Merge 153240c8d6 into 1ea555a5ac

* Update pyproject.toml (#101)

* Update pyproject.toml

* Update requirements.txt

* Update requirements-min.txt

* Upgrade Playwright version to 1.57.0

* Update langchain-community version to 0.3.29

* Update requirements.txt

* Update requirements-min.txt

backend/open_webui/routers/audio.py

@@ -33,6 +33,7 @@ from fastapi.responses import FileResponse
 from pydantic import BaseModel
 
 
+from open_webui.utils.misc import strict_match_mime_type
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.headers import include_user_info_headers
 from open_webui.config import (
@@ -1155,17 +1156,9 @@ def transcription(
 
     stt_supported_content_types = getattr(
         request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
-    )
+    ) or ["audio/*", "video/webm"]
 
-    if not any(
-        fnmatch(file.content_type, content_type)
-        for content_type in (
-            stt_supported_content_types
-            if stt_supported_content_types
-            and any(t.strip() for t in stt_supported_content_types)
-            else ["audio/*", "video/webm"]
-        )
-    ):
+    if not strict_match_mime_type(stt_supported_content_types, file.content_type):
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,

backend/open_webui/routers/files.py

@@ -47,7 +47,7 @@ from open_webui.storage.provider import Storage
 
 from open_webui.utils.auth import get_admin_user, get_verified_user
 from open_webui.utils.access_control import has_access
-
+from open_webui.utils.misc import strict_match_mime_type
 from pydantic import BaseModel
 
 log = logging.getLogger(__name__)
@@ -104,17 +104,9 @@ def process_uploaded_file(request, file, file_path, file_item, file_metadata, us
         if file.content_type:
             stt_supported_content_types = getattr(
                 request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
-            )
+            ) or ["audio/*", "video/webm"]
 
-            if any(
-                fnmatch(file.content_type, content_type)
-                for content_type in (
-                    stt_supported_content_types
-                    if stt_supported_content_types
-                    and any(t.strip() for t in stt_supported_content_types)
-                    else ["audio/*", "video/webm"]
-                )
-            ):
+            if strict_match_mime_type(stt_supported_content_types, file.content_type):
                 file_path = Storage.get_file(file_path)
                 result = transcribe(request, file_path, file_metadata, user)
 

backend/open_webui/utils/misc.py

@@ -9,6 +9,7 @@ from pathlib import Path
 from typing import Callable, Optional, Sequence, Union
 import json
 import aiohttp
+import mimeparse
 
 
 import collections.abc
@@ -577,6 +578,37 @@ def throttle(interval: float = 10.0):
     return decorator
 
 
+def strict_match_mime_type(supported: list[str] | str, header: str) -> Optional[str]:
+    """
+    Strictly match the mime type with the supported mime types.
+
+    :param supported: The supported mime types.
+    :param header: The header to match.
+    :return: The matched mime type or None if no match is found.
+    """
+
+    try:
+        if isinstance(supported, str):
+            supported = supported.split(",")
+
+        supported = [s for s in supported if s.strip() and "/" in s]
+
+        match = mimeparse.best_match(supported, header)
+        if not match:
+            return None
+
+        _, _, match_params = mimeparse.parse_mime_type(match)
+        _, _, header_params = mimeparse.parse_mime_type(header)
+        for k, v in match_params.items():
+            if header_params.get(k) != v:
+                return None
+
+        return match
+    except Exception as e:
+        log.exception(f"Failed to match mime type {header}: {e}")
+        return None
+
+
 def extract_urls(text: str) -> list[str]:
     # Regex pattern to match URLs
     url_pattern = re.compile(
@@ -624,14 +656,17 @@ def stream_chunks_handler(stream: aiohttp.StreamReader):
                         yield line
                     else:
                         yield b"data: {}"
+                        yield b"\n"
                 else:
                     # Normal mode: check if line exceeds limit
                     if len(line) > max_buffer_size:
                         skip_mode = True
                         yield b"data: {}"
+                        yield b"\n"
                         log.info(f"Skip mode triggered, line size: {len(line)}")
                     else:
                         yield line
+                        yield b"\n"
 
