Merge pull request #13707 from open-webui/dev

0.6.8

CHANGELOG.md

@@ -5,6 +5,40 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.6.8] - 2025-05-10
+
+### Added
+
+- 🏆 **External Reranker Support for Knowledge Base Search**: Supercharge your Retrieval-Augmented Generation (RAG) workflows with the new External Reranker integration; easily plug in advanced reranking services via the UI to deliver sharper and more relevant search results, accelerating research and insight discovery.
+- 📤 **Unstylized PDF Export Option (Reduced File Size)**: When exporting chat transcripts or documents, you can now choose an unstylized PDF export for snappier downloads, minimal file size, and clean data archiving—perfect for large-scale storage or sharing.
+- 📝 **Vazirmatn Font for Persian & Arabic**: Arabic and Persian users will now see their text beautifully rendered with the specialized Vazirmatn font for an improved localized reading experience.
+- 🏷️ **SharePoint Tenant ID Support for OneDrive**: You can now specify a SharePoint tenant ID in OneDrive settings for seamless authentication and granular enterprise integration.
+- 👤 **Refresh OAuth Profile Picture**: Your OAuth profile picture now updates in real-time, ensuring your presence and avatar always match your latest identity across integrated platforms.
+- 🔧 **Milvus Configuration Improvements**: Configure index and metric types for Milvus directly within settings; take full control of your vector database for more accurate and robust AI search experiences.
+- 🛡️ **S3 Tagging Toggle for Compatibility**: Optional S3 tagging via an environment toggle grants full compatibility with all storage backends—including those that don’t support tagging like Cloudflare R2—ensuring error-free attachment and document management.
+- 👨‍🦯 **Icon Button Accessibility Improvements**: Key interactive icon-buttons now include aria-labels and ARIA descriptions, so screen readers provide precise guidance about what action each button performs for improved accessibility.
+- ♿ **Enhanced Accessibility with Modal Focus Trap**: Modal dialogs and pop-ups now feature a focus trap and improved ARIA roles, ensuring seamless navigation and screen reader support—making the interface friendlier for everyone, including keyboard and assistive tech users.
+- 🏃 **Improved Admin User List Loading Indicator**: The user list loading experience is now clearer and more responsive in the admin panel.
+- 🧑‍🤝‍🧑 **Larger Admin User List Page Size**: Admins can now manage up to 30 users per page in the admin interface, drastically reducing pagination and making large user teams easier and faster to manage.
+- 🌠 **Default Code Interpreter Prompt Clarified**: The built-in code interpreter prompt is now more explicit, preventing AI from wrapping code in Markdown blocks when not needed—ensuring properly formatted code runs as intended every time.
+- 🧾 **Improved Default Title Generation Prompt Template**: Title generation now uses a robust template for reliable JSON output, improving chat organization and searchability.
+- 🔗 **Support Jupyter Notebooks with Non-Root Base URLs**: Notebook-based code execution now supports non-root deployed Jupyter servers, granting full flexibility for hybrid or multi-user setups.
+- 📰 **UI Scrollbar Always Visible for Overflow Tools**: When available tools overflow the display, the scrollbar is now always visible and there’s a handy "show all" toggle, making navigation of large toolsets snappier and more intuitive.
+- 🛠️ **General Backend Refactoring for Stability**: Multiple under-the-hood improvements have been made across backend components, ensuring smoother performance, fewer errors, and a more reliable overall experience for all users.
+- 🚀 **Optimized Web Search for Faster Results**: Web search speed and performance have been significantly enhanced, delivering answers and sources in record time to accelerate your research-heavy workflows.
+- 💡 **More Supported Languages**: Expanded language support ensures an even wider range of users can enjoy an intuitive and natural interface in their native tongue.
+
+### Fixed
+
+- 🏃‍♂️ **Exhausting Workers in Nginx Reverse Proxy Due to Websocket Fix**: Websocket sessions are now fully compatible behind Nginx, eliminating worker exhaustion and restoring 24/7 reliability for real-time chats even in complex deployments.
+- 🎤 **Audio Transcription Issue with OpenAI Resolved**: OpenAI-based audio transcription now handles WebM and newer formats without error, ensuring seamless voice-to-text workflows every time.
+- 👉 **Message Input RTL Issue Fixed**: The chat message input now displays correctly for right-to-left languages, creating a flawless typing and reading experience for Arabic, Hebrew, and more.
+- 🀄 **Katex: Proper Rendering of Chinese Characters Next to Math**: Math formulas now render perfectly even when directly adjacent to Chinese (CJK) characters, improving visual clarity for multilingual teams and cross-language documents.
+- 🔂 **Duplicate Web Search URLs Eliminated**: Search results now reliably filter out URL duplicates, so your knowledge and search citations are always clean, trimmed, and easy to review.
+- 📄 **Markdown Rendering Fixed in Knowledge Bases**: Markdown is now displayed correctly within knowledge bases, enabling better formatting and clarity of information-rich files.
+- 🗂️ **LDAP Import/Loading Issue Resolved**: LDAP user imports process correctly, ensuring smooth onboarding and access without interruption.
+- 🌎 **Pinecone Batch Operations and Async Safety**: All Pinecone operations (batch insert, upsert, delete) now run efficiently and safely in an async environment, boosting performance and preventing slowdowns in large-scale RAG jobs.
+
 ## [0.6.7] - 2025-05-07
 
 ### Added

Caddyfile.localhost

@@ -1,64 +0,0 @@
-# Run with
-#    caddy run --envfile ./example.env --config ./Caddyfile.localhost
-#
-# This is configured for
-#    - Automatic HTTPS (even for localhost)
-#    - Reverse Proxying to Ollama API Base URL (http://localhost:11434/api)
-#    - CORS
-#    - HTTP Basic Auth API Tokens (uncomment basicauth section)
-
-
-# CORS Preflight (OPTIONS) + Request (GET, POST, PATCH, PUT, DELETE)
-(cors-api) {
-	@match-cors-api-preflight method OPTIONS
-	handle @match-cors-api-preflight {
-		header {
-			Access-Control-Allow-Origin "{http.request.header.origin}"
-			Access-Control-Allow-Methods "GET, POST, PUT, PATCH, DELETE, OPTIONS"
-			Access-Control-Allow-Headers "Origin, Accept, Authorization, Content-Type, X-Requested-With"
-			Access-Control-Allow-Credentials "true"
-			Access-Control-Max-Age "3600"
-			defer
-		}
-		respond "" 204
-	}
-
-	@match-cors-api-request {
-		not {
-			header Origin "{http.request.scheme}://{http.request.host}"
-		}
-		header Origin "{http.request.header.origin}"
-	}
-	handle @match-cors-api-request {
-		header {
-			Access-Control-Allow-Origin "{http.request.header.origin}"
-			Access-Control-Allow-Methods "GET, POST, PUT, PATCH, DELETE, OPTIONS"
-			Access-Control-Allow-Headers "Origin, Accept, Authorization, Content-Type, X-Requested-With"
-			Access-Control-Allow-Credentials "true"
-			Access-Control-Max-Age "3600"
-			defer
-		}
-	}
-}
-
-# replace localhost with example.com or whatever
-localhost {
-	## HTTP Basic Auth
-	## (uncomment to enable)
-	# basicauth {
-	# 	# see .example.env for how to generate tokens
-	# 	{env.OLLAMA_API_ID} {env.OLLAMA_API_TOKEN_DIGEST}
-	# }
-
-	handle /api/* {
-		# Comment to disable CORS
-		import cors-api
-
-		reverse_proxy localhost:11434
-	}
-
-	# Same-Origin Static Web Server
-	file_server {
-		root ./build/
-	}
-}

backend/open_webui/config.py

@@ -109,54 +109,7 @@ if os.path.exists(f"{DATA_DIR}/config.json"):
 
 DEFAULT_CONFIG = {
     "version": 0,
-    "ui": {
+    "ui": {},
-        "default_locale": "",
-        "prompt_suggestions": [
-            {
-                "title": [
-                    "Help me study",
-                    "vocabulary for a college entrance exam",
-                ],
-                "content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option.",
-            },
-            {
-                "title": [
-                    "Give me ideas",
-                    "for what to do with my kids' art",
-                ],
-                "content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter.",
-            },
-            {
-                "title": ["Tell me a fun fact", "about the Roman Empire"],
-                "content": "Tell me a random fun fact about the Roman Empire",
-            },
-            {
-                "title": [
-                    "Show me a code snippet",
-                    "of a website's sticky header",
-                ],
-                "content": "Show me a code snippet of a website's sticky header in CSS and JavaScript.",
-            },
-            {
-                "title": [
-                    "Explain options trading",
-                    "if I'm familiar with buying and selling stocks",
-                ],
-                "content": "Explain options trading in simple terms if I'm familiar with buying and selling stocks.",
-            },
-            {
-                "title": ["Overcome procrastination", "give me tips"],
-                "content": "Could you start by asking me about instances when I procrastinate the most and then give me some suggestions to overcome it?",
-            },
-            {
-                "title": [
-                    "Grammar check",
-                    "rewrite it for better readability ",
-                ],
-                "content": 'Check the following sentence for grammar and clarity: "[sentence]". Rewrite it for better readability while maintaining its original meaning.',
-            },
-        ],
-    },
 }
 
 
@@ -552,6 +505,12 @@ OAUTH_ALLOWED_DOMAINS = PersistentConfig(
     ],
 )
 
+OAUTH_UPDATE_PICTURE_ON_LOGIN = PersistentConfig(
+    "OAUTH_UPDATE_PICTURE_ON_LOGIN",
+    "oauth.update_picture_on_login",
+    os.environ.get("OAUTH_UPDATE_PICTURE_ON_LOGIN", "False").lower() == "true",
+)
+
 
 def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
@@ -761,9 +720,10 @@ S3_BUCKET_NAME = os.environ.get("S3_BUCKET_NAME", None)
 S3_KEY_PREFIX = os.environ.get("S3_KEY_PREFIX", None)
 S3_ENDPOINT_URL = os.environ.get("S3_ENDPOINT_URL", None)
 S3_USE_ACCELERATE_ENDPOINT = (
-    os.environ.get("S3_USE_ACCELERATE_ENDPOINT", "False").lower() == "true"
+    os.environ.get("S3_USE_ACCELERATE_ENDPOINT", "false").lower() == "true"
 )
 S3_ADDRESSING_STYLE = os.environ.get("S3_ADDRESSING_STYLE", None)
+S3_ENABLE_TAGGING = os.getenv("S3_ENABLE_TAGGING", "false").lower() == "true"
 
 GCS_BUCKET_NAME = os.environ.get("GCS_BUCKET_NAME", None)
 GOOGLE_APPLICATION_CREDENTIALS_JSON = os.environ.get(
@@ -1255,7 +1215,16 @@ ENABLE_USER_WEBHOOKS = PersistentConfig(
 )
 
