tools"])
2024-05-30 05:03:22 +00:00
2024-12-11 10:41:25 +00:00
app.include_router(memories.router, prefix="/api/v1/memories", tags=["memories"])
app.include_router(folders.router, prefix="/api/v1/folders", tags=["folders"])
app.include_router(groups.router, prefix="/api/v1/groups", tags=["groups"])
app.include_router(files.router, prefix="/api/v1/files", tags=["files"])
app.include_router(functions.router, prefix="/api/v1/functions", tags=["functions"])
app.include_router(
evaluations.router, prefix="/api/v1/evaluations", tags=["evaluations"]
)
app.include_router(utils.router, prefix="/api/v1/utils", tags=["utils"])
2024-05-30 05:03:22 +00:00
# SCIM 2.0 API for identity management
2025-08-06 10:25:42 +00:00
if SCIM_ENABLED:
app.include_router(scim.router, prefix="/api/v1/scim/v2", tags=["scim"])
2024-05-30 05:03:22 +00:00
try:
audit_level = AuditLevel(AUDIT_LOG_LEVEL)
except ValueError as e:
logger.error(f"Invalid audit level: {AUDIT_LOG_LEVEL}. Error: {e}")
audit_level = AuditLevel.NONE
if audit_level != AuditLevel.NONE:
app.add_middleware(
AuditLoggingMiddleware,
audit_level=audit_level,
excluded_paths=AUDIT_EXCLUDED_PATHS,
max_body_size=MAX_BODY_LOG_SIZE,
)
2024-12-12 02:36:59 +00:00
##################################
#
# Chat Endpoints
#
##################################
2024-05-30 05:03:22 +00:00
2024-12-13 04:22:17 +00:00
@app.get("/api/models")
2025-08-10 20:45:59 +00:00
@app.get("/api/v1/models") # Experimental: Compatibility with OpenAI API
2025-06-28 11:12:31 +00:00
async def get_models(
request: Request, refresh: bool = False, user=Depends(get_verified_user)
):
2025-06-28 15:15:52 +00:00
all_models = await get_all_models(request, refresh=refresh, user=user)
2025-03-11 20:37:30 +00:00
models = []
for model in all_models:
# Filter out filter pipelines
if "pipeline" in model and model["pipeline"].get("type", None) == "filter":
continue
2025-04-14 00:28:09 +00:00
try:
model_tags = [
tag.get("name")
for tag in model.get("info", {}).get("meta", {}).get("tags", [])
]
tags = [tag.get("name") for tag in model.get("tags", [])]
tags = list(set(model_tags + tags))
model["tags"] = [{"name": tag} for tag in tags]
except Exception as e:
log.debug(f"Error processing model tags: {e}")
model["tags"] = []
pass
2024-05-28 19:04:19 +00:00
2025-03-11 20:37:30 +00:00
models.append(model)
2024-05-30 05:18:27 +00:00
2024-12-13 04:22:17 +00:00
model_order_list = request.app.state.config.MODEL_ORDER_LIST
if model_order_list:
model_order_dict = {model_id: i for i, model_id in enumerate(model_order_list)}
# Sort models by order list priority, with fallback for those not in the list
models.sort(
2025-08-13 14:18:30 +00:00
key=lambda model: (
model_order_dict.get(model.get("id", ""), float("inf")),
(model.get("name", "") or ""),
2025-08-13 14:18:30 +00:00
)
2024-05-30 05:18:27 +00:00
)
2024-05-28 19:32:49 +00:00
2025-09-17 04:19:21 +00:00
models = get_filtered_models(models, user)
2024-05-28 19:32:49 +00:00
2024-11-23 04:11:46 +00:00
log.debug(
2025-07-31 12:17:33 +00:00
f"/api/models returned filtered models accessible to the user: {json.dumps([model.get('id') for model in models])}"
2024-11-23 04:11:46 +00:00
)
2024-05-24 08:40:48 +00:00
return {"data": models}
2024-05-28 19:32:49 +00:00
2024-11-16 03:14:24 +00:00
@app.get("/api/models/base")
2024-12-12 04:26:24 +00:00
async def get_base_models(request: Request, user=Depends(get_admin_user)):
models = await get_all_base_models(request, user=user)
2024-11-16 03:14:24 +00:00
return {"data": models}
2024-05-28 19:32:49 +00:00
2024-05-28 20:05:31 +00:00
2025-06-04 20:37:31 +00:00
##################################
# Embeddings
##################################
@app.post("/api/embeddings")
2025-08-10 20:45:59 +00:00
@app.post("/api/v1/embeddings") # Experimental: Compatibility with OpenAI API
2025-06-04 20:37:31 +00:00
async def embeddings(
request: Request, form_data: dict, user=Depends(get_verified_user)
):
"""
OpenAI-compatible embeddings endpoint.
This handler:
- Performs user/model checks and dispatches to the correct backend.
- Supports OpenAI, Ollama, arena models, pipelines, and any compatible provider.
Args:
request (Request): Request context.
form_data (dict): OpenAI-like payload (e.g., {"model": "...", "input": [...]})
user (UserModel): Authenticated user.
Returns:
dict: OpenAI-compatible embeddings response.