             # Save the last incomplete fragment
             buffer = lines[-1]
@@ -646,5 +681,6 @@ def stream_chunks_handler(stream: aiohttp.StreamReader):
         # Process remaining buffer data
         if buffer and not skip_mode:
             yield buffer
+            yield b"\n"
 
     return yield_safe_stream_chunks()

backend/requirements-min.txt

@@ -1,7 +1,7 @@
 # Minimal requirements for backend to run
 # WIP: use this as a reference to build a minimal docker image
 
-fastapi==0.123.0
+fastapi==0.124.0
 uvicorn[standard]==0.37.0
 pydantic==2.12.5
 python-multipart==0.0.20
@@ -16,7 +16,7 @@ PyJWT[crypto]==2.10.1
 authlib==1.6.5
 
 requests==2.32.5
-aiohttp==3.12.15
+aiohttp==3.13.2
 async-timeout
 aiocache
 aiofiles
@@ -24,21 +24,21 @@ starlette-compress==1.6.1
 httpx[socks,http2,zstd,cli,brotli]==0.28.1
 starsessions[redis]==2.2.1
 
-sqlalchemy==2.0.38
+sqlalchemy==2.0.44
 alembic==1.17.2
 peewee==3.18.3
 peewee-migrate==1.14.3
 
-pycrdt==0.12.25
+pycrdt==0.12.44
 redis
 
-APScheduler==3.10.4
-RestrictedPython==8.0
+APScheduler==3.11.1
+RestrictedPython==8.1
 
 loguru==0.7.3
 asgiref==3.11.0
 
-mcp==1.22.0
+mcp==1.23.1
 openai
 
 langchain==0.3.27
@@ -46,6 +46,6 @@ langchain-community==0.3.29
 fake-useragent==2.2.0
 
 chromadb==1.3.5
-black==25.11.0
+black==25.12.0
 pydub
 chardet==5.2.0

backend/requirements.txt

@@ -1,4 +1,4 @@
-fastapi==0.123.0
+fastapi==0.124.0
 uvicorn[standard]==0.37.0
 pydantic==2.12.5
 python-multipart==0.0.20
@@ -13,35 +13,36 @@ PyJWT[crypto]==2.10.1
 authlib==1.6.5
 
 requests==2.32.5
-aiohttp==3.12.15
+aiohttp==3.13.2
 async-timeout
 aiocache
 aiofiles
 starlette-compress==1.6.1
 httpx[socks,http2,zstd,cli,brotli]==0.28.1
 starsessions[redis]==2.2.1
+python-mimeparse==2.0.0
 
-sqlalchemy==2.0.38
+sqlalchemy==2.0.44
 alembic==1.17.2
 peewee==3.18.3
 peewee-migrate==1.14.3
 
-pycrdt==0.12.25
+pycrdt==0.12.44
 redis
 
-APScheduler==3.10.4
-RestrictedPython==8.0
+APScheduler==3.11.1
+RestrictedPython==8.1
 
 loguru==0.7.3
 asgiref==3.11.0
 
 # AI libraries
 tiktoken
-mcp==1.22.0
+mcp==1.23.3
 
 openai
 anthropic
-google-genai==1.52.0
+google-genai==1.54.0
 google-generativeai==0.8.5
 
 langchain==0.3.27
@@ -49,8 +50,8 @@ langchain-community==0.3.29
 
 fake-useragent==2.2.0
 chromadb==1.3.5
-weaviate-client==4.17.0
-opensearch-py==2.8.0
+weaviate-client==4.18.3
+opensearch-py==3.1.0
 
 transformers==4.57.3
 sentence-transformers==5.1.2
@@ -60,43 +61,43 @@ einops==0.8.1
 