 # FastAPI / AnyIO settings
-THREAD_POOL_SIZE = int(os.getenv("THREAD_POOL_SIZE", "0"))
+THREAD_POOL_SIZE = os.getenv("THREAD_POOL_SIZE", None)
+
+if THREAD_POOL_SIZE is not None and isinstance(THREAD_POOL_SIZE, str):
+    try:
+        THREAD_POOL_SIZE = int(THREAD_POOL_SIZE)
+    except ValueError:
+        log.warning(
+            f"THREAD_POOL_SIZE is not a valid integer: {THREAD_POOL_SIZE}. Defaulting to None."
+        )
+        THREAD_POOL_SIZE = None
 
 
 def validate_cors_origins(origins):
@@ -1357,6 +1326,9 @@ Generate a concise, 3-5 word title with an emoji summarizing the chat history.
 - Use emojis that enhance understanding of the topic, but avoid quotation marks or special formatting.
 - Write the title in the chat's primary language; default to English if multilingual.
 - Prioritize accuracy over excessive creativity; keep it clear and simple.
+- Your entire response must consist solely of the JSON object, without any introductory or concluding text.
+- The output must be a single, raw JSON object, without any markdown code fences or other encapsulating text.
+- Ensure no conversational text, affirmations, or explanations precede or follow the raw JSON output, as this will cause direct parsing failure.
 ### Output:
 JSON format: { "title": "your concise title here" }
 ### Examples:
@@ -1699,7 +1671,8 @@ DEFAULT_CODE_INTERPRETER_PROMPT = """
 1. **Code Interpreter**: `<code_interpreter type="code" lang="python"></code_interpreter>`
    - You have access to a Python shell that runs directly in the user's browser, enabling fast execution of code for analysis, calculations, or problem-solving.  Use it in this response.
    - The Python code you write can incorporate a wide array of libraries, handle data manipulation or visualization, perform API calls for web-related tasks, or tackle virtually any computational challenge. Use this flexibility to **think outside the box, craft elegant solutions, and harness Python's full potential**.
-   - To use it, **you must enclose your code within `<code_interpreter type="code" lang="python">` XML tags** and stop right away. If you don't, the code won't execute. Do NOT use triple backticks.
+   - To use it, **you must enclose your code within `<code_interpreter type="code" lang="python">` XML tags** and stop right away. If you don't, the code won't execute. 
+   - When writing code in the code_interpreter XML tag, Do NOT use the triple backticks code block for markdown formatting, example: ```py # python code ``` will cause an error because it is markdown formatting, it is not python code.
    - When coding, **always aim to print meaningful outputs** (e.g., results, tables, summaries, or visuals) to better interpret and verify the findings. Avoid relying on implicit outputs; prioritize explicit and clear print statements so the results are effectively communicated to the user.  
    - After obtaining the printed output, **always provide a concise analysis, interpretation, or next steps to help the user understand the findings or refine the outcome further.**  
    - If the results are unclear, unexpected, or require validation, refine the code and execute it again as needed. Always aim to deliver meaningful insights from the results, iterating if necessary.  
@@ -1746,6 +1719,12 @@ MILVUS_URI = os.environ.get("MILVUS_URI", f"{DATA_DIR}/vector_db/milvus.db")
 MILVUS_DB = os.environ.get("MILVUS_DB", "default")
 MILVUS_TOKEN = os.environ.get("MILVUS_TOKEN", None)
 
+MILVUS_INDEX_TYPE = os.environ.get("MILVUS_INDEX_TYPE", "HNSW")
+MILVUS_METRIC_TYPE = os.environ.get("MILVUS_METRIC_TYPE", "COSINE")
+MILVUS_HNSW_M = int(os.environ.get("MILVUS_HNSW_M", "16"))
+MILVUS_HNSW_EFCONSTRUCTION = int(os.environ.get("MILVUS_HNSW_EFCONSTRUCTION", "100"))
+MILVUS_IVF_FLAT_NLIST = int(os.environ.get("MILVUS_IVF_FLAT_NLIST", "128"))
+
 # Qdrant
 QDRANT_URI = os.environ.get("QDRANT_URI", None)
 QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY", None)
@@ -1833,6 +1812,11 @@ ONEDRIVE_SHAREPOINT_URL = PersistentConfig(
     os.environ.get("ONEDRIVE_SHAREPOINT_URL", ""),
 )
 
+ONEDRIVE_SHAREPOINT_TENANT_ID = PersistentConfig(
+    "ONEDRIVE_SHAREPOINT_TENANT_ID",
+    "onedrive.sharepoint_tenant_id",
+    os.environ.get("ONEDRIVE_SHAREPOINT_TENANT_ID", ""),
+)
 
 # RAG Content Extraction
 CONTENT_EXTRACTION_ENGINE = PersistentConfig(
@@ -1981,6 +1965,12 @@ RAG_EMBEDDING_PREFIX_FIELD_NAME = os.environ.get(
     "RAG_EMBEDDING_PREFIX_FIELD_NAME", None
 )
 
+RAG_RERANKING_ENGINE = PersistentConfig(
+    "RAG_RERANKING_ENGINE",
+    "rag.reranking_engine",
+    os.environ.get("RAG_RERANKING_ENGINE", ""),
+)
+
 RAG_RERANKING_MODEL = PersistentConfig(
     "RAG_RERANKING_MODEL",
     "rag.reranking_model",
@@ -1989,6 +1979,7 @@ RAG_RERANKING_MODEL = PersistentConfig(
 if RAG_RERANKING_MODEL.value != "":
     log.info(f"Reranking model set: {RAG_RERANKING_MODEL.value}")
 
+
 RAG_RERANKING_MODEL_AUTO_UPDATE = (
     not OFFLINE_MODE
     and os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "True").lower() == "true"
@@ -1998,6 +1989,18 @@ RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
     os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "True").lower() == "true"
 )
 
+RAG_EXTERNAL_RERANKER_URL = PersistentConfig(
+    "RAG_EXTERNAL_RERANKER_URL",
+    "rag.external_reranker_url",
+    os.environ.get("RAG_EXTERNAL_RERANKER_URL", ""),
+)
+
+RAG_EXTERNAL_RERANKER_API_KEY = PersistentConfig(
+    "RAG_EXTERNAL_RERANKER_API_KEY",
+    "rag.external_reranker_api_key",
+    os.environ.get("RAG_EXTERNAL_RERANKER_API_KEY", ""),
+)
+
 
 RAG_TEXT_SPLITTER = PersistentConfig(
     "RAG_TEXT_SPLITTER",

backend/open_webui/main.py

@@ -103,6 +103,7 @@ from open_webui.config import (
     ENABLE_OPENAI_API,
     ONEDRIVE_CLIENT_ID,
     ONEDRIVE_SHAREPOINT_URL,
+    ONEDRIVE_SHAREPOINT_TENANT_ID,
     OPENAI_API_BASE_URLS,
     OPENAI_API_KEYS,
     OPENAI_API_CONFIGS,
@@ -187,7 +188,10 @@ from open_webui.config import (
     RAG_EMBEDDING_MODEL,
     RAG_EMBEDDING_MODEL_AUTO_UPDATE,
     RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
+    RAG_RERANKING_ENGINE,
     RAG_RERANKING_MODEL,
+    RAG_EXTERNAL_RERANKER_URL,
+    RAG_EXTERNAL_RERANKER_API_KEY,
     RAG_RERANKING_MODEL_AUTO_UPDATE,
     RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
     RAG_EMBEDDING_ENGINE,
@@ -255,6 +259,7 @@ from open_webui.config import (
     GOOGLE_DRIVE_API_KEY,
     ONEDRIVE_CLIENT_ID,
     ONEDRIVE_SHAREPOINT_URL,
+    ONEDRIVE_SHAREPOINT_TENANT_ID,
     ENABLE_RAG_HYBRID_SEARCH,
     ENABLE_RAG_LOCAL_WEB_FETCH,
     ENABLE_WEB_LOADER_SSL_VERIFICATION,
@@ -459,10 +464,9 @@ async def lifespan(app: FastAPI):
     log.info("Installing external dependencies of functions and tools...")
     install_tool_and_function_dependencies()
 
-    pool_size = THREAD_POOL_SIZE
+    if THREAD_POOL_SIZE and THREAD_POOL_SIZE > 0:
-    if pool_size and pool_size > 0:
         limiter = anyio.to_thread.current_default_thread_limiter()
-        limiter.total_tokens = pool_size
+        limiter.total_tokens = THREAD_POOL_SIZE
 
     asyncio.create_task(periodic_usage_pool_cleanup())
 
@@ -654,7 +658,12 @@ 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
 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
+
 app.state.config.RAG_TEMPLATE = RAG_TEMPLATE
 
 app.state.config.RAG_OPENAI_API_BASE_URL = RAG_OPENAI_API_BASE_URL
@@ -735,7 +744,10 @@ try:
     )
 
     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,
     )
 except Exception as e:
@@ -1381,6 +1393,7 @@ async def get_app_config(request: Request):
                 "onedrive": {
                     "client_id": ONEDRIVE_CLIENT_ID.value,
                     "sharepoint_url": ONEDRIVE_SHAREPOINT_URL.value,
+                    "sharepoint_tenant_id": ONEDRIVE_SHAREPOINT_TENANT_ID.value,
                 },
                 "license_metadata": app.state.LICENSE_METADATA,
                 **(

backend/open_webui/retrieval/models/external.py

@@ -0,0 +1,58 @@
+import logging
+import requests
+from typing import Optional, List, Tuple
+
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+class ExternalReranker:
+    def __init__(
+        self,
+        api_key: str,
+        url: str = "http://localhost:8080/v1/rerank",
+        model: str = "reranker",
+    ):
+        self.api_key = api_key
+        self.url = url
+        self.model = model
+
+    def predict(self, sentences: List[Tuple[str, str]]) -> Optional[List[float]]:
+        query = sentences[0][0]
+        docs = [i[1] for i in sentences]
+
+        payload = {
+            "model": self.model,
+            "query": query,
+            "documents": docs,
+            "top_n": len(docs),
+        }
+
+        try:
+            log.info(f"ExternalReranker:predict:model {self.model}")
+            log.info(f"ExternalReranker:predict:query {query}")
+
+            r = requests.post(
+                f"{self.url}",
+                headers={
+                    "Content-Type": "application/json",
+                    "Authorization": f"Bearer {self.api_key}",
+                },
+                json=payload,
+            )
+
+            r.raise_for_status()
+            data = r.json()
+
+            if "results" in data:
+                sorted_results = sorted(data["results"], key=lambda x: x["index"])
+                return [result["relevance_score"] for result in sorted_results]
+            else:
+                log.error("No results found in external reranking response")
+                return None
+
+        except Exception as e:
+            log.exception(f"Error in external reranking: {e}")
+            return None

backend/open_webui/retrieval/vector/dbs/milvus.py

@@ -3,7 +3,6 @@ from pymilvus import FieldSchema, DataType
 import json
 import logging
 from typing import Optional
-
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
@@ -14,6 +13,11 @@ from open_webui.config import (
     MILVUS_URI,
     MILVUS_DB,
     MILVUS_TOKEN,
+    MILVUS_INDEX_TYPE,
+    MILVUS_METRIC_TYPE,
+    MILVUS_HNSW_M,
+    MILVUS_HNSW_EFCONSTRUCTION,
+    MILVUS_IVF_FLAT_NLIST,
 )
 from open_webui.env import SRC_LOG_LEVELS
 