"""
# Make sure models are loaded in app state
if not request.app.state.MODELS:
await get_all_models(request, user=user)
# Use generic dispatcher in utils.embeddings
return await generate_embeddings(request, form_data, user)
2024-12-12 02:05:42 +00:00
@app.post("/api/chat/completions")
2025-08-10 20:45:59 +00:00
@app.post("/api/v1/chat/completions") # Experimental: Compatibility with OpenAI API
2024-12-13 04:22:17 +00:00
async def chat_completion(
2024-12-12 04:39:55 +00:00
request: Request,
2024-12-12 02:05:42 +00:00
form_data: dict,
user=Depends(get_verified_user),
):
"""
聊天完成接口 - 处理用户与 AI 模型的对话请求
核心功能:
1. 模型验证: 检查模型是否存在及用户访问权限
2. 元数据构建: 提取 chat_id, message_id, session_id 等上下文信息
3. Payload 处理: 通过 process_chat_payload 处理消息工具调用文件等
4. 聊天执行: 调用 chat_completion_handler LLM 交互
5. 响应处理: 通过 process_chat_response 处理流式/非流式响应
6. 异步任务: 如果有 session_id创建后台任务异步执行
Args:
request: FastAPI Request 对象
form_data: 聊天请求数据包含:
- model: 模型 ID
- messages: 对话历史 (OpenAI 格式)
- chat_id: 聊天会话 ID
- id: 消息 ID
- session_id: 会话 ID (用于异步任务)
- tool_ids: 工具 ID 列表
- files: 附加文件列表
- stream: 是否流式响应
user: 已验证的用户对象
Returns:
- 同步模式: 返回 LLM 响应 (流式 StreamingResponse 或完整 JSON)
- 异步模式: 返回 {"status": True, "task_id": "xxx"}
Raises:
HTTPException 400: 模型不存在无访问权限参数错误
HTTPException 404: Chat 不存在
处理流程:
1. 加载所有模型到 app.state.MODELS
2. 验证模型访问权限 (check_model_access)
3. 构建 metadata (包含 user_id, chat_id, tool_ids )
4. 定义 process_chat 内部函数:
- 调用 process_chat_payload (处理 Pipeline/Filter/Tools)
- 调用 chat_completion_handler ( LLM 交互)
- 更新数据库消息记录
- 调用 process_chat_response (处理响应事件发射)
5. 根据是否有 session_id 决定同步/异步执行
"""
# === 1. 初始化阶段:加载模型列表 ===
2024-12-13 06:32:28 +00:00
if not request.app.state.MODELS:
await get_all_models(request, user=user) # 从数据库和后端服务加载所有可用模型
2024-12-13 06:28:42 +00:00
# === 2. 提取请求参数 ===
model_id = form_data.get("model", None) # 用户选择的模型 ID (如 "gpt-4")
model_item = form_data.pop("model_item", {}) # 模型元数据 (包含 direct 标志)
tasks = form_data.pop("background_tasks", None) # 后台任务列表
2025-02-13 06:56:33 +00:00
metadata = {}
2024-12-13 06:28:42 +00:00
try:
# === 3. 模型验证与权限检查 ===
2025-02-13 06:56:33 +00:00
if not model_item.get("direct", False):
# 标准模式:使用平台内置模型
2025-02-13 06:56:33 +00:00
if model_id not in request.app.state.MODELS:
raise Exception("Model not found")
model = request.app.state.MODELS[model_id] # 从缓存获取模型配置
model_info = Models.get_model_by_id(model_id) # 从数据库获取模型详细信息
2025-02-13 06:56:33 +00:00
# 检查用户是否有权限访问该模型
if not BYPASS_MODEL_ACCESS_CONTROL and (
user.role != "admin" or not BYPASS_ADMIN_ACCESS_CONTROL
):
2025-02-13 06:56:33 +00:00
try:
check_model_access(user, model) # 检查 RBAC 权限
2025-02-13 06:56:33 +00:00
except Exception as e:
raise e
else:
# Direct 模式:用户直接传入 OpenAI API 等外部模型配置
2025-02-13 06:56:33 +00:00
model = model_item
model_info = None
request.state.direct = True # 标记为直连模式
2025-02-13 06:56:33 +00:00
request.state.model = model
2024-05-28 19:32:49 +00:00
# === 4. 提取模型参数 ===
2025-08-09 21:29:51 +00:00
model_info_params = (
model_info.params.model_dump() if model_info and model_info.params else {}
)
# 流式响应分块大小 (用于控制 SSE 推送频率)
stream_delta_chunk_size = form_data.get("params", {}).get(
"stream_delta_chunk_size"
)
# 推理标签 (用于标记 AI 的思考过程,如 <think>...</think>)
2025-08-27 13:24:16 +00:00
reasoning_tags = form_data.get("params", {}).get("reasoning_tags")
2025-08-09 21:29:51 +00:00
# 模型参数优先级高于请求参数
2025-08-09 21:31:07 +00:00
if model_info_params.get("stream_delta_chunk_size"):
2025-08-09 21:29:51 +00:00
stream_delta_chunk_size = model_info_params.get("stream_delta_chunk_size")
2025-08-27 13:24:16 +00:00
if model_info_params.get("reasoning_tags") is not None:
reasoning_tags = model_info_params.get("reasoning_tags")
# === 5. 构建元数据 (metadata) - 贯穿整个处理流程的上下文 ===
2024-12-19 02:04:56 +00:00
metadata = {
2024-12-19 09:00:32 +00:00
"user_id": user.id,
"chat_id": form_data.pop("chat_id", None), # 聊天会话 ID
"message_id": form_data.pop("id", None), # 当前消息 ID
"session_id": form_data.pop("session_id", None), # WebSocket 会话 ID (异步任务)
"filter_ids": form_data.pop("filter_ids", []), # Pipeline Filter ID 列表
"tool_ids": form_data.get("tool_ids", None), # 工具/函数调用 ID 列表
"tool_servers": form_data.pop("tool_servers", None), # 外部工具服务器配置
"files": form_data.get("files", None), # 用户上传的文件列表
"features": form_data.get("features", {}), # 功能开关 (如 web_search)
"variables": form_data.get("variables", {}), # 模板变量
"model": model, # 模型配置对象
"direct": model_item.get("direct", False), # 是否直连模式
"params": {
"stream_delta_chunk_size": stream_delta_chunk_size,
2025-08-27 13:24:16 +00:00
"reasoning_tags": reasoning_tags,
"function_calling": (
"native" # 原生函数调用 (如 OpenAI Function Calling)
if (
form_data.get("params", {}).get("function_calling") == "native"
2025-08-09 21:29:51 +00:00
or model_info_params.get("function_calling") == "native"
)
else "default" # 默认模式 (通过 Prompt 实现)
),
},
2024-12-19 02:04:56 +00:00
}
2025-02-13 08:34:45 +00:00
# === 6. 权限二次验证:检查用户是否拥有该 chat ===
2025-08-09 17:10:12 +00:00
if metadata.get("chat_id") and (user and user.role != "admin"):
if not metadata["chat_id"].startswith("local:"): # local: 前缀表示临时会话
2025-08-13 15:18:30 +00:00
chat = Chats.get_chat_by_id_and_user_id(metadata["chat_id"], user.id)
if chat is None:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=ERROR_MESSAGES.DEFAULT(),
)
2025-08-09 17:10:12 +00:00
# === 7. 保存元数据到请求状态和 form_data ===
request.state.metadata = metadata # 供其他中间件/处理器访问
form_data["metadata"] = metadata # 传递给下游处理函数
2024-12-19 02:04:56 +00:00
2024-12-13 06:28:42 +00:00
except Exception as e:
2025-08-18 21:24:53 +00:00
log.debug(f"Error processing chat metadata: {e}")
2024-05-28 19:32:49 +00:00
raise HTTPException(
2024-12-13 06:28:42 +00:00