 ftfy==6.3.1
 chardet==5.2.0
-pypdf==6.4.0
-fpdf2==2.8.2
-pymdown-extensions==10.17.2
-docx2txt==0.8
+pypdf==6.4.1
+fpdf2==2.8.5
+pymdown-extensions==10.18
+docx2txt==0.9
 python-pptx==1.0.2
 unstructured==0.18.21
 msoffcrypto-tool==5.4.2
-nltk==3.9.1
+nltk==3.9.2
 Markdown==3.10
 pypandoc==1.16.2
-pandas==2.2.3
+pandas==2.3.3
 openpyxl==3.1.5
 pyxlsb==1.0.10
-xlrd==2.0.1
+xlrd==2.0.2
 validators==0.35.0
 psutil
 sentencepiece
 soundfile==0.13.1
 
-pillow==11.3.0
-opencv-python-headless==4.11.0.86
+pillow==12.0.0
+opencv-python-headless==4.12.0.88
 rapidocr-onnxruntime==1.4.4
 rank-bm25==0.2.2
 
-onnxruntime==1.20.1
-faster-whisper==1.1.1
+onnxruntime==1.23.2
+faster-whisper==1.2.1
 
-black==25.11.0
-youtube-transcript-api==1.2.2
+black==25.12.0
+youtube-transcript-api==1.2.3
 pytube==15.0.0
 
 pydub
-ddgs==9.9.2
+ddgs==9.9.3
 
 azure-ai-documentintelligence==1.0.2
-azure-identity==1.25.0
-azure-storage-blob==12.24.1
+azure-identity==1.25.1
+azure-storage-blob==12.27.1
 azure-search-documents==11.6.0
 
 ## Google Drive
@@ -105,26 +106,26 @@ google-auth-httplib2
 google-auth-oauthlib
 
 googleapis-common-protos==1.72.0
-google-cloud-storage==2.19.0
+google-cloud-storage==3.7.0
 
 ## Databases
 pymongo
-psycopg2-binary==2.9.10
-pgvector==0.4.1
+psycopg2-binary==2.9.11
+pgvector==0.4.2
 
-PyMySQL==1.1.1
-boto3==1.41.5
+PyMySQL==1.1.2
+boto3==1.42.5
 
 pymilvus==2.6.5
 qdrant-client==1.16.1
-playwright==1.56.0 # Caution: version must match docker-compose.playwright.yaml
-elasticsearch==9.1.0
+playwright==1.57.0 # Caution: version must match docker-compose.playwright.yaml - Update the docker-compose.yaml if necessary
+elasticsearch==9.2.0
 pinecone==6.0.2
-oracledb==3.2.0
+oracledb==3.4.1
 
 av==14.0.1 # Caution: Set due to FATAL FIPS SELFTEST FAILURE, see discussion https://github.com/open-webui/open-webui/discussions/15720
 
-colbert-ai==0.2.21
+colbert-ai==0.2.22
 
 
 ## Tests
@@ -136,17 +137,17 @@ pytest-docker~=3.2.5
 ldap3==2.9.1
 
 ## Firecrawl
-firecrawl-py==4.10.0
+firecrawl-py==4.10.4
 
 ## Trace
-opentelemetry-api==1.38.0
-opentelemetry-sdk==1.38.0
-opentelemetry-exporter-otlp==1.38.0
-opentelemetry-instrumentation==0.59b0
-opentelemetry-instrumentation-fastapi==0.59b0
-opentelemetry-instrumentation-sqlalchemy==0.59b0
-opentelemetry-instrumentation-redis==0.59b0
-opentelemetry-instrumentation-requests==0.59b0
-opentelemetry-instrumentation-logging==0.59b0
-opentelemetry-instrumentation-httpx==0.59b0
-opentelemetry-instrumentation-aiohttp-client==0.59b0
+opentelemetry-api==1.39.0
+opentelemetry-sdk==1.39.0
+opentelemetry-exporter-otlp==1.39.0
+opentelemetry-instrumentation==0.60b0
+opentelemetry-instrumentation-fastapi==0.60b0
+opentelemetry-instrumentation-sqlalchemy==0.60b0
+opentelemetry-instrumentation-redis==0.60b0
+opentelemetry-instrumentation-requests==0.60b0
+opentelemetry-instrumentation-logging==0.60b0
+opentelemetry-instrumentation-httpx==0.60b0
+opentelemetry-instrumentation-aiohttp-client==0.60b0