@@ -33,7 +37,6 @@ class MilvusClient(VectorDBBase):
         ids = []
         documents = []
         metadatas = []
-
         for match in result:
             _ids = []
             _documents = []
@@ -42,11 +45,9 @@ class MilvusClient(VectorDBBase):
                 _ids.append(item.get("id"))
                 _documents.append(item.get("data", {}).get("text"))
                 _metadatas.append(item.get("metadata"))
-
             ids.append(_ids)
             documents.append(_documents)
             metadatas.append(_metadatas)
-
         return GetResult(
             **{
                 "ids": ids,
@@ -60,13 +61,11 @@ class MilvusClient(VectorDBBase):
         distances = []
         documents = []
         metadatas = []
-
         for match in result:
             _ids = []
             _distances = []
             _documents = []
             _metadatas = []
-
             for item in match:
                 _ids.append(item.get("id"))
                 # normalize milvus score from [-1, 1] to [0, 1] range
@@ -75,12 +74,10 @@ class MilvusClient(VectorDBBase):
                 _distances.append(_dist)
                 _documents.append(item.get("entity", {}).get("data", {}).get("text"))
                 _metadatas.append(item.get("entity", {}).get("metadata"))
-
             ids.append(_ids)
             distances.append(_distances)
             documents.append(_documents)
             metadatas.append(_metadatas)
-
         return SearchResult(
             **{
                 "ids": ids,
@@ -113,11 +110,39 @@ class MilvusClient(VectorDBBase):
         )
 
         index_params = self.client.prepare_index_params()
+
+        # Use configurations from config.py
+        index_type = MILVUS_INDEX_TYPE.upper()
+        metric_type = MILVUS_METRIC_TYPE.upper()
+
+        log.info(f"Using Milvus index type: {index_type}, metric type: {metric_type}")
+
+        index_creation_params = {}
+        if index_type == "HNSW":
+            index_creation_params = {
+                "M": MILVUS_HNSW_M,
+                "efConstruction": MILVUS_HNSW_EFCONSTRUCTION,
+            }
+            log.info(f"HNSW params: {index_creation_params}")
+        elif index_type == "IVF_FLAT":
+            index_creation_params = {"nlist": MILVUS_IVF_FLAT_NLIST}
+            log.info(f"IVF_FLAT params: {index_creation_params}")
+        elif index_type in ["FLAT", "AUTOINDEX"]:
+            log.info(f"Using {index_type} index with no specific build-time params.")
+        else:
+            log.warning(
+                f"Unsupported MILVUS_INDEX_TYPE: '{index_type}'. "
+                f"Supported types: HNSW, IVF_FLAT, FLAT, AUTOINDEX. "
+                f"Milvus will use its default for the collection if this type is not directly supported for index creation."
+            )
+            # For unsupported types, pass the type directly to Milvus; it might handle it or use a default.
+            # If Milvus errors out, the user needs to correct the MILVUS_INDEX_TYPE env var.
+
         index_params.add_index(
             field_name="vector",
-            index_type="HNSW",
+            index_type=index_type,
-            metric_type="COSINE",
+            metric_type=metric_type,
-            params={"M": 16, "efConstruction": 100},
+            params=index_creation_params,
         )
 
         self.client.create_collection(
@@ -125,6 +150,9 @@ class MilvusClient(VectorDBBase):
             schema=schema,
             index_params=index_params,
         )
+        log.info(
+            f"Successfully created collection '{self.collection_prefix}_{collection_name}' with index type '{index_type}' and metric '{metric_type}'."
+        )
 
     def has_collection(self, collection_name: str) -> bool:
         # Check if the collection exists based on the collection name.
@@ -145,84 +173,113 @@ class MilvusClient(VectorDBBase):
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
         collection_name = collection_name.replace("-", "_")
+        # For some index types like IVF_FLAT, search params like nprobe can be set.
+        # Example: search_params = {"nprobe": 10} if using IVF_FLAT
+        # For simplicity, not adding configurable search_params here, but could be extended.
         result = self.client.search(
             collection_name=f"{self.collection_prefix}_{collection_name}",
             data=vectors,
             limit=limit,
             output_fields=["data", "metadata"],
+            # search_params=search_params # Potentially add later if needed
         )
-
         return self._result_to_search_result(result)
 
     def query(self, collection_name: str, filter: dict, limit: Optional[int] = None):
         # Construct the filter string for querying
         collection_name = collection_name.replace("-", "_")
         if not self.has_collection(collection_name):
+            log.warning(
+                f"Query attempted on non-existent collection: {self.collection_prefix}_{collection_name}"
+            )
             return None
-
         filter_string = " && ".join(
             [
                 f'metadata["{key}"] == {json.dumps(value)}'
                 for key, value in filter.items()
             ]
         )
-
         max_limit = 16383  # The maximum number of records per request
         all_results = []
-
         if limit is None:
-            limit = float("inf")  # Use infinity as a placeholder for no limit
+            # Milvus default limit for query if not specified is 16384, but docs mention iteration.
+            # Let's set a practical high number if "all" is intended, or handle true pagination.
+            # For now, if limit is None, we'll fetch in batches up to a very large number.
+            # This part could be refined based on expected use cases for "get all".
+            # For this function signature, None implies "as many as possible" up to Milvus limits.
+            limit = (
+                16384 * 10
+            )  # A large number to signify fetching many, will be capped by actual data or max_limit per call.
+            log.info(
+                f"Limit not specified for query, fetching up to {limit} results in batches."
+            )
 
         # Initialize offset and remaining to handle pagination
         offset = 0
         remaining = limit
 
         try:
+            log.info(
+                f"Querying collection {self.collection_prefix}_{collection_name} with filter: '{filter_string}', limit: {limit}"
+            )
             # Loop until there are no more items to fetch or the desired limit is reached
             while remaining > 0:
-                log.info(f"remaining: {remaining}")
                 current_fetch = min(
-                    max_limit, remaining
+                    max_limit, remaining if isinstance(remaining, int) else max_limit
-                )  # Determine how many items to fetch in this iteration
+                )
+                log.debug(
+                    f"Querying with offset: {offset}, current_fetch: {current_fetch}"
+                )
 
                 results = self.client.query(
                     collection_name=f"{self.collection_prefix}_{collection_name}",
                     filter=filter_string,
-                    output_fields=["*"],
+                    output_fields=[
+                        "id",
+                        "data",
+                        "metadata",
+                    ],  # Explicitly list needed fields. Vector not usually needed in query.
                     limit=current_fetch,
                     offset=offset,
                 )
 
                 if not results:
+                    log.debug("No more results from query.")
                     break
 
                 all_results.extend(results)
                 results_count = len(results)
-                remaining -= (
+                log.debug(f"Fetched {results_count} results in this batch.")
-                    results_count  # Decrease remaining by the number of items fetched
+
-                )
+                if isinstance(remaining, int):
+                    remaining -= results_count
+
                 offset += results_count
 
-                # Break the loop if the results returned are less than the requested fetch count
+                # Break the loop if the results returned are less than the requested fetch count (means end of data)
                 if results_count < current_fetch:
+                    log.debug(
+                        "Fetched less than requested, assuming end of results for this query."
+                    )
                     break
 
-            log.debug(all_results)
+            log.info(f"Total results from query: {len(all_results)}")
             return self._result_to_get_result([all_results])
         except Exception as e:
             log.exception(
-                f"Error querying collection {collection_name} with limit {limit}: {e}"
+                f"Error querying collection {self.collection_prefix}_{collection_name} with filter '{filter_string}' and limit {limit}: {e}"
             )
             return None
 
     def get(self, collection_name: str) -> Optional[GetResult]:
-        # Get all the items in the collection.
+        # Get all the items in the collection. This can be very resource-intensive for large collections.
         collection_name = collection_name.replace("-", "_")
-        result = self.client.query(
+        log.warning(
-            collection_name=f"{self.collection_prefix}_{collection_name}",
+            f"Fetching ALL items from collection '{self.collection_prefix}_{collection_name}'. This might be slow for large collections."
-            filter='id != ""',
         )
-        return self._result_to_get_result([result])
+        # Using query with a trivial filter to get all items.
+        # This will use the paginated query logic.
+        return self.query(collection_name=collection_name, filter={}, limit=None)
 
     def insert(self, collection_name: str, items: list[VectorItem]):
         # Insert the items into the collection, if the collection does not exist, it will be created.
@@ -230,10 +287,23 @@ class MilvusClient(VectorDBBase):
         if not self.client.has_collection(
             collection_name=f"{self.collection_prefix}_{collection_name}"
         ):
+            log.info(
+                f"Collection {self.collection_prefix}_{collection_name} does not exist. Creating now."
+            )
+            if not items:
+                log.error(
+                    f"Cannot create collection {self.collection_prefix}_{collection_name} without items to determine dimension."
+                )
+                raise ValueError(
+                    "Cannot create Milvus collection without items to determine vector dimension."
+                )
             self._create_collection(
                 collection_name=collection_name, dimension=len(items[0]["vector"])
             )
 
+        log.info(
+            f"Inserting {len(items)} items into collection {self.collection_prefix}_{collection_name}."
+        )
         return self.client.insert(
             collection_name=f"{self.collection_prefix}_{collection_name}",
             data=[
@@ -253,10 +323,23 @@ class MilvusClient(VectorDBBase):
         if not self.client.has_collection(
             collection_name=f"{self.collection_prefix}_{collection_name}"
         ):
+            log.info(
+                f"Collection {self.collection_prefix}_{collection_name} does not exist for upsert. Creating now."
+            )
+            if not items:
+                log.error(
+                    f"Cannot create collection {self.collection_prefix}_{collection_name} for upsert without items to determine dimension."
+                )
+                raise ValueError(
+                    "Cannot create Milvus collection for upsert without items to determine vector dimension."
+                )
             self._create_collection(
                 collection_name=collection_name, dimension=len(items[0]["vector"])
             )
 
+        log.info(
+            f"Upserting {len(items)} items into collection {self.collection_prefix}_{collection_name}."
+        )
         return self.client.upsert(
             collection_name=f"{self.collection_prefix}_{collection_name}",
             data=[
@@ -276,30 +359,55 @@ class MilvusClient(VectorDBBase):
         ids: Optional[list[str]] = None,
         filter: Optional[dict] = None,
     ):
-        # Delete the items from the collection based on the ids.
+        # Delete the items from the collection based on the ids or filter.
         collection_name = collection_name.replace("-", "_")
+        if not self.has_collection(collection_name):
+            log.warning(
+                f"Delete attempted on non-existent collection: {self.collection_prefix}_{collection_name}"
+            )
+            return None
+
         if ids:
+            log.info(
+                f"Deleting items by IDs from {self.collection_prefix}_{collection_name}. IDs: {ids}"
+            )
             return self.client.delete(
                 collection_name=f"{self.collection_prefix}_{collection_name}",
                 ids=ids,
             )
         elif filter:
-            # Convert the filter dictionary to a string using JSON_CONTAINS.
             filter_string = " && ".join(
                 [
                     f'metadata["{key}"] == {json.dumps(value)}'
                     for key, value in filter.items()
                 ]
             )
-
+            log.info(
+                f"Deleting items by filter from {self.collection_prefix}_{collection_name}. Filter: {filter_string}"
+            )
             return self.client.delete(
                 collection_name=f"{self.collection_prefix}_{collection_name}",
                 filter=filter_string,
             )
+        else:
+            log.warning(
+                f"Delete operation on {self.collection_prefix}_{collection_name} called without IDs or filter. No action taken."
+            )
+            return None
 
     def reset(self):
-        # Resets the database. This will delete all collections and item entries.
+        # Resets the database. This will delete all collections and item entries that match the prefix.
+        log.warning(
+            f"Resetting Milvus: Deleting all collections with prefix '{self.collection_prefix}'."
+        )
         collection_names = self.client.list_collections()
-        for collection_name in collection_names:
+        deleted_collections = []
-            if collection_name.startswith(self.collection_prefix):
+        for collection_name_full in collection_names:
-                self.client.drop_collection(collection_name=collection_name)
+            if collection_name_full.startswith(self.collection_prefix):
+                try:
+                    self.client.drop_collection(collection_name=collection_name_full)
+                    deleted_collections.append(collection_name_full)
+                    log.info(f"Deleted collection: {collection_name_full}")
+                except Exception as e:
+                    log.error(f"Error deleting collection {collection_name_full}: {e}")
+        log.info(f"Milvus reset complete. Deleted collections: {deleted_collections}")

backend/open_webui/retrieval/vector/dbs/pinecone.py

@@ -1,6 +1,13 @@
 from typing import Optional, List, Dict, Any, Union
 import logging
-from pinecone import Pinecone, ServerlessSpec
+import time  # for measuring elapsed time
+from pinecone import ServerlessSpec
+
+import asyncio  # for async upserts
+import functools  # for partial binding in async tasks
+
+import concurrent.futures  # for parallel batch upserts
+from pinecone.grpc import PineconeGRPC  # use gRPC client for faster upserts
 
 from open_webui.retrieval.vector.main import (
     VectorDBBase,
@@ -40,8 +47,13 @@ class PineconeClient(VectorDBBase):
         self.metric = PINECONE_METRIC
         self.cloud = PINECONE_CLOUD
 