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e),
2024-05-28 19:32:49 +00:00
)
# === 8. 定义内部处理函数 process_chat ===
2025-08-18 21:24:53 +00:00
async def process_chat(request, form_data, user, metadata, model):
"""处理完整的聊天流程Payload 处理 → LLM 调用 → 响应处理"""
2025-08-18 21:24:53 +00:00
try:
# 8.1 Payload 预处理:执行 Pipeline Filters、工具注入、RAG 检索等
# remark并不涉及消息的持久化只涉及发送给 LLM 前,上下文的封装
2025-08-18 21:24:53 +00:00
form_data, metadata, events = await process_chat_payload(
request, form_data, user, metadata, model
)
2025-02-05 05:01:53 +00:00
# 8.2 调用 LLM 完成对话 (核心)
response = await chat_completion_handler(request, form_data, user, chatting_completion = True)
# 8.3 更新数据库:保存模型 ID 到消息记录
2025-08-18 21:24:53 +00:00
if metadata.get("chat_id") and metadata.get("message_id"):
try:
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
if not metadata["chat_id"].startswith("local:"):
Chats.upsert_message_to_chat_by_id_and_message_id(
metadata["chat_id"],
metadata["message_id"],
{
"model": model_id,
},
)
2025-08-18 21:24:53 +00:00
except:
pass
# 8.4 响应后处理:执行后置 Pipeline、事件发射、任务回调等
2025-08-18 21:24:53 +00:00
return await process_chat_response(
request, response, form_data, user, metadata, model, events, tasks
)
# 8.5 异常处理:取消任务
2025-08-18 21:24:53 +00:00
except asyncio.CancelledError:
log.info("Chat processing was cancelled")
2025-08-13 14:18:30 +00:00
try:
2025-08-18 21:24:53 +00:00
event_emitter = get_event_emitter(metadata)
await event_emitter(
{"type": "chat:tasks:cancel"}, # 通知前端任务已取消
2025-08-13 14:18:30 +00:00
)
2025-08-18 21:24:53 +00:00
except Exception as e:
2025-08-13 14:18:30 +00:00
pass
# 8.6 异常处理:记录错误到数据库并通知前端
2025-08-18 21:24:53 +00:00
except Exception as e:
log.debug(f"Error processing chat payload: {e}")
if metadata.get("chat_id") and metadata.get("message_id"):
try:
# 将错误信息保存到消息记录
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
if not metadata["chat_id"].startswith("local:"):
Chats.upsert_message_to_chat_by_id_and_message_id(
metadata["chat_id"],
metadata["message_id"],
{
"error": {"content": str(e)},
},
)
2025-09-01 10:14:20 +00:00
# 通过 WebSocket 发送错误事件到前端
2025-09-01 10:14:20 +00:00
event_emitter = get_event_emitter(metadata)
await event_emitter(
{
"type": "chat:message:error",
"data": {"error": {"content": str(e)}},
}
)
await event_emitter(
{"type": "chat:tasks:cancel"},
)
2025-08-18 21:24:53 +00:00
except:
pass
# 8.7 清理资源:断开 MCP 客户端连接
2025-09-23 06:03:26 +00:00
finally:
try:
if mcp_clients := metadata.get("mcp_clients"):
2025-09-28 17:42:02 +00:00
for client in mcp_clients.values():
await client.disconnect() # 断开 Model Context Protocol 客户端
2025-09-23 06:03:26 +00:00
except Exception as e:
log.debug(f"Error cleaning up: {e}")
pass
2025-06-16 09:45:36 +00:00
# === 9. 决定执行模式:异步任务 vs 同步执行 ===
2025-08-18 21:24:53 +00:00
if (
metadata.get("session_id")
and metadata.get("chat_id")
and metadata.get("message_id")
):
# 异步模式:创建后台任务,立即返回 task_id 给前端
# 前端通过 WebSocket 监听任务状态和流式响应
2025-08-18 21:24:53 +00:00
task_id, _ = await create_task(
request.app.state.redis,
process_chat(request, form_data, user, metadata, model),
id=metadata["chat_id"],
2024-05-28 19:32:49 +00:00
)
2025-08-18 21:24:53 +00:00
return {"status": True, "task_id": task_id}
else:
# 同步模式:直接执行并返回响应 (流式或完整)
2025-08-18 21:24:53 +00:00
return await process_chat(request, form_data, user, metadata, model)
2024-05-28 19:32:49 +00:00
2024-12-13 06:28:42 +00:00
# Alias for chat_completion (Legacy)
2024-12-13 04:22:17 +00:00
generate_chat_completions = chat_completion
generate_chat_completion = chat_completion
2024-12-12 02:05:42 +00:00
@app.post("/api/chat/tutorial")
async def chat_completion_tutorial(
request: Request, form_data: dict, user=Depends(get_verified_user)
):
"""
最小可正常工作的示例复用核心聊天链路支持直连/历史消息/流式返回
- 入参与 /api/chat/completions 基本兼容但不做额外后台任务
- 若提供 chat_id/message_id会读取历史消息并可触发 WS 事件否则直接返回 SSE
"""
# 直连兼容
model_item = form_data.pop("model_item", {})
if model_item.get("direct"):
request.state.direct = True
request.state.model = model_item
# 确保模型可用
if not request.app.state.MODELS:
await get_all_models(request, user=user)
model_id = form_data.get("model") or next(iter(request.app.state.MODELS.keys()))
if model_id not in request.app.state.MODELS:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST, detail="Model not found"
)
model = request.app.state.MODELS[model_id]
if user.role == "user":
check_model_access(user, model)
# 取消息历史:优先用传入 messages否则按 chat_id 取全量
messages = form_data.get("messages") or []
chat_id = form_data.get("chat_id")
message_id = form_data.get("id") or form_data.get("message_id")
if not messages and chat_id:
messages_map = Chats.get_messages_map_by_chat_id(chat_id)
if messages_map:
if message_id and message_id in messages_map:
messages = get_message_list(messages_map, message_id)
else:
messages = list(messages_map.values())
# 准备 metadata便于复用后续事件/DB 逻辑
metadata = {
"user_id": user.id,
"chat_id": chat_id,
"message_id": message_id,
"session_id": form_data.get("session_id"),
"model": model,
"direct": model_item.get("direct", False),
"params": {},
}
request.state.metadata = metadata
form_data["metadata"] = metadata
# 核心链路:预处理 -> 调模型 -> 流式/非流式响应处理
form_data["model"] = model_id
form_data["messages"] = messages
form_data["stream"] = True # 强制流式,便于示例
form_data, metadata, events = await process_chat_payload(
request, form_data, user, metadata, model
)
response = await chat_completion_handler(request, form_data, user)
return await process_chat_response(
request, response, form_data, user, metadata, model, events, tasks=None
)
2024-12-12 02:05:42 +00:00
@app.post("/api/chat/completed")
2024-12-12 03:52:46 +00:00
async def chat_completed(