docker-compose.playwright.yaml

@@ -1,8 +1,8 @@
 services:
   playwright:
-    image: mcr.microsoft.com/playwright:v1.56.0-noble # Version must match requirements.txt
+    image: mcr.microsoft.com/playwright:v1.57.0-noble # Version must match requirements.txt
     container_name: playwright
-    command: npx -y playwright@1.56.0 run-server --port 3000 --host 0.0.0.0
+    command: npx -y playwright@1.57.0 run-server --port 3000 --host 0.0.0.0
 
   open-webui:
     environment:

pyproject.toml

@@ -6,7 +6,7 @@ authors = [
 ]
 license = { file = "LICENSE" }
 dependencies = [
-    "fastapi==0.123.0",
+    "fastapi==0.124.0",
     "uvicorn[standard]==0.37.0",
     "pydantic==2.12.5",
     "python-multipart==0.0.20",
@@ -21,7 +21,7 @@ dependencies = [
     "authlib==1.6.5",
 
     "requests==2.32.5",
-    "aiohttp==3.12.15",
+    "aiohttp==3.13.2",
     "async-timeout",
     "aiocache",
     "aiofiles",
@@ -29,26 +29,26 @@ dependencies = [
     "httpx[socks,http2,zstd,cli,brotli]==0.28.1",
     "starsessions[redis]==2.2.1",
 
-    "sqlalchemy==2.0.38",
+    "sqlalchemy==2.0.44",
     "alembic==1.17.2",
     "peewee==3.18.3",
     "peewee-migrate==1.14.3",
 
-    "pycrdt==0.12.25",
+    "pycrdt==0.12.44",
     "redis",
 
-    "APScheduler==3.10.4",
-    "RestrictedPython==8.0",
+    "APScheduler==3.11.1",
+    "RestrictedPython==8.1",
 
     "loguru==0.7.3",
     "asgiref==3.11.0",
 
     "tiktoken",
-    "mcp==1.22.0",
+    "mcp==1.23.3",
 
     "openai",
     "anthropic",
-    "google-genai==1.52.0",
+    "google-genai==1.54.0",
     "google-generativeai==0.8.5",
 
     "langchain==0.3.27",
@@ -56,62 +56,62 @@ dependencies = [
 
     "fake-useragent==2.2.0",
     "chromadb==1.3.5",
-    "opensearch-py==2.8.0",
-    "PyMySQL==1.1.1",
-    "boto3==1.41.5",
+    "opensearch-py==3.1.0",
+    "PyMySQL==1.1.2",
+    "boto3==1.42.5",
     
     "transformers==4.57.3",
     "sentence-transformers==5.1.2",
     "accelerate",
-    "pyarrow==20.0.0",
+    "pyarrow==20.0.0", # fix: pin pyarrow version to 20 for rpi compatibility #15897
     "einops==0.8.1",
 
     "ftfy==6.3.1",
     "chardet==5.2.0",
-    "pypdf==6.4.0",
-    "fpdf2==2.8.2",
-    "pymdown-extensions==10.17.2",
-    "docx2txt==0.8",
+    "pypdf==6.4.1",
+    "fpdf2==2.8.5",
+    "pymdown-extensions==10.18",
+    "docx2txt==0.9",
     "python-pptx==1.0.2",
     "unstructured==0.18.21",
     "msoffcrypto-tool==5.4.2",
-    "nltk==3.9.1",
+    "nltk==3.9.2",
     "Markdown==3.10",
     "pypandoc==1.16.2",
-    "pandas==2.2.3",
+    "pandas==2.3.3",
     "openpyxl==3.1.5",
     "pyxlsb==1.0.10",
-    "xlrd==2.0.1",
+    "xlrd==2.0.2",
     "validators==0.35.0",
     "psutil",
     "sentencepiece",
     "soundfile==0.13.1",
     "azure-ai-documentintelligence==1.0.2",
 