-        # Initialize Pinecone client
+        # Initialize Pinecone gRPC client for improved performance
-        self.client = Pinecone(api_key=self.api_key)
+        self.client = PineconeGRPC(
+            api_key=self.api_key, environment=self.environment, cloud=self.cloud
+        )
+
+        # Persistent executor for batch operations
+        self._executor = concurrent.futures.ThreadPoolExecutor(max_workers=5)
 
         # Create index if it doesn't exist
         self._initialize_index()
@@ -191,27 +203,29 @@ class PineconeClient(VectorDBBase):
             log.warning("No items to insert")
             return
 
+        start_time = time.time()
+
         collection_name_with_prefix = self._get_collection_name_with_prefix(
             collection_name
         )
         points = self._create_points(items, collection_name_with_prefix)
 
-        # Insert in batches for better performance and reliability
+        # Parallelize batch inserts for performance
+        executor = self._executor
+        futures = []
         for i in range(0, len(points), BATCH_SIZE):
             batch = points[i : i + BATCH_SIZE]
+            futures.append(executor.submit(self.index.upsert, vectors=batch))
+        for future in concurrent.futures.as_completed(futures):
             try:
-                self.index.upsert(vectors=batch)
+                future.result()
-                log.debug(
-                    f"Inserted batch of {len(batch)} vectors into '{collection_name_with_prefix}'"
-                )
             except Exception as e:
-                log.error(
+                log.error(f"Error inserting batch: {e}")
-                    f"Error inserting batch into '{collection_name_with_prefix}': {e}"
-                )
                 raise
-
+        elapsed = time.time() - start_time
+        log.debug(f"Insert of {len(points)} vectors took {elapsed:.2f} seconds")
         log.info(
-            f"Successfully inserted {len(items)} vectors into '{collection_name_with_prefix}'"
+            f"Successfully inserted {len(points)} vectors in parallel batches into '{collection_name_with_prefix}'"
         )
 
     def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
@@ -220,29 +234,119 @@ class PineconeClient(VectorDBBase):
             log.warning("No items to upsert")
             return
 
+        start_time = time.time()
+
+        collection_name_with_prefix = self._get_collection_name_with_prefix(
+            collection_name
+        )
+        points = self._create_points(items, collection_name_with_prefix)
+
+        # Parallelize batch upserts for performance
+        executor = self._executor
+        futures = []
+        for i in range(0, len(points), BATCH_SIZE):
+            batch = points[i : i + BATCH_SIZE]
+            futures.append(executor.submit(self.index.upsert, vectors=batch))
+        for future in concurrent.futures.as_completed(futures):
+            try:
+                future.result()
+            except Exception as e:
+                log.error(f"Error upserting batch: {e}")
+                raise
+        elapsed = time.time() - start_time
+        log.debug(f"Upsert of {len(points)} vectors took {elapsed:.2f} seconds")
+        log.info(
+            f"Successfully upserted {len(points)} vectors in parallel batches into '{collection_name_with_prefix}'"
+        )
+
+    async def insert_async(self, collection_name: str, items: List[VectorItem]) -> None:
+        """Async version of insert using asyncio and run_in_executor for improved performance."""
+        if not items:
+            log.warning("No items to insert")
+            return
+
+        collection_name_with_prefix = self._get_collection_name_with_prefix(
+            collection_name
+        )
+        points = self._create_points(items, collection_name_with_prefix)
+
+        # Create batches
+        batches = [
+            points[i : i + BATCH_SIZE] for i in range(0, len(points), BATCH_SIZE)
+        ]
+        loop = asyncio.get_event_loop()
+        tasks = [
+            loop.run_in_executor(
+                None, functools.partial(self.index.upsert, vectors=batch)
+            )
+            for batch in batches
+        ]
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+        for result in results:
+            if isinstance(result, Exception):
+                log.error(f"Error in async insert batch: {result}")
+                raise result
+        log.info(
+            f"Successfully async inserted {len(points)} vectors in batches into '{collection_name_with_prefix}'"
+        )
+
+    async def upsert_async(self, collection_name: str, items: List[VectorItem]) -> None:
+        """Async version of upsert using asyncio and run_in_executor for improved performance."""
+        if not items:
+            log.warning("No items to upsert")
+            return
+
         collection_name_with_prefix = self._get_collection_name_with_prefix(
             collection_name
         )
         points = self._create_points(items, collection_name_with_prefix)
 
-        # Upsert in batches
+        # Create batches
-        for i in range(0, len(points), BATCH_SIZE):
+        batches = [
-            batch = points[i : i + BATCH_SIZE]
+            points[i : i + BATCH_SIZE] for i in range(0, len(points), BATCH_SIZE)
-            try:
+        ]
-                self.index.upsert(vectors=batch)
+        loop = asyncio.get_event_loop()
-                log.debug(
+        tasks = [
-                    f"Upserted batch of {len(batch)} vectors into '{collection_name_with_prefix}'"
+            loop.run_in_executor(
-                )
+                None, functools.partial(self.index.upsert, vectors=batch)
-            except Exception as e:
+            )
-                log.error(
+            for batch in batches
-                    f"Error upserting batch into '{collection_name_with_prefix}': {e}"
+        ]
-                )
+        results = await asyncio.gather(*tasks, return_exceptions=True)
-                raise
+        for result in results:
-
+            if isinstance(result, Exception):
+                log.error(f"Error in async upsert batch: {result}")
+                raise result
         log.info(
-            f"Successfully upserted {len(items)} vectors into '{collection_name_with_prefix}'"
+            f"Successfully async upserted {len(points)} vectors in batches into '{collection_name_with_prefix}'"
         )
 
+    def streaming_upsert(self, collection_name: str, items: List[VectorItem]) -> None:
+        """Perform a streaming upsert over gRPC for performance testing."""
+        if not items:
+            log.warning("No items to upsert via streaming")
+            return
+
+        collection_name_with_prefix = self._get_collection_name_with_prefix(
+            collection_name
+        )
+        points = self._create_points(items, collection_name_with_prefix)
+
+        # Open a streaming upsert channel
+        stream = self.index.streaming_upsert()
+        try:
+            for point in points:
+                # send each point over the stream
+                stream.send(point)
+            # close the stream to finalize
+            stream.close()
+            log.info(
+                f"Successfully streamed upsert of {len(points)} vectors into '{collection_name_with_prefix}'"
+            )
+        except Exception as e:
+            log.error(f"Error during streaming upsert: {e}")
+            raise
+
     def search(
         self, collection_name: str, vectors: List[List[Union[float, int]]], limit: int
     ) -> Optional[SearchResult]:
@@ -410,3 +514,20 @@ class PineconeClient(VectorDBBase):
         except Exception as e:
             log.error(f"Failed to reset Pinecone index: {e}")
             raise
+
+    def close(self):
+        """Shut down the gRPC channel and thread pool."""
+        try:
+            self.client.close()
+            log.info("Pinecone gRPC channel closed.")
+        except Exception as e:
+            log.warning(f"Failed to close Pinecone gRPC channel: {e}")
+        self._executor.shutdown(wait=True)
+
+    def __enter__(self):
+        """Enter context manager."""
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """Exit context manager, ensuring resources are cleaned up."""
+        self.close()

backend/open_webui/routers/audio.py

@@ -71,23 +71,27 @@ from pydub import AudioSegment
 from pydub.utils import mediainfo
 
 
-def get_audio_format(file_path):
+def get_audio_convert_format(file_path):
     """Check if the given file needs to be converted to a different format."""
     if not os.path.isfile(file_path):
         log.error(f"File not found: {file_path}")
         return False
 
-    info = mediainfo(file_path)
+    try:
-    if (
+        info = mediainfo(file_path)
-        info.get("codec_name") == "aac"
+
-        and info.get("codec_type") == "audio"
+        if (
-        and info.get("codec_tag_string") == "mp4a"
+            info.get("codec_name") == "aac"
-    ):
+            and info.get("codec_type") == "audio"
-        return "mp4"
+            and info.get("codec_tag_string") == "mp4a"
-    elif info.get("format_name") == "ogg":
+        ):
-        return "ogg"
+            return "mp4"
-    elif info.get("format_name") == "matroska,webm":
+        elif info.get("format_name") == "ogg":
-        return "webm"
+            return "ogg"
+    except Exception as e:
+        log.error(f"Error getting audio format: {e}")
+        return False
+
     return None
 
 
@@ -538,14 +542,17 @@ def transcribe(request: Request, file_path):
         log.debug(data)
         return data
     elif request.app.state.config.STT_ENGINE == "openai":
-        audio_format = get_audio_format(file_path)
+        convert_format = get_audio_convert_format(file_path)
-        if audio_format:
+
-            os.rename(file_path, file_path.replace(".wav", f".{audio_format}"))
+        if convert_format:
+            ext = convert_format.split(".")[-1]
+
+            os.rename(file_path, file_path.replace(".{ext}", f".{convert_format}"))
             # Convert unsupported audio file to WAV format
             convert_audio_to_wav(
-                file_path.replace(".wav", f".{audio_format}"),
+                file_path.replace(".{ext}", f".{convert_format}"),
                 file_path,
-                audio_format,
+                convert_format,
             )
 
         r = None

backend/open_webui/routers/auths.py

@@ -234,7 +234,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
             ],
         )
 