request: Request, form_data: dict, user=Depends(get_verified_user)
2024-05-28 19:32:49 +00:00
):
2024-05-30 05:18:27 +00:00
try:
2025-02-13 06:56:33 +00:00
model_item = form_data.pop("model_item", {})
if model_item.get("direct", False):
request.state.direct = True
request.state.model = model_item
2024-12-13 04:22:17 +00:00
return await chat_completed_handler(request, form_data, user)
2024-12-12 03:52:46 +00:00
except Exception as e:
2024-12-13 04:22:17 +00:00
raise HTTPException(
2024-12-12 03:52:46 +00:00
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e),
2024-05-30 05:18:27 +00:00
)
2024-05-28 19:32:49 +00:00
2024-12-12 02:05:42 +00:00
@app.post("/api/chat/actions/{action_id}")
2024-12-12 04:39:55 +00:00
async def chat_action(
request: Request, action_id: str, form_data: dict, user=Depends(get_verified_user)
):
2024-12-13 04:22:17 +00:00
try:
2025-02-13 06:56:33 +00:00
model_item = form_data.pop("model_item", {})
if model_item.get("direct", False):
request.state.direct = True
request.state.model = model_item
2024-12-13 04:22:17 +00:00
return await chat_action_handler(request, action_id, form_data, user)
2024-05-30 05:18:27 +00:00
except Exception as e:
2024-05-28 19:32:49 +00:00
raise HTTPException(
2024-12-13 04:22:17 +00:00
status_code=status.HTTP_400_BAD_REQUEST,
detail=str(e),
2024-05-28 19:32:49 +00:00
)
2024-12-19 09:00:32 +00:00
@app.post("/api/tasks/stop/{task_id}")
2025-06-08 16:58:31 +00:00
async def stop_task_endpoint(
request: Request, task_id: str, user=Depends(get_verified_user)
):
2024-12-19 09:00:32 +00:00
try:
2025-07-11 13:53:53 +00:00
result = await stop_task(request.app.state.redis, task_id)
2024-12-19 09:00:32 +00:00
return result
except ValueError as e:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(e))
@app.get("/api/tasks")
2025-06-08 16:58:31 +00:00
async def list_tasks_endpoint(request: Request, user=Depends(get_verified_user)):
2025-07-11 13:53:53 +00:00
return {"tasks": await list_tasks(request.app.state.redis)}
2025-04-13 03:51:02 +00:00
@app.get("/api/tasks/chat/{chat_id}")
2025-06-08 16:58:31 +00:00
async def list_tasks_by_chat_id_endpoint(
request: Request, chat_id: str, user=Depends(get_verified_user)
):
2025-04-13 03:51:02 +00:00
chat = Chats.get_chat_by_id(chat_id)
if chat is None or chat.user_id != user.id:
return {"task_ids": []}
2025-07-11 14:14:48 +00:00
task_ids = await list_task_ids_by_item_id(request.app.state.redis, chat_id)
2025-04-13 03:51:02 +00:00
log.debug(f"Task IDs for chat {chat_id}: {task_ids}")
2025-04-13 03:51:02 +00:00
return {"task_ids": task_ids}
2024-12-19 09:00:32 +00:00
2024-06-20 08:51:39 +00:00
##################################
#
# Config Endpoints
#
##################################
2024-02-22 02:12:01 +00:00
@app.get("/api/config")
2024-08-19 14:49:40 +00:00
async def get_app_config(request: Request):
user = None
token = None
auth_header = request.headers.get("Authorization")
if auth_header:
cred = get_http_authorization_cred(auth_header)
if cred:
token = cred.credentials
if not token and "token" in request.cookies:
2024-08-19 14:49:40 +00:00
token = request.cookies.get("token")
if token:
2024-11-06 05:14:02 +00:00
try:
data = decode_token(token)
except Exception as e:
log.debug(e)
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
detail="Invalid token",
)
2024-08-19 14:49:40 +00:00
if data is not None and "id" in data:
user = Users.get_user_by_id(data["id"])
2025-03-04 06:24:19 +00:00
user_count = Users.get_num_users()
2024-11-06 04:47:23 +00:00
onboarding = False
2025-03-04 06:24:19 +00:00
2024-11-03 11:00:28 +00:00
if user is None:
2024-11-06 04:47:23 +00:00
onboarding = user_count == 0
2024-11-03 11:00:28 +00:00
2024-02-22 02:12:01 +00:00
return {
2024-11-06 04:47:23 +00:00
**({"onboarding": True} if onboarding else {}),
"status": True,
"name": app.state.WEBUI_NAME,
"version": VERSION,
"default_locale": str(DEFAULT_LOCALE),
"oauth": {
2024-08-19 14:49:40 +00:00
"providers": {
name: config.get("name", name)
for name, config in OAUTH_PROVIDERS.items()
}
},
"features": {
"auth": WEBUI_AUTH,
"auth_trusted_header": bool(app.state.AUTH_TRUSTED_EMAIL_HEADER),
"enable_signup_password_confirmation": ENABLE_SIGNUP_PASSWORD_CONFIRMATION,
"enable_signup_email_verification": True,
"enable_ldap": app.state.config.ENABLE_LDAP,
"enable_api_key": app.state.config.ENABLE_API_KEY,
"enable_signup": app.state.config.ENABLE_SIGNUP,
"enable_login_form": app.state.config.ENABLE_LOGIN_FORM,
"enable_websocket": ENABLE_WEBSOCKET_SUPPORT,
"enable_version_update_check": ENABLE_VERSION_UPDATE_CHECK,
"signup_email_verification_send_interval": app.state.email_verification_config["send_interval"],
2024-08-19 14:49:40 +00:00
**(
{
2025-02-12 07:12:00 +00:00
"enable_direct_connections": app.state.config.ENABLE_DIRECT_CONNECTIONS,
2024-12-23 04:02:14 +00:00
"enable_channels": app.state.config.ENABLE_CHANNELS,
2025-05-01 12:39:36 +00:00
"enable_notes": app.state.config.ENABLE_NOTES,
2025-04-12 23:33:36 +00:00
"enable_web_search": app.state.config.ENABLE_WEB_SEARCH,
"enable_code_execution": app.state.config.ENABLE_CODE_EXECUTION,
2025-02-10 10:28:01 +00:00
"enable_code_interpreter": app.state.config.ENABLE_CODE_INTERPRETER,
2024-12-12 03:52:46 +00:00
"enable_image_generation": app.state.config.ENABLE_IMAGE_GENERATION,
2025-02-10 10:28:01 +00:00
"enable_autocomplete_generation": app.state.config.ENABLE_AUTOCOMPLETE_GENERATION,
2024-12-12 02:53:38 +00:00
"enable_community_sharing": app.state.config.ENABLE_COMMUNITY_SHARING,
"enable_message_rating": app.state.config.ENABLE_MESSAGE_RATING,
2025-03-31 04:31:16 +00:00
"enable_user_webhooks": app.state.config.ENABLE_USER_WEBHOOKS,
2024-08-19 14:49:40 +00:00