-    "pillow==11.3.0",
-    "opencv-python-headless==4.11.0.86",
+    "pillow==12.0.0",
+    "opencv-python-headless==4.12.0.88",
     "rapidocr-onnxruntime==1.4.4",
     "rank-bm25==0.2.2",
 
-    "onnxruntime==1.20.1",
-    "faster-whisper==1.1.1",
+    "onnxruntime==1.23.2",
+    "faster-whisper==1.2.1",
 
-    "black==25.11.0",
-    "youtube-transcript-api==1.2.2",
+    "black==25.12.0",
+    "youtube-transcript-api==1.2.3",
     "pytube==15.0.0",
 
     "pydub",
-    "ddgs==9.9.2",
+    "ddgs==9.9.3",
 
     "google-api-python-client",
     "google-auth-httplib2",
     "google-auth-oauthlib",
 
     "googleapis-common-protos==1.72.0",
-    "google-cloud-storage==2.19.0",
+    "google-cloud-storage==3.7.0",
 
-    "azure-identity==1.25.0",
-    "azure-storage-blob==12.24.1",
+    "azure-identity==1.25.1",
+    "azure-storage-blob==12.27.1",
 
     "ldap3==2.9.1",
 ]
@@ -130,8 +130,8 @@ classifiers = [
 
 [project.optional-dependencies]
 postgres = [
-    "psycopg2-binary==2.9.10",
-    "pgvector==0.4.1",
+    "psycopg2-binary==2.9.11",
+    "pgvector==0.4.2",
 ]
 
 all = [
@@ -143,17 +143,18 @@ all = [
     "docker~=7.1.0",
     "pytest~=8.3.2",
     "pytest-docker~=3.2.5",
-    "playwright==1.56.0",
-    "elasticsearch==9.1.0",
+    "playwright==1.57.0", # Caution: version must match docker-compose.playwright.yaml - Update the docker-compose.yaml if necessary
+    "elasticsearch==9.2.0",
 
     "qdrant-client==1.16.1",
-    "weaviate-client==4.17.0",
+    "pymilvus==2.6.4",
+    "weaviate-client==4.18.3",
     "pymilvus==2.6.5",
     "pinecone==6.0.2",
-    "oracledb==3.2.0",
-    "colbert-ai==0.2.21",
+    "oracledb==3.4.1",
+    "colbert-ai==0.2.22",
 
-    "firecrawl-py==4.10.0",
+    "firecrawl-py==4.10.4",
     "azure-search-documents==11.6.0",
 ]
 

src/lib/i18n/locales/zh-CN/translation.json

@@ -1624,6 +1624,7 @@
 	"Tika": "Tika",
 	"Tika Server URL required.": "请输入 Tika 服务器接口地址",
 	"Tiktoken": "Tiktoken",
+	"Timeout": "超时时间",
 	"Title": "标题",
 	"Title Auto-Generation": "自动生成标题",
 	"Title cannot be an empty string.": "标题不能为空",

src/lib/i18n/locales/zh-TW/translation.json

@@ -1624,6 +1624,7 @@
 	"Tika": "Tika",
 	"Tika Server URL required.": "需要提供 Tika 伺服器 URL。",
 	"Tiktoken": "Tiktoken",
+	"Timeout": "逾時時間",
 	"Title": "標題",
 	"Title Auto-Generation": "自動產生標題",
 	"Title cannot be an empty string.": "標題不能是空字串。",