-        if not search_success:
+        if not search_success or not connection_app.entries:
             raise HTTPException(400, detail="User not found in the LDAP server")
 
         entry = connection_app.entries[0]

backend/open_webui/routers/files.py

@@ -133,6 +133,7 @@ def upload_file(
                         "audio/ogg",
                         "audio/x-m4a",
                         "audio/webm",
+                        "video/webm",
                     )
                 ):
                     file_path = Storage.get_file(file_path)
@@ -150,7 +151,6 @@ def upload_file(
                     "video/mp4",
                     "video/ogg",
                     "video/quicktime",
-                    "video/webm",
                 ]:
                     process_file(request, ProcessFileForm(file_id=id), user=user)
 

backend/open_webui/routers/retrieval.py

@@ -3,6 +3,8 @@ import logging
 import mimetypes
 import os
 import shutil
+import asyncio
+
 
 import uuid
 from datetime import datetime
@@ -135,7 +137,10 @@ def get_ef(
 
 
 def get_rf(
+    engine: str = "",
     reranking_model: Optional[str] = None,
+    external_reranker_url: str = "",
+    external_reranker_api_key: str = "",
     auto_update: bool = False,
 ):
     rf = None
@@ -153,19 +158,33 @@ def get_rf(
                 log.error(f"ColBERT: {e}")
                 raise Exception(ERROR_MESSAGES.DEFAULT(e))
         else:
-            import sentence_transformers
+            if engine == "external":
+                try:
+                    from open_webui.retrieval.models.external import ExternalReranker
+
+                    rf = ExternalReranker(
+                        url=external_reranker_url,
+                        api_key=external_reranker_api_key,
+                        model=reranking_model,
+                    )
+                except Exception as e:
+                    log.error(f"ExternalReranking: {e}")
+                    raise Exception(ERROR_MESSAGES.DEFAULT(e))
+            else:
+                import sentence_transformers
+
+                try:
+                    rf = sentence_transformers.CrossEncoder(
+                        get_model_path(reranking_model, auto_update),
+                        device=DEVICE_TYPE,
+                        trust_remote_code=RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
+                        backend=SENTENCE_TRANSFORMERS_CROSS_ENCODER_BACKEND,
+                        model_kwargs=SENTENCE_TRANSFORMERS_CROSS_ENCODER_MODEL_KWARGS,
+                    )
+                except Exception as e:
+                    log.error(f"CrossEncoder: {e}")
+                    raise Exception(ERROR_MESSAGES.DEFAULT("CrossEncoder error"))
 
-            try:
-                rf = sentence_transformers.CrossEncoder(
-                    get_model_path(reranking_model, auto_update),
-                    device=DEVICE_TYPE,
-                    trust_remote_code=RAG_RERANKING_MODEL_TRUST_REMOTE_CODE,
-                    backend=SENTENCE_TRANSFORMERS_CROSS_ENCODER_BACKEND,
-                    model_kwargs=SENTENCE_TRANSFORMERS_CROSS_ENCODER_MODEL_KWARGS,
-                )
-            except Exception as e:
-                log.error(f"CrossEncoder: {e}")
-                raise Exception(ERROR_MESSAGES.DEFAULT("CrossEncoder error"))
     return rf
 
 
@@ -188,7 +207,7 @@ class ProcessUrlForm(CollectionNameForm):
 
 
 class SearchForm(BaseModel):
-    query: str
+    queries: List[str]
 
 
 @router.get("/")
@@ -223,14 +242,6 @@ async def get_embedding_config(request: Request, user=Depends(get_admin_user)):
     }
 
 
-@router.get("/reranking")
-async def get_reraanking_config(request: Request, user=Depends(get_admin_user)):
-    return {
-        "status": True,
-        "reranking_model": request.app.state.config.RAG_RERANKING_MODEL,
-    }
-
-
 class OpenAIConfigForm(BaseModel):
     url: str
     key: str
@@ -325,41 +336,6 @@ async def update_embedding_config(
         )
 
 
-class RerankingModelUpdateForm(BaseModel):
-    reranking_model: str
-
-
-@router.post("/reranking/update")
-async def update_reranking_config(
-    request: Request, form_data: RerankingModelUpdateForm, user=Depends(get_admin_user)
-):
-    log.info(
-        f"Updating reranking model: {request.app.state.config.RAG_RERANKING_MODEL} to {form_data.reranking_model}"
-    )
-    try:
-        request.app.state.config.RAG_RERANKING_MODEL = form_data.reranking_model
-
-        try:
-            request.app.state.rf = get_rf(
-                request.app.state.config.RAG_RERANKING_MODEL,
-                True,
-            )
-        except Exception as e:
-            log.error(f"Error loading reranking model: {e}")
-            request.app.state.config.ENABLE_RAG_HYBRID_SEARCH = False
-
-        return {
-            "status": True,
-            "reranking_model": request.app.state.config.RAG_RERANKING_MODEL,
-        }
-    except Exception as e:
-        log.exception(f"Problem updating reranking model: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
-
-
 @router.get("/config")
 async def get_rag_config(request: Request, user=Depends(get_admin_user)):
     return {
@@ -383,6 +359,11 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
+        # Reranking settings
+        "RAG_RERANKING_MODEL": request.app.state.config.RAG_RERANKING_MODEL,
+        "RAG_RERANKING_ENGINE": request.app.state.config.RAG_RERANKING_ENGINE,
+        "RAG_EXTERNAL_RERANKER_URL": request.app.state.config.RAG_EXTERNAL_RERANKER_URL,
+        "RAG_EXTERNAL_RERANKER_API_KEY": request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
         # Chunking settings
         "TEXT_SPLITTER": request.app.state.config.TEXT_SPLITTER,
         "CHUNK_SIZE": request.app.state.config.CHUNK_SIZE,
@@ -519,6 +500,12 @@ class ConfigForm(BaseModel):
     DOCUMENT_INTELLIGENCE_KEY: Optional[str] = None
     MISTRAL_OCR_API_KEY: Optional[str] = None
 
+    # Reranking settings
+    RAG_RERANKING_MODEL: Optional[str] = None
+    RAG_RERANKING_ENGINE: Optional[str] = None
+    RAG_EXTERNAL_RERANKER_URL: Optional[str] = None
+    RAG_EXTERNAL_RERANKER_API_KEY: Optional[str] = None
+
     # Chunking settings
     TEXT_SPLITTER: Optional[str] = None
     CHUNK_SIZE: Optional[int] = None
@@ -630,6 +617,49 @@ async def update_rag_config(
         else request.app.state.config.MISTRAL_OCR_API_KEY
     )
 
+    # Reranking settings
+    request.app.state.config.RAG_RERANKING_ENGINE = (
+        form_data.RAG_RERANKING_ENGINE
+        if form_data.RAG_RERANKING_ENGINE is not None
+        else request.app.state.config.RAG_RERANKING_ENGINE
+    )
+
+    request.app.state.config.RAG_EXTERNAL_RERANKER_URL = (
+        form_data.RAG_EXTERNAL_RERANKER_URL
+        if form_data.RAG_EXTERNAL_RERANKER_URL is not None
+        else request.app.state.config.RAG_EXTERNAL_RERANKER_URL
+    )
+
+    request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY = (
+        form_data.RAG_EXTERNAL_RERANKER_API_KEY
+        if form_data.RAG_EXTERNAL_RERANKER_API_KEY is not None
+        else request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY
+    )
+
+    log.info(
+        f"Updating reranking model: {request.app.state.config.RAG_RERANKING_MODEL} to {form_data.RAG_RERANKING_MODEL}"
+    )
+    try:
+        request.app.state.config.RAG_RERANKING_MODEL = form_data.RAG_RERANKING_MODEL
+
+        try:
+            request.app.state.rf = get_rf(
+                request.app.state.config.RAG_RERANKING_ENGINE,
+                request.app.state.config.RAG_RERANKING_MODEL,
+                request.app.state.config.RAG_EXTERNAL_RERANKER_URL,
+                request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
+                True,
+            )
+        except Exception as e:
+            log.error(f"Error loading reranking model: {e}")
+            request.app.state.config.ENABLE_RAG_HYBRID_SEARCH = False
+    except Exception as e:
+        log.exception(f"Problem updating reranking model: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
+
     # Chunking settings
     request.app.state.config.TEXT_SPLITTER = (
         form_data.TEXT_SPLITTER
@@ -786,6 +816,11 @@ async def update_rag_config(
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
+        # Reranking settings
+        "RAG_RERANKING_MODEL": request.app.state.config.RAG_RERANKING_MODEL,
+        "RAG_RERANKING_ENGINE": request.app.state.config.RAG_RERANKING_ENGINE,
+        "RAG_EXTERNAL_RERANKER_URL": request.app.state.config.RAG_EXTERNAL_RERANKER_URL,
+        "RAG_EXTERNAL_RERANKER_API_KEY": request.app.state.config.RAG_EXTERNAL_RERANKER_API_KEY,
         # Chunking settings
         "TEXT_SPLITTER": request.app.state.config.TEXT_SPLITTER,
         "CHUNK_SIZE": request.app.state.config.CHUNK_SIZE,
@@ -1568,16 +1603,34 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
 async def process_web_search(
     request: Request, form_data: SearchForm, user=Depends(get_verified_user)
 ):
+
+    urls = []
     try:
         logging.info(
-            f"trying to web search with {request.app.state.config.WEB_SEARCH_ENGINE, form_data.query}"
+            f"trying to web search with {request.app.state.config.WEB_SEARCH_ENGINE, form_data.queries}"
-        )
-        web_results = await run_in_threadpool(
-            search_web,
-            request,
-            request.app.state.config.WEB_SEARCH_ENGINE,
-            form_data.query,
         )
+
+        search_tasks = [
+            run_in_threadpool(
+                search_web,
+                request,
+                request.app.state.config.WEB_SEARCH_ENGINE,
+                query,
+            )
+            for query in form_data.queries
+        ]
+
+        search_results = await asyncio.gather(*search_tasks)
+
+        for result in search_results:
+            if result:
+                for item in result:
+                    if item and item.link:
+                        urls.append(item.link)
+
+        urls = list(dict.fromkeys(urls))
+        log.debug(f"urls: {urls}")
+
     except Exception as e:
         log.exception(e)
 
@@ -1586,10 +1639,7 @@ async def process_web_search(
             detail=ERROR_MESSAGES.WEB_SEARCH_ERROR(e),
         )
 
-    log.debug(f"web_results: {web_results}")
-
     try:
-        urls = [result.link for result in web_results]
         loader = get_web_loader(
             urls,
             verify_ssl=request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
@@ -1599,7 +1649,7 @@ async def process_web_search(
         docs = await loader.aload()
         urls = [
             doc.metadata.get("source") for doc in docs if doc.metadata.get("source")
-        ]  # only keep URLs
+        ]  # only keep the urls returned by the loader
 
         if request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL:
             return {
@@ -1616,29 +1666,28 @@ async def process_web_search(
                 "loaded_count": len(docs),
             }
         else:
-            collection_names = []
+            # Create a single collection for all documents
-            for doc_idx, doc in enumerate(docs):
+            collection_name = (
-                if doc and doc.page_content:
+                f"web-search-{calculate_sha256_string('-'.join(form_data.queries))}"[
-                    try:
+                    :63
-                        collection_name = f"web-search-{calculate_sha256_string(form_data.query + '-' + urls[doc_idx])}"[
+                ]
-                            :63
+            )
-                        ]
 
-                        collection_names.append(collection_name)
+            try:
-                        await run_in_threadpool(
+                await run_in_threadpool(
-                            save_docs_to_vector_db,
+                    save_docs_to_vector_db,
-                            request,
+                    request,
-                            [doc],
+                    docs,
-                            collection_name,
+                    collection_name,
-                            overwrite=True,
+                    overwrite=True,
-                            user=user,
+                    user=user,
-                        )
+                )
-                    except Exception as e:
+            except Exception as e:
-                        log.debug(f"error saving doc {doc_idx}: {e}")
+                log.debug(f"error saving docs: {e}")
 
             return {
                 "status": True,
-                "collection_names": collection_names,
+                "collection_names": [collection_name],
                 "filenames": urls,
                 "loaded_count": len(docs),
             }

backend/open_webui/routers/tasks.py

@@ -186,20 +186,9 @@ async def generate_title(
     else:
         template = DEFAULT_TITLE_GENERATION_PROMPT_TEMPLATE
 