"enable_admin_export": ENABLE_ADMIN_EXPORT,
"enable_admin_chat_access": ENABLE_ADMIN_CHAT_ACCESS,
2025-02-10 10:28:01 +00:00
"enable_google_drive_integration": app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
2025-02-24 14:14:10 +00:00
"enable_onedrive_integration": app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
**(
{
2025-09-17 17:18:23 +00:00
"enable_onedrive_personal": ENABLE_ONEDRIVE_PERSONAL,
"enable_onedrive_business": ENABLE_ONEDRIVE_BUSINESS,
}
if app.state.config.ENABLE_ONEDRIVE_INTEGRATION
else {}
),
2024-08-19 14:49:40 +00:00
}
if user is not None
else {}
),
2024-06-08 03:18:48 +00:00
},
2024-08-19 14:49:40 +00:00
**(
{
2024-12-12 02:53:38 +00:00
"default_models": app.state.config.DEFAULT_MODELS,
"default_prompt_suggestions": app.state.config.DEFAULT_PROMPT_SUGGESTIONS,
2025-03-04 10:45:05 +00:00
"user_count": user_count,
2025-02-18 00:25:50 +00:00
"code": {
"engine": app.state.config.CODE_EXECUTION_ENGINE,
},
2024-08-19 14:49:40 +00:00
"audio": {
"tts": {
2024-12-12 03:52:46 +00:00
"engine": app.state.config.TTS_ENGINE,
"voice": app.state.config.TTS_VOICE,
"split_on": app.state.config.TTS_SPLIT_ON,
2024-08-19 14:49:40 +00:00
},
"stt": {
2024-12-12 03:52:46 +00:00
"engine": app.state.config.STT_ENGINE,
2024-08-19 14:49:40 +00:00
},
},
2024-08-27 15:05:24 +00:00
"file": {
2024-12-12 03:52:46 +00:00
"max_size": app.state.config.FILE_MAX_SIZE,
"max_count": app.state.config.FILE_MAX_COUNT,
2025-06-16 12:52:57 +00:00
"image_compression": {
"width": app.state.config.FILE_IMAGE_COMPRESSION_WIDTH,
"height": app.state.config.FILE_IMAGE_COMPRESSION_HEIGHT,
},
2024-08-27 15:05:24 +00:00
},
2024-12-12 02:53:38 +00:00
"permissions": {**app.state.config.USER_PERMISSIONS},
"google_drive": {
"client_id": GOOGLE_DRIVE_CLIENT_ID.value,
"api_key": GOOGLE_DRIVE_API_KEY.value,
},
2025-04-14 15:27:59 +00:00
"onedrive": {
"client_id_personal": ONEDRIVE_CLIENT_ID_PERSONAL,
"client_id_business": ONEDRIVE_CLIENT_ID_BUSINESS,
2025-04-14 15:27:59 +00:00
"sharepoint_url": ONEDRIVE_SHAREPOINT_URL.value,
"sharepoint_tenant_id": ONEDRIVE_SHAREPOINT_TENANT_ID.value,
2025-04-14 15:27:59 +00:00
},
2025-05-14 16:58:54 +00:00
"ui": {
2025-05-14 17:39:17 +00:00
"pending_user_overlay_title": app.state.config.PENDING_USER_OVERLAY_TITLE,
"pending_user_overlay_content": app.state.config.PENDING_USER_OVERLAY_CONTENT,
2025-05-14 19:53:28 +00:00
"response_watermark": app.state.config.RESPONSE_WATERMARK,
2025-05-14 16:58:54 +00:00
},
2025-03-04 10:45:05 +00:00
"license_metadata": app.state.LICENSE_METADATA,
2025-03-04 06:24:19 +00:00
**(
{
"active_entries": app.state.USER_COUNT,
}
if user.role == "admin"
else {}
),
}
2025-07-28 07:09:48 +00:00
if user is not None and (user.role in ["admin", "user"])
2025-07-11 23:39:58 +00:00
else {
**(
2025-08-13 22:27:24 +00:00
{
"ui": {
"pending_user_overlay_title": app.state.config.PENDING_USER_OVERLAY_TITLE,
"pending_user_overlay_content": app.state.config.PENDING_USER_OVERLAY_CONTENT,
}
}
if user and user.role == "pending"
else {}
2025-08-14 00:50:33 +00:00
),
**(
2025-07-11 23:39:58 +00:00
{
"metadata": {
"login_footer": app.state.LICENSE_METADATA.get(
"login_footer", ""
2025-07-31 14:45:39 +00:00
),
"auth_logo_position": app.state.LICENSE_METADATA.get(
"auth_logo_position", ""
),
2025-07-11 23:39:58 +00:00
}
}
if app.state.LICENSE_METADATA
else {}
2025-08-13 22:27:24 +00:00
),
2025-07-11 23:39:58 +00:00
}
2024-08-19 14:49:40 +00:00
),
2024-02-22 02:12:01 +00:00
}
2024-12-10 08:54:13 +00:00
class UrlForm(BaseModel):
url: str
2024-06-20 08:51:39 +00:00
2024-03-21 01:35:02 +00:00
@app.get("/api/webhook")
async def get_webhook_url(user=Depends(get_admin_user)):
return {
"url": app.state.config.WEBHOOK_URL,
2024-03-21 01:35:02 +00:00
}
@app.post("/api/webhook")
async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
app.state.config.WEBHOOK_URL = form_data.url
2024-12-12 02:53:38 +00:00
app.state.WEBHOOK_URL = app.state.config.WEBHOOK_URL
return {"url": app.state.config.WEBHOOK_URL}
2024-03-05 08:59:35 +00:00
@app.get("/api/version")
2024-08-03 13:24:26 +00:00
async def get_app_version():
2024-03-05 08:59:35 +00:00
return {
"version": VERSION,
}
2024-02-25 19:26:58 +00:00
@app.get("/api/version/updates")
2025-02-03 21:42:03 +00:00
async def get_app_latest_release_version(user=Depends(get_verified_user)):
if not ENABLE_VERSION_UPDATE_CHECK:
log.debug(
f"Version update check is disabled, returning current version as latest version"
)
return {"current": VERSION, "latest": VERSION}
2024-02-25 19:26:58 +00:00
try:
2024-09-27 12:38:56 +00:00
timeout = aiohttp.ClientTimeout(total=1)
async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
2024-04-10 06:03:05 +00:00
async with session.get(
2025-05-14 19:33:52 +00:00
"https://api.github.com/repos/open-webui/open-webui/releases/latest",
ssl=AIOHTTP_CLIENT_SESSION_SSL,
2024-04-10 06:03:05 +00:00
) as response:
response.raise_for_status()
data = await response.json()
latest_version = data["tag_name"]
return {"current": VERSION, "latest": latest_version[1:]}
2024-09-30 14:32:38 +00:00
except Exception as e:
log.debug(e)
2024-09-27 12:38:56 +00:00
return {"current": VERSION, "latest": VERSION}
2024-02-25 19:26:58 +00:00
2024-04-10 08:27:19 +00:00
2024-12-10 08:54:13 +00:00
@app.get("/api/changelog")
async def get_app_changelog():
return {key: CHANGELOG[key] for idx, key in enumerate(CHANGELOG) if idx < 5}
2025-06-16 06:42:34 +00:00
@app.get("/api/usage")
async def get_current_usage(user=Depends(get_verified_user)):
"""
Get current usage statistics for CyberLover.
2025-06-16 06:42:34 +00:00
This is an experimental endpoint and subject to change.
"""
try:
return {"model_ids": get_models_in_use(), "user_ids": get_active_user_ids()}
except Exception as e:
log.error(f"Error getting usage statistics: {e}")
raise HTTPException(status_code=500, detail="Internal Server Error")
############################
# OAuth Login & Callback
############################
2025-09-25 06:49:16 +00:00
# Initialize OAuth client manager with any MCP tool servers using OAuth 2.1
if len(app.state.config.TOOL_SERVER_CONNECTIONS) > 0:
for tool_server_connection in app.state.config.TOOL_SERVER_CONNECTIONS:
if tool_server_connection.get("type", "openapi") == "mcp":
server_id = tool_server_connection.get("info", {}).get("id")
auth_type = tool_server_connection.get("auth_type", "none")
if server_id and auth_type == "oauth_2.1":
oauth_client_info = tool_server_connection.get("info", {}).get(
2025-09-25 06:56:09 +00:00
"oauth_client_info", ""
2025-09-25 06:49:16 +00:00
)
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
try:
oauth_client_info = decrypt_data(oauth_client_info)
app.state.oauth_client_manager.add_client(
f"mcp:{server_id}",
OAuthClientInformationFull(**oauth_client_info),
)
except Exception as e:
log.error(
f"Error adding OAuth client for MCP tool server {server_id}: {e}"
)
pass
2025-09-25 06:49:16 +00:00
try:
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
if ENABLE_STAR_SESSIONS_MIDDLEWARE:
redis_session_store = RedisStore(
url=REDIS_URL,
prefix=(f"{REDIS_KEY_PREFIX}:session:" if REDIS_KEY_PREFIX else "session:"),
)
2025-09-25 06:49:16 +00:00
app.add_middleware(SessionAutoloadMiddleware)
app.add_middleware(
StarSessionsMiddleware,
store=redis_session_store,
cookie_name="owui-session",
cookie_same_site=WEBUI_SESSION_COOKIE_SAME_SITE,
cookie_https_only=WEBUI_SESSION_COOKIE_SECURE,
)
log.info("Using Redis for session")
else:
raise ValueError("No Redis URL provided")
except Exception as e:
app.add_middleware(
SessionMiddleware,
secret_key=WEBUI_SECRET_KEY,
session_cookie="owui-session",
same_site=WEBUI_SESSION_COOKIE_SAME_SITE,
https_only=WEBUI_SESSION_COOKIE_SECURE,
)
2025-09-25 06:49:16 +00:00
@app.get("/oauth/clients/{client_id}/authorize")
async def oauth_client_authorize(
client_id: str,
request: Request,
response: Response,
user=Depends(get_verified_user),
):
return await oauth_client_manager.handle_authorize(request, client_id=client_id)
@app.get("/oauth/clients/{client_id}/callback")
async def oauth_client_callback(
client_id: str,
request: Request,
response: Response,
user=Depends(get_verified_user),
):
return await oauth_client_manager.handle_callback(
request,
client_id=client_id,
user_id=user.id if user else None,
response=response,
)
@app.get("/oauth/{provider}/login")
async def oauth_login(provider: str, request: Request):
2025-02-16 08:11:18 +00:00
return await oauth_manager.handle_login(request, provider)
# OAuth login logic is as follows:
# 1. Attempt to find a user with matching subject ID, tied to the provider
# 2. If OAUTH_MERGE_ACCOUNTS_BY_EMAIL is true, find a user with the email address provided via OAuth
# - This is considered insecure in general, as OAuth providers do not always verify email addresses
# 3. If there is no user, and ENABLE_OAUTH_SIGNUP is true, create a user
2024-10-14 07:13:26 +00:00
# - Email addresses are considered unique, so we fail registration if the email address is already taken
2025-09-25 06:49:16 +00:00
@app.get("/oauth/{provider}/login/callback")
2025-09-25 16:28:33 +00:00
@app.get("/oauth/{provider}/callback") # Legacy endpoint
2025-09-25 06:49:16 +00:00
async def oauth_login_callback(provider: str, request: Request, response: Response):
2025-02-16 08:11:18 +00:00
return await oauth_manager.handle_callback(request, provider, response)
@app.get("/manifest.json")
async def get_manifest_json():
2025-04-10 17:35:43 +00:00
if app.state.EXTERNAL_PWA_MANIFEST_URL:
return requests.get(app.state.EXTERNAL_PWA_MANIFEST_URL).json()
else:
return {
"name": app.state.WEBUI_NAME,
"short_name": app.state.WEBUI_NAME,
2025-08-08 10:18:17 +00:00
"description": f"{app.state.WEBUI_NAME} is an open, extensible, user-friendly interface for AI that adapts to your workflow.",
2025-04-10 17:35:43 +00:00
"start_url": "/",
"display": "standalone",
"background_color": "#343541",
"icons": [
{
"src": "/static/logo.png",
"type": "image/png",
"sizes": "500x500",
"purpose": "any",
},
{
"src": "/static/logo.png",
"type": "image/png",
"sizes": "500x500",
"purpose": "maskable",
},
],
0.6.33 (#18118) * feat: improve ollama model management experience This commit introduces several improvements to the Ollama model management modal: - Adds a cancel button to the model pulling operation, using the existing 'x' button pattern. - Adds a cancel button to the "Update All" models operation, allowing the user to cancel the update for the currently processing model. - Cleans up toast notifications when updating all models. A single toast is now shown at the beginning and a summary toast at the end, preventing notification spam. - Refactors the `ManageOllama.svelte` component to support these new cancellation features. - Adds tooltips to all buttons in the modal to improve clarity. - Disables buttons when their corresponding input fields are empty to prevent accidental clicks. * fix * i18n: improve Chinese translation * fix: handle non‑UTF8 chars in third‑party responses without error * German translation of new strings in i18n * log web search queries only with level 'debug' instead of 'info' * Tool calls now only include text and dont inlcude other content like image b64 * fix onedrive * fix: discovery url * fix: default permissions not being loaded * fix: ai