-    messages = form_data["messages"]
-
-    # Remove reasoning details from the messages
-    for message in messages:
-        message["content"] = re.sub(
-            r"<details\s+type=\"reasoning\"[^>]*>.*?<\/details>",
-            "",
-            message["content"],
-            flags=re.S,
-        ).strip()
-
     content = title_generation_template(
         template,
-        messages,
+        form_data["messages"],
         {
             "name": user.name,
             "location": user.info.get("location") if user.info else None,

backend/open_webui/routers/users.py

@@ -34,7 +34,7 @@ router = APIRouter()
 ############################
 
 
-PAGE_ITEM_COUNT = 10
+PAGE_ITEM_COUNT = 30
 
 
 @router.get("/", response_model=UserListResponse)

backend/open_webui/socket/main.py

@@ -159,18 +159,19 @@ def get_models_in_use():
 
 @sio.on("usage")
 async def usage(sid, data):
-    model_id = data["model"]
+    if sid in SESSION_POOL:
-    # Record the timestamp for the last update
+        model_id = data["model"]
-    current_time = int(time.time())
+        # Record the timestamp for the last update
+        current_time = int(time.time())
 
-    # Store the new usage data and task
+        # Store the new usage data and task
-    USAGE_POOL[model_id] = {
+        USAGE_POOL[model_id] = {
-        **(USAGE_POOL[model_id] if model_id in USAGE_POOL else {}),
+            **(USAGE_POOL[model_id] if model_id in USAGE_POOL else {}),
-        sid: {"updated_at": current_time},
+            sid: {"updated_at": current_time},
-    }
+        }
 
-    # Broadcast the usage data to all clients
+        # Broadcast the usage data to all clients
-    await sio.emit("usage", {"models": get_models_in_use()})
+        await sio.emit("usage", {"models": get_models_in_use()})
 
 
 @sio.event
@@ -192,9 +193,6 @@ async def connect(sid, environ, auth):
             # print(f"user {user.name}({user.id}) connected with session ID {sid}")
             await sio.emit("user-list", {"user_ids": list(USER_POOL.keys())})
             await sio.emit("usage", {"models": get_models_in_use()})
-            return True
-
-    return False
 
 
 @sio.on("user-join")
@@ -281,7 +279,8 @@ async def channel_events(sid, data):
 
 @sio.on("user-list")
 async def user_list(sid):
-    await sio.emit("user-list", {"user_ids": list(USER_POOL.keys())})
+    if sid in SESSION_POOL:
+        await sio.emit("user-list", {"user_ids": list(USER_POOL.keys())})
 
 
 @sio.event

backend/open_webui/storage/provider.py

@@ -17,6 +17,7 @@ from open_webui.config import (
     S3_SECRET_ACCESS_KEY,
     S3_USE_ACCELERATE_ENDPOINT,
     S3_ADDRESSING_STYLE,
+    S3_ENABLE_TAGGING,
     GCS_BUCKET_NAME,
     GOOGLE_APPLICATION_CREDENTIALS_JSON,
     AZURE_STORAGE_ENDPOINT,
@@ -140,18 +141,19 @@ class S3StorageProvider(StorageProvider):
     ) -> Tuple[bytes, str]:
         """Handles uploading of the file to S3 storage."""
         _, file_path = LocalStorageProvider.upload_file(file, filename, tags)
-        tagging = {"TagSet": [{"Key": k, "Value": v} for k, v in tags.items()]}
+        s3_key = os.path.join(self.key_prefix, filename)
         try:
-            s3_key = os.path.join(self.key_prefix, filename)
             self.s3_client.upload_file(file_path, self.bucket_name, s3_key)
-            self.s3_client.put_object_tagging(
+            if S3_ENABLE_TAGGING and tags:
-                Bucket=self.bucket_name,
+                tagging = {"TagSet": [{"Key": k, "Value": v} for k, v in tags.items()]}
-                Key=s3_key,
+                self.s3_client.put_object_tagging(
-                Tagging=tagging,
+                    Bucket=self.bucket_name,
-            )
+                    Key=s3_key,
+                    Tagging=tagging,
+                )
             return (
                 open(file_path, "rb").read(),
-                "s3://" + self.bucket_name + "/" + s3_key,
+                f"s3://{self.bucket_name}/{s3_key}",
             )
         except ClientError as e:
             raise RuntimeError(f"Error uploading file to S3: {e}")

backend/open_webui/utils/code_interpreter.py

@@ -44,12 +44,14 @@ class JupyterCodeExecuter:
         :param password: Jupyter password (optional)
         :param timeout: WebSocket timeout in seconds (default: 60s)
         """
-        self.base_url = base_url.rstrip("/")
+        self.base_url = base_url
         self.code = code
         self.token = token
         self.password = password
         self.timeout = timeout
         self.kernel_id = ""
+        if self.base_url[-1] != "/":
+            self.base_url += "/"
         self.session = aiohttp.ClientSession(trust_env=True, base_url=self.base_url)
         self.params = {}
         self.result = ResultModel()
@@ -61,7 +63,7 @@ class JupyterCodeExecuter:
         if self.kernel_id:
             try:
                 async with self.session.delete(
-                    f"/api/kernels/{self.kernel_id}", params=self.params
+                    f"api/kernels/{self.kernel_id}", params=self.params
                 ) as response:
                     response.raise_for_status()
             except Exception as err:
@@ -81,7 +83,7 @@ class JupyterCodeExecuter:
     async def sign_in(self) -> None:
         # password authentication
         if self.password and not self.token:
-            async with self.session.get("/login") as response:
+            async with self.session.get("login") as response:
                 response.raise_for_status()
                 xsrf_token = response.cookies["_xsrf"].value
                 if not xsrf_token:
@@ -89,7 +91,7 @@ class JupyterCodeExecuter:
                 self.session.cookie_jar.update_cookies(response.cookies)
                 self.session.headers.update({"X-XSRFToken": xsrf_token})
             async with self.session.post(
-                "/login",
+                "login",
                 data={"_xsrf": xsrf_token, "password": self.password},
                 allow_redirects=False,
             ) as response:
@@ -101,17 +103,15 @@ class JupyterCodeExecuter:
             self.params.update({"token": self.token})
 
     async def init_kernel(self) -> None:
-        async with self.session.post(
+        async with self.session.post(url="api/kernels", params=self.params) as response:
-            url="/api/kernels", params=self.params
-        ) as response:
             response.raise_for_status()
             kernel_data = await response.json()
             self.kernel_id = kernel_data["id"]
 
     def init_ws(self) -> (str, dict):
-        ws_base = self.base_url.replace("http", "ws")
+        ws_base = self.base_url.replace("http", "ws", 1)
         ws_params = "?" + "&".join([f"{key}={val}" for key, val in self.params.items()])
-        websocket_url = f"{ws_base}/api/kernels/{self.kernel_id}/channels{ws_params if len(ws_params) > 1 else ''}"
+        websocket_url = f"{ws_base}api/kernels/{self.kernel_id}/channels{ws_params if len(ws_params) > 1 else ''}"
         ws_headers = {}
         if self.password and not self.token:
             ws_headers = {

backend/open_webui/utils/middleware.py

@@ -353,8 +353,6 @@ async def chat_web_search_handler(
         )
         return form_data
 
-    all_results = []
-
     await event_emitter(
         {
             "type": "status",
@@ -366,106 +364,75 @@ async def chat_web_search_handler(
         }
     )
 
-    gathered_results = await asyncio.gather(
+    try:
-        *(
+        results = await process_web_search(
-            process_web_search(
+            request,
-                request,
+            SearchForm(queries=queries),
-                SearchForm(**{"query": searchQuery}),
+            user=user,
-                user=user,
+        )
-            )
-            for searchQuery in queries
-        ),
-        return_exceptions=True,
-    )
 
-    for searchQuery, results in zip(queries, gathered_results):
+        if results:
-        try:
+            files = form_data.get("files", [])
-            if isinstance(results, Exception):
-                raise Exception(f"Error searching {searchQuery}: {str(results)}")
 
-            if results:
+            if results.get("collection_names"):
-                all_results.append(results)
+                for col_idx, collection_name in enumerate(
-                files = form_data.get("files", [])
+                    results.get("collection_names")
+                ):
+                    files.append(
+                        {
+                            "collection_name": collection_name,
+                            "name": ", ".join(queries),
+                            "type": "web_search",
+                            "urls": results["filenames"],
+                        }
+                    )
+            elif results.get("docs"):
+                # Invoked when bypass embedding and retrieval is set to True
+                docs = results["docs"]
+                files.append(
+                    {
+                        "docs": docs,
+                        "name": ", ".join(queries),
+                        "type": "web_search",
+                        "urls": results["filenames"],
+                    }
+                )
 
-                if results.get("collection_names"):
+            form_data["files"] = files
-                    for col_idx, collection_name in enumerate(
-                        results.get("collection_names")
-                    ):
-                        files.append(
-                            {
-                                "collection_name": collection_name,
-                                "name": searchQuery,
-                                "type": "web_search",
-                                "urls": [results["filenames"][col_idx]],
-                            }
-                        )
-                elif results.get("docs"):
-                    # Invoked when bypass embedding and retrieval is set to True
-                    docs = results["docs"]
 
-                    if len(docs) == len(results["filenames"]):
-                        # the number of docs and filenames (urls) should be the same
-                        for doc_idx, doc in enumerate(docs):
-                            files.append(
-                                {
-                                    "docs": [doc],
-                                    "name": searchQuery,
-                                    "type": "web_search",
-                                    "urls": [results["filenames"][doc_idx]],
-                                }
-                            )
-                    else:
-                        # edge case when the number of docs and filenames (urls) are not the same
-                        # this should not happen, but if it does, we will just append the docs
-                        files.append(
-                            {
-                                "docs": results.get("docs", []),
-                                "name": searchQuery,
-                                "type": "web_search",
-                                "urls": results["filenames"],
-                            }
-                        )
-
-                form_data["files"] = files
-        except Exception as e:
-            log.exception(e)
             await event_emitter(
                 {
                     "type": "status",
                     "data": {
                         "action": "web_search",
-                        "description": 'Error searching "{{searchQuery}}"',
+                        "description": "Searched {{count}} sites",
-                        "query": searchQuery,
+                        "urls": results["filenames"],
+                        "done": True,
+                    },
+                }
+            )
+        else:
+            await event_emitter(
+                {
+                    "type": "status",
+                    "data": {
+                        "action": "web_search",
+                        "description": "No search results found",
                         "done": True,
                         "error": True,
                     },
                 }
             )
 
-    if all_results:
+    except Exception as e:
-        urls = []
+        log.exception(e)
-        for results in all_results:
-            if "filenames" in results:
-                urls.extend(results["filenames"])
-
         await event_emitter(
             {
                 "type": "status",
                 "data": {
                     "action": "web_search",
-                    "description": "Searched {{count}} sites",
+                    "description": "An error occurred while searching the web",
-                    "urls": urls,
+                    "queries": queries,
-                    "done": True,
-                },
-            }
-        )
-    else:
-        await event_emitter(
-            {
-                "type": "status",
-                "data": {
-                    "action": "web_search",
-                    "description": "No search results found",
                     "done": True,
                     "error": True,
                 },
@@ -672,6 +639,9 @@ def apply_params_to_form_data(form_data, model):
         if "frequency_penalty" in params and params["frequency_penalty"] is not None:
             form_data["frequency_penalty"] = params["frequency_penalty"]
 