hallucination * fix: non rich text input copy * refac: rm print statements * refac: disable direct models from model editors * refac/fix: do not process xlsx files with azure doc intelligence * Update pull_request_template.md * Update generated image translation in DE-de * added missing danish translations * feat(onedrive): Enable search and "My Organization" pivot * style(onedrive): Formatting fix * feat: Implement toggling for vertical and horizontal flow layouts This commit introduces the necessary logic and UI controls to allow users to switch the Flow component layout between vertical and horizontal orientations. * **`Flow.svelte` Refactoring:** * Updates logic for calculating level offsets and node positions to consistently respect the current flow orientation. * Adds a control panel using `<Controls>` and `<SwitchButton>` components. * Provides user interface elements to easily switch the flow layout between horizontal and vertical orientations. * build(deps): bump pydantic from 2.11.7 to 2.11.9 in /backend Bumps [pydantic](https://github.com/pydantic/pydantic) from 2.11.7 to 2.11.9. - [Release notes](https://github.com/pydantic/pydantic/releases) - [Changelog](https://github.com/pydantic/pydantic/blob/v2.11.9/HISTORY.md) - [Commits](https://github.com/pydantic/pydantic/compare/v2.11.7...v2.11.9) --- updated-dependencies: - dependency-name: pydantic dependency-version: 2.11.9 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump black from 25.1.0 to 25.9.0 in /backend Bumps [black](https://github.com/psf/black) from 25.1.0 to 25.9.0. - [Release notes](https://github.com/psf/black/releases) - [Changelog](https://github.com/psf/black/blob/main/CHANGES.md) - [Commits](https://github.com/psf/black/compare/25.1.0...25.9.0) --- updated-dependencies: - dependency-name: black dependency-version: 25.9.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump markdown from 3.8.2 to 3.9 in /backend Bumps [markdown](https://github.com/Python-Markdown/markdown) from 3.8.2 to 3.9. - [Release notes](https://github.com/Python-Markdown/markdown/releases) - [Changelog](https://github.com/Python-Markdown/markdown/blob/master/docs/changelog.md) - [Commits](https://github.com/Python-Markdown/markdown/compare/3.8.2...3.9.0) --- updated-dependencies: - dependency-name: markdown dependency-version: '3.9' dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump chromadb from 1.0.20 to 1.1.0 in /backend Bumps [chromadb](https://github.com/chroma-core/chroma) from 1.0.20 to 1.1.0. - [Release notes](https://github.com/chroma-core/chroma/releases) - [Changelog](https://github.com/chroma-core/chroma/blob/main/RELEASE_PROCESS.md) - [Commits](https://github.com/chroma-core/chroma/compare/1.0.20...1.1.0) --- updated-dependencies: - dependency-name: chromadb dependency-version: 1.1.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * build(deps): bump opentelemetry-api from 1.36.0 to 1.37.0 Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.36.0 to 1.37.0. - [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases) - [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md) - [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.36.0...v1.37.0) --- updated-dependencies: - dependency-name: opentelemetry-api dependency-version: 1.37.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * refac: ollama embed form data * fix: non rich text handling * fix: oauth client registration * refac * chore: dep bump * chore: fastapi bump * chore/refac: bump bcrypt and remove passlib * Improving Korean Translation * refac * Improving Korean Translation * feat: PWA share_target implementation Co-Authored-By: gjveld <19951982+gjveld@users.noreply.github.com> * refac: message input mobile detection behaviour * feat: model_ids per folder * Update translation.json (pt-BR) inclusion of new translations of items that have been added * refac * refac * refac * refac * refac/fix: temp chat * refac * refac: stop task * refac/fix: azure audio escape * refac: external tool validation * refac/enh: start.sh additional args support * refac * refac: styling * refac/fix: direct connection floating action buttons * refac/fix: system prompt duplication * refac/enh: openai tts additional params support * refac * feat: load data in parallel to accelerate page loading speed * i18n: improve Chinese translation * refac * refac: model selector * UPD: i18n es-ES Translation v0.6.33 UPD: i18n es-ES Translation v0.6.33 Updated new strings. * refac * improved query pref by querying only relevant columns * refac/enh: docling params * refac * refac: openai additional headers support * refac * FEAT: Add Vega Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Feature required in https://github.com/open-webui/open-webui/discussions/18022 Added npm vega lib to package.json Added function for visualization renderer to src/libs/utils/index.ts Added logic to src/lib/components/chat/Messages/CodeBlock.svelte The treatment is similar as for mermaid diagrams. Reference: https://vega.github.io/vega/ * refac * chore * refac * FEAT: Add Vega-Lite Char Visualizer Renderer ### FEAT: Add Vega Char Visualizer Renderer Add suport for Vega-Lite Specifications. Vega-Lite is a "compiled" version of Vega Char Visualizer. For be rendered with Vega it have to be compiled. This PR add the check and compile if necessary, is a complement of recent Vega Renderer Feature added. * refac * refac/fix: switch * enh/refac: url input handling * refac * refac: styling * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. * removed redundant knowledge API call * Fix Code Format * refac: model workspace view * refac * refac: knowledge * refac: prompts * refac: tools * refac * feat: attach folder * refac: make tencentcloud-sdk-python optional * refac/fix: oauth * enh: ENABLE_OAUTH_EMAIL_FALLBACK * refac/fix: folders * Update requirements.txt * Update pyproject.toml * UPD: Add Validators & Error Toast for Mermaid & Vega diagrams ### UPD: Feat: Add Validators & Error Toast for Mermaid & Vega diagrams Description: As many time the diagrams generated or entered have syntax errors the diagrams are not rendered due to that errors, but as there isn't any notification is difficult to know what happend. This PR add validator and toast notification when error on Mermaid and Vega/Vega-Lite diagrams, helping the user to fix its. Note: Another possibility of integrating this Graph Visualizer is through its svelte component: https://github.com/vega/svelte-vega/tree/main/packages/svelte-vega * Removed unused toast import & Code Format * refac * refac: external tool server view * refac * refac: overview * refac: styling * refac * Update bug_report.yaml * refac * refac * refac * refac * refac: oauth client fallback * Fixed: Cannot handle batch sizes > 1 if no padding token is defined Fixes Cannot handle batch sizes > 1 if no padding token is defined For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id. * refac: fallback to reasoning content * fix(i18n): corrected typo in Spanish translation for "Reasoning Tags" Typo fixed in Spanish translation file at line 1240 of `open-webui/src/lib/i18n/locales/es-ES/translation.json`: - Incorrect: "Eriquetas de Razonamiento" - Correct: "Etiquetas de Razonamiento" This improves clarity and consistency in the UI. * refac/fix: ENABLE_STAR_SESSIONS_MIDDLEWARE * refac/fix: redirect * refac * refac * refac * refac: web search error handling * refac: source parsing * refac: functions * refac * refac/enh: note pdf export * refac/fix: mcp oauth2.1 * chore: format * chore: Changelog (#17995) * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * Update CHANGELOG.md * refac * chore: dep bump --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: silentoplayz <jacwoo21@outlook.com> Co-authored-by: Shirasawa <764798966@qq.com> Co-authored-by: Jan Kessler <jakessle@uni-mainz.de> Co-authored-by: Jacob Leksan <jacob.leksan@expedient.com> Co-authored-by: Classic298 <27028174+Classic298@users.noreply.github.com> Co-authored-by: sinejespersen <sinejespersen@protonmail.com> Co-authored-by: Selene Blok <selene.blok@rws.nl> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Cyp <cypher9715@naver.com> Co-authored-by: gjveld <19951982+gjveld@users.noreply.github.com> Co-authored-by: joaoback <156559121+joaoback@users.noreply.github.com> Co-authored-by: _00_ <131402327+rgaricano@users.noreply.github.com> Co-authored-by: expruc <eygabi01@gmail.com> Co-authored-by: YetheSamartaka <55753928+YetheSamartaka@users.noreply.github.com> Co-authored-by: Akutangulo <akutangulo@gmail.com>
2025-10-07 21:20:27 +00:00
"share_target": {
"action": "/",
"method": "GET",
"params": {"text": "shared"},
},
2025-04-10 17:35:43 +00:00
}
2024-04-10 08:27:19 +00:00
2024-05-07 00:29:16 +00:00
@app.get("/opensearch.xml")
async def get_opensearch_xml():
xml_content = rf"""
<OpenSearchDescription xmlns="http://a9.com/-/spec/opensearch/1.1/" xmlns:moz="http://www.mozilla.org/2006/browser/search/">
2025-02-16 08:11:18 +00:00
<ShortName>{app.state.WEBUI_NAME}</ShortName>
<Description>Search {app.state.WEBUI_NAME}</Description>
2024-05-07 00:29:16 +00:00
<InputEncoding>UTF-8</InputEncoding>
2024-12-25 16:50:57 +00:00
<Image width="16" height="16" type="image/x-icon">{app.state.config.WEBUI_URL}/static/favicon.png</Image>
<Url type="text/html" method="get" template="{app.state.config.WEBUI_URL}/?q={"{searchTerms}"}"/>
<moz:SearchForm>{app.state.config.WEBUI_URL}</moz:SearchForm>
2024-05-07 00:29:16 +00:00
</OpenSearchDescription>
"""
return Response(content=xml_content, media_type="application/xml")
2024-05-15 18:17:18 +00:00
@app.get("/health")
async def healthcheck():
return {"status": True}
@app.get("/health/db")
async def healthcheck_with_db():
Session.execute(text("SELECT 1;")).all()
return {"status": True}
app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
@app.get("/favicon.png")
async def get_favicon():
return FileResponse(os.path.join(STATIC_DIR, "favicon.png"))
@app.get("/cache/{path:path}")
async def serve_cache_file(
path: str,
user=Depends(get_verified_user),
):
file_path = os.path.abspath(os.path.join(CACHE_DIR, path))
# prevent path traversal
if not file_path.startswith(os.path.abspath(CACHE_DIR)):
raise HTTPException(status_code=404, detail="File not found")
if not os.path.isfile(file_path):
raise HTTPException(status_code=404, detail="File not found")
return FileResponse(file_path)
2024-02-24 01:12:19 +00:00
2024-10-08 01:19:13 +00:00
2024-12-17 21:52:57 +00:00
def swagger_ui_html(*args, **kwargs):
2024-12-16 18:00:51 +00:00
return get_swagger_ui_html(
*args,
**kwargs,
swagger_js_url="/static/swagger-ui/swagger-ui-bundle.js",
swagger_css_url="/static/swagger-ui/swagger-ui.css",
2024-12-17 21:51:29 +00:00
swagger_favicon_url="/static/swagger-ui/favicon.png",
2024-12-16 18:00:51 +00:00
)
2024-12-17 21:51:29 +00:00
2024-12-17 21:52:57 +00:00
applications.get_swagger_ui_html = swagger_ui_html
2024-02-24 01:12:19 +00:00
if os.path.exists(FRONTEND_BUILD_DIR):
2024-05-22 04:38:58 +00:00
mimetypes.add_type("text/javascript", ".js")
app.mount(
"/",
SPAStaticFiles(directory=FRONTEND_BUILD_DIR, html=True),
name="spa-static-files",
)
else:
log.warning(
f"Frontend build directory not found at '{FRONTEND_BUILD_DIR}'. Serving API only."
)