+        if "presence_penalty" in params and params["presence_penalty"] is not None:
+            form_data["presence_penalty"] = params["presence_penalty"]
+
         if "reasoning_effort" in params and params["reasoning_effort"] is not None:
             form_data["reasoning_effort"] = params["reasoning_effort"]
 
@@ -974,6 +944,20 @@ async def process_chat_response(
         if message:
             messages = get_message_list(message_map, message.get("id"))
 
+            # Remove reasoning details and files from the messages.
+            # as get_message_list creates a new list, it does not affect
+            # the original messages outside of this handler
+            for message in messages:
+                message["content"] = re.sub(
+                    r"<details\s+type=\"reasoning\"[^>]*>.*?<\/details>",
+                    "",
+                    message["content"],
+                    flags=re.S,
+                ).strip()
+
+                if message.get("files"):
+                    message["files"] = []
+
             if tasks and messages:
                 if TASKS.TITLE_GENERATION in tasks:
                     if tasks[TASKS.TITLE_GENERATION]:

backend/open_webui/utils/oauth.py

@@ -34,6 +34,7 @@ from open_webui.config import (
     OAUTH_ALLOWED_ROLES,
     OAUTH_ADMIN_ROLES,
     OAUTH_ALLOWED_DOMAINS,
+    OAUTH_UPDATE_PICTURE_ON_LOGIN,
     WEBHOOK_URL,
     JWT_EXPIRES_IN,
     AppConfig,
@@ -72,6 +73,7 @@ auth_manager_config.OAUTH_ADMIN_ROLES = OAUTH_ADMIN_ROLES
 auth_manager_config.OAUTH_ALLOWED_DOMAINS = OAUTH_ALLOWED_DOMAINS
 auth_manager_config.WEBHOOK_URL = WEBHOOK_URL
 auth_manager_config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
+auth_manager_config.OAUTH_UPDATE_PICTURE_ON_LOGIN = OAUTH_UPDATE_PICTURE_ON_LOGIN
 
 
 class OAuthManager:
@@ -282,6 +284,49 @@ class OAuthManager:
                     id=group_model.id, form_data=update_form, overwrite=False
                 )
 
+    async def _process_picture_url(
+        self, picture_url: str, access_token: str = None
+    ) -> str:
+        """Process a picture URL and return a base64 encoded data URL.
+
+        Args:
+            picture_url: The URL of the picture to process
+            access_token: Optional OAuth access token for authenticated requests
+
+        Returns:
+            A data URL containing the base64 encoded picture, or "/user.png" if processing fails
+        """
+        if not picture_url:
+            return "/user.png"
+
+        try:
+            get_kwargs = {}
+            if access_token:
+                get_kwargs["headers"] = {
+                    "Authorization": f"Bearer {access_token}",
+                }
+            async with aiohttp.ClientSession() as session:
+                async with session.get(picture_url, **get_kwargs) as resp:
+                    if resp.ok:
+                        picture = await resp.read()
+                        base64_encoded_picture = base64.b64encode(picture).decode(
+                            "utf-8"
+                        )
+                        guessed_mime_type = mimetypes.guess_type(picture_url)[0]
+                        if guessed_mime_type is None:
+                            guessed_mime_type = "image/jpeg"
+                        return (
+                            f"data:{guessed_mime_type};base64,{base64_encoded_picture}"
+                        )
+                    else:
+                        log.warning(
+                            f"Failed to fetch profile picture from {picture_url}"
+                        )
+                        return "/user.png"
+        except Exception as e:
+            log.error(f"Error processing profile picture '{picture_url}': {e}")
+            return "/user.png"
+
     async def handle_login(self, request, provider):
         if provider not in OAUTH_PROVIDERS:
             raise HTTPException(404)
@@ -382,6 +427,22 @@ class OAuthManager:
             if user.role != determined_role:
                 Users.update_user_role_by_id(user.id, determined_role)
 
+            # Update profile picture if enabled and different from current
+            if auth_manager_config.OAUTH_UPDATE_PICTURE_ON_LOGIN:
+                picture_claim = auth_manager_config.OAUTH_PICTURE_CLAIM
+                if picture_claim:
+                    new_picture_url = user_data.get(
+                        picture_claim, OAUTH_PROVIDERS[provider].get("picture_url", "")
+                    )
+                    processed_picture_url = await self._process_picture_url(
+                        new_picture_url, token.get("access_token")
+                    )
+                    if processed_picture_url != user.profile_image_url:
+                        Users.update_user_profile_image_url_by_id(
+                            user.id, processed_picture_url
+                        )
+                        log.debug(f"Updated profile picture for user {user.email}")
+
         if not user:
             user_count = Users.get_num_users()
 
@@ -397,40 +458,9 @@ class OAuthManager:
                     picture_url = user_data.get(
                         picture_claim, OAUTH_PROVIDERS[provider].get("picture_url", "")
                     )
-                    if picture_url:
+                    picture_url = await self._process_picture_url(
-                        # Download the profile image into a base64 string
+                        picture_url, token.get("access_token")
-                        try:
+                    )
-                            access_token = token.get("access_token")
-                            get_kwargs = {}
-                            if access_token:
-                                get_kwargs["headers"] = {
-                                    "Authorization": f"Bearer {access_token}",
-                                }
-                            async with aiohttp.ClientSession(trust_env=True) as session:
-                                async with session.get(
-                                    picture_url, **get_kwargs
-                                ) as resp:
-                                    if resp.ok:
-                                        picture = await resp.read()
-                                        base64_encoded_picture = base64.b64encode(
-                                            picture
-                                        ).decode("utf-8")
-                                        guessed_mime_type = mimetypes.guess_type(
-                                            picture_url
-                                        )[0]
-                                        if guessed_mime_type is None:
-                                            # assume JPG, browsers are tolerant enough of image formats
-                                            guessed_mime_type = "image/jpeg"
-                                        picture_url = f"data:{guessed_mime_type};base64,{base64_encoded_picture}"
-                                    else:
-                                        picture_url = "/user.png"
-                        except Exception as e:
-                            log.error(
-                                f"Error downloading profile image '{picture_url}': {e}"
-                            )
-                            picture_url = "/user.png"
-                    if not picture_url:
-                        picture_url = "/user.png"
                 else:
                     picture_url = "/user.png"
 

backend/open_webui/utils/payload.py

@@ -59,6 +59,7 @@ def apply_model_params_to_body_openai(params: dict, form_data: dict) -> dict:
         "top_p": float,
         "max_tokens": int,
         "frequency_penalty": float,
+        "presence_penalty": float,
         "reasoning_effort": str,
         "seed": lambda x: x,
         "stop": lambda x: [bytes(s, "utf-8").decode("unicode_escape") for s in x],

backend/start.sh

@@ -65,4 +65,6 @@ if [ -n "$SPACE_ID" ]; then
   export WEBUI_URL=${SPACE_HOST}
 fi
 
-WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn open_webui.main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*' --workers "${UVICORN_WORKERS:-1}"
+PYTHON_CMD=$(command -v python3 || command -v python)
+
+WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec "$PYTHON_CMD" -m uvicorn open_webui.main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*' --workers "${UVICORN_WORKERS:-1}"

contribution_stats.py

@@ -0,0 +1,74 @@
+import os
+import subprocess
+from collections import Counter
+
+CONFIG_FILE_EXTENSIONS = (".json", ".yml", ".yaml", ".ini", ".conf", ".toml")
+
+
+def is_text_file(filepath):
+    # Check for binary file by scanning for null bytes.
+    try:
+        with open(filepath, "rb") as f:
+            chunk = f.read(4096)
+        if b"\0" in chunk:
+            return False
+        return True
+    except Exception:
+        return False
+
+
+def should_skip_file(path):
+    base = os.path.basename(path)
+    # Skip dotfiles and dotdirs
+    if base.startswith("."):
+        return True
+    # Skip config files by extension
+    if base.lower().endswith(CONFIG_FILE_EXTENSIONS):
+        return True
+    return False
+
+
+def get_tracked_files():
+    try:
+        output = subprocess.check_output(["git", "ls-files"], text=True)
+        files = output.strip().split("\n")
+        files = [f for f in files if f and os.path.isfile(f)]
+        return files
+    except subprocess.CalledProcessError:
+        print("Error: Are you in a git repository?")
+        return []
+
+
+def main():
+    files = get_tracked_files()
+    email_counter = Counter()
+    total_lines = 0
+
+    for file in files:
+        if should_skip_file(file):
+            continue
+        if not is_text_file(file):
+            continue
+        try:
+            blame = subprocess.check_output(
+                ["git", "blame", "-e", file], text=True, errors="replace"
+            )
+            for line in blame.splitlines():
+                # The email always inside <>
+                if "<" in line and ">" in line:
+                    try:
+                        email = line.split("<")[1].split(">")[0].strip()
+                    except Exception:
+                        continue
+                    email_counter[email] += 1
+                    total_lines += 1
+        except subprocess.CalledProcessError:
+            continue
+
+    for email, lines in email_counter.most_common():
+        percent = (lines / total_lines * 100) if total_lines else 0
+        print(f"{email}: {lines}/{total_lines} {percent:.2f}%")
+
+
+if __name__ == "__main__":
+    main()

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.6.7",
+	"version": "0.6.8",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.6.7",
+			"version": "0.6.8",
 			"dependencies": {
 				"@azure/msal-browser": "^4.5.0",
 				"@codemirror/lang-javascript": "^6.2.2",
@@ -36,6 +36,7 @@
 				"dompurify": "^3.2.5",
 				"eventsource-parser": "^1.1.2",
 				"file-saver": "^2.0.5",
+				"focus-trap": "^7.6.4",
 				"fuse.js": "^7.0.0",
 				"highlight.js": "^11.9.0",
 				"html-entities": "^2.5.3",
@@ -6801,9 +6802,10 @@
 			"dev": true
 		},
 		"node_modules/focus-trap": {
-			"version": "7.5.4",
+			"version": "7.6.4",
-			"resolved": "https://registry.npmjs.org/focus-trap/-/focus-trap-7.5.4.tgz",
+			"resolved": "https://registry.npmjs.org/focus-trap/-/focus-trap-7.6.4.tgz",
-			"integrity": "sha512-N7kHdlgsO/v+iD/dMoJKtsSqs5Dz/dXZVebRgJw23LDk+jMi/974zyiOYDziY2JPp8xivq9BmUGwIJMiuSBi7w==",
+			"integrity": "sha512-xx560wGBk7seZ6y933idtjJQc1l+ck+pI3sKvhKozdBV1dRZoKhkW5xoCaFv9tQiX5RH1xfSxjuNu6g+lmN/gw==",
+			"license": "MIT",
 			"dependencies": {
 				"tabbable": "^6.2.0"
 			}

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.6.7",
+	"version": "0.6.8",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -79,6 +79,7 @@
 		"dompurify": "^3.2.5",
 		"eventsource-parser": "^1.1.2",
 		"file-saver": "^2.0.5",
+		"focus-trap": "^7.6.4",
 		"fuse.js": "^7.0.0",
 		"highlight.js": "^11.9.0",
 		"html-entities": "^2.5.3",

src/app.css

@@ -24,6 +24,12 @@
 	font-display: swap;
 }
 
+@font-face {
+	font-family: 'Vazirmatn';
+	src: url('/assets/fonts/Vazirmatn-Variable.ttf');
+	font-display: swap;
+}
+
 html {
 	word-break: break-word;
 }

src/lib/components/ChangelogModal.svelte

@@ -43,6 +43,7 @@
 					fill="currentColor"
 					class="w-5 h-5"
 				>
+					<p class="sr-only">{$i18n.t('Close')}</p>
 					<path
 						d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
 					/>

src/lib/components/OnBoarding.svelte

@@ -87,6 +87,7 @@
 				<div class="flex justify-center mt-8">
 					<div class="flex flex-col justify-center items-center">
 						<button
+							aria-labelledby="get-started"
 							class="relative z-20 flex p-1 rounded-full bg-white/5 hover:bg-white/10 transition font-medium text-sm"
 							on:click={() => {
 								getStartedHandler();
@@ -94,12 +95,12 @@
 						>
 							<ArrowRightCircle className="size-6" />
 						</button>
-						<div class="mt-1.5 font-primary text-base font-medium">{$i18n.t(`Get started`)}</div>
+						<div id="get-started" class="mt-1.5 font-primary text-base font-medium">
+							{$i18n.t(`Get started`)}
+						</div>
 					</div>
 				</div>
 			</div>
-
-			<!-- <div class="absolute bottom-12 left-0 right-0 w-full"></div> -->
 		</div>
 	</div>
 {/if}

src/lib/components/admin/Settings/Documents.svelte

@@ -123,35 +123,6 @@
 		}
 	};
 
-	const rerankingModelUpdateHandler = async () => {
-		console.log('Update reranking model attempt:', rerankingModel);
-
-		updateRerankingModelLoading = true;
-		const res = await updateRerankingConfig(localStorage.token, {
-			reranking_model: rerankingModel
-		}).catch(async (error) => {
-			toast.error(`${error}`);
-			await setRerankingConfig();
-			return null;
-		});
-		updateRerankingModelLoading = false;
-
-		if (res) {
-			console.log('rerankingModelUpdateHandler:', res);
-			if (res.status === true) {
-				if (rerankingModel === '') {
-					toast.success($i18n.t('Reranking model disabled', res), {
-						duration: 1000 * 10
-					});
-				} else {
-					toast.success($i18n.t('Reranking model set to "{{reranking_model}}"', res), {
-						duration: 1000 * 10
-					});
-				}
-			}
-		}
-	};
-
 	const submitHandler = async () => {
 		if (RAGConfig.CONTENT_EXTRACTION_ENGINE === 'tika' && RAGConfig.TIKA_SERVER_URL === '') {
 			toast.error($i18n.t('Tika Server URL required.'));
@@ -190,10 +161,6 @@
 
 		if (!RAGConfig.BYPASS_EMBEDDING_AND_RETRIEVAL) {
 			await embeddingModelUpdateHandler();
-
-			if (RAGConfig.ENABLE_RAG_HYBRID_SEARCH) {
-				await rerankingModelUpdateHandler();
-			}
 		}
 
 		const res = await updateRAGConfig(localStorage.token, RAGConfig);
@@ -215,18 +182,8 @@
 			OllamaUrl = embeddingConfig.ollama_config.url;
 		}
 	};
-
-	const setRerankingConfig = async () => {
-		const rerankingConfig = await getRerankingConfig(localStorage.token);
-
-		if (rerankingConfig) {
-			rerankingModel = rerankingConfig.reranking_model;
-		}
-	};
-
 	onMount(async () => {
 		await setEmbeddingConfig();
-		await setRerankingConfig();
 
 		RAGConfig = await getRAGConfig(localStorage.token);
 	});
@@ -655,6 +612,48 @@
 							</div>
 
 							{#if RAGConfig.ENABLE_RAG_HYBRID_SEARCH === true}
+								<div class="  mb-2.5 flex flex-col w-full justify-between">
+									<div class="flex w-full justify-between">
+										<div class=" self-center text-xs font-medium">
+											{$i18n.t('Reranking Engine')}
+										</div>
+										<div class="flex items-center relative">
+											<select
+												class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-right"
+												bind:value={RAGConfig.RAG_RERANKING_ENGINE}
+												placeholder="Select a reranking model engine"
+												on:change={(e) => {
+													if (e.target.value === 'external') {
+														RAGConfig.RAG_RERANKING_MODEL = '';
+													} else if (e.target.value === '') {
+														RAGConfig.RAG_RERANKING_MODEL = 'BAAI/bge-reranker-v2-m3';
+													}
+												}}
+											>
+												<option value="">{$i18n.t('Default (SentenceTransformers)')}</option>
+												<option value="external">{$i18n.t('External')}</option>
+											</select>
+										</div>
+									</div>
+
+									{#if RAGConfig.RAG_RERANKING_ENGINE === 'external'}
+										<div class="my-0.5 flex gap-2 pr-2">
+											<input
+												class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
+												placeholder={$i18n.t('API Base URL')}
+												bind:value={RAGConfig.RAG_EXTERNAL_RERANKER_URL}
+												required
+											/>
+
+											<SensitiveInput
+												placeholder={$i18n.t('API Key')}
+												bind:value={RAGConfig.RAG_EXTERNAL_RERANKER_API_KEY}
+												required={false}
+											/>
+										</div>
+									{/if}
+								</div>
+
 								<div class="  mb-2.5 flex flex-col w-full">
 									<div class=" mb-1 text-xs font-medium">{$i18n.t('Reranking Model')}</div>
 
@@ -666,62 +665,9 @@
 													placeholder={$i18n.t('Set reranking model (e.g. {{model}})', {
 														model: 'BAAI/bge-reranker-v2-m3'
 													})}
-													bind:value={rerankingModel}
+													bind:value={RAGConfig.RAG_RERANKING_MODEL}
 												/>
 											</div>
-											<button
-												class="px-2.5 bg-transparent text-gray-800 dark:bg-transparent dark:text-gray-100 rounded-lg transition"
-												on:click={() => {
-													rerankingModelUpdateHandler();
-												}}
-												disabled={updateRerankingModelLoading}
-											>
-												{#if updateRerankingModelLoading}
-													<div class="self-center">
-														<svg
-															class=" w-4 h-4"
-															viewBox="0 0 24 24"
-															fill="currentColor"
-															xmlns="http://www.w3.org/2000/svg"
-														>
-															<style>
-																.spinner_ajPY {
-																	transform-origin: center;
-																	animation: spinner_AtaB 0.75s infinite linear;
-																}
-
-																@keyframes spinner_AtaB {
-																	100% {
-																		transform: rotate(360deg);
-																	}
-																}
-															</style>
-															<path
-																d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
-																opacity=".25"
-															/>
-															<path
-																d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
-																class="spinner_ajPY"
-															/>
-														</svg>
-													</div>
-												{:else}
-													<svg
-														xmlns="http://www.w3.org/2000/svg"
-														viewBox="0 0 16 16"
-														fill="currentColor"
-														class="w-4 h-4"
-													>
-														<path
-															d="M8.75 2.75a.75.75 0 0 0-1.5 0v5.69L5.03 6.22a.75.75 0 0 0-1.06 1.06l3.5 3.5a.75.75 0 0 0 1.06 0l3.5-3.5a.75.75 0 0 0-1.06-1.06L8.75 8.44V2.75Z"
-														/>
-														<path
-															d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
-														/>
-													</svg>
-												{/if}
-											</button>
 										</div>
 									</div>
 								</div>

src/lib/components/admin/Users/UserList.svelte

@@ -32,13 +32,14 @@
 	import About from '$lib/components/chat/Settings/About.svelte';
 	import Banner from '$lib/components/common/Banner.svelte';
 	import Markdown from '$lib/components/chat/Messages/Markdown.svelte';
+	import Spinner from '$lib/components/common/Spinner.svelte';
 
 	const i18n = getContext('i18n');
 
 	let page = 1;
 
-	let users = [];
+	let users = null;
-	let total = 0;
+	let total = null;
 
 	let query = '';
 	let orderBy = 'created_at'; // default sort key
@@ -181,314 +182,293 @@
 	</div>
 {/if}
 
-<div class="mt-0.5 mb-2 gap-1 flex flex-col md:flex-row justify-between">
+{#if users === null || total === null}
-	<div class="flex md:self-center text-lg font-medium px-0.5">
+	<div class="my-10">
-		<div class="flex-shrink-0">
+		<Spinner />
-			{$i18n.t('Users')}
+	</div>
-		</div>
+{:else}
-		<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-50 dark:bg-gray-850" />
+	<div class="mt-0.5 mb-2 gap-1 flex flex-col md:flex-row justify-between">
+		<div class="flex md:self-center text-lg font-medium px-0.5">
+			<div class="flex-shrink-0">
+				{$i18n.t('Users')}
+			</div>
+			<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-50 dark:bg-gray-850" />
 
-		{#if ($config?.license_metadata?.seats ?? null) !== null}
+			{#if ($config?.license_metadata?.seats ?? null) !== null}
-			{#if total > $config?.license_metadata?.seats}
+				{#if total > $config?.license_metadata?.seats}
-				<span class="text-lg font-medium text-red-500"
+					<span class="text-lg font-medium text-red-500"
-					>{total} of {$config?.license_metadata?.seats}
+						>{total} of {$config?.license_metadata?.seats}
-					<span class="text-sm font-normal">available users</span></span
+						<span class="text-sm font-normal">available users</span></span
-				>
+					>
+				{:else}
+					<span class="text-lg font-medium text-gray-500 dark:text-gray-300"
+						>{total} of {$config?.license_metadata?.seats}
+						<span class="text-sm font-normal">available users</span></span
+					>
+				{/if}
 			{:else}
-				<span class="text-lg font-medium text-gray-500 dark:text-gray-300"
+				<span class="text-lg font-medium text-gray-500 dark:text-gray-300">{total}</span>
-					>{total} of {$config?.license_metadata?.seats}
-					<span class="text-sm font-normal">available users</span></span
-				>
 			{/if}
-		{:else}
-			<span class="text-lg font-medium text-gray-500 dark:text-gray-300">{total}</span>
-		{/if}
-	</div>
-
-	<div class="flex gap-1">
-		<div class=" flex w-full space-x-2">
-			<div class="flex flex-1">
-				<div class=" self-center ml-1 mr-3">
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 20 20"
-						fill="currentColor"
-						class="w-4 h-4"
-					>
-						<path
-							fill-rule="evenodd"
-							d="M9 3.5a5.5 5.5 0 100 11 5.5 5.5 0 000-11zM2 9a7 7 0 1112.452 4.391l3.328 3.329a.75.75 0 11-1.06 1.06l-3.329-3.328A7 7 0 012 9z"
-							clip-rule="evenodd"
-						/>
-					</svg>
-				</div>
-				<input
-					class=" w-full text-sm pr-4 py-1 rounded-r-xl outline-hidden bg-transparent"
-					bind:value={query}
-					placeholder={$i18n.t('Search')}
-				/>
-			</div>
-
-			<div>
-				<Tooltip content={$i18n.t('Add User')}>
-					<button
-						class=" p-2 rounded-xl hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 transition font-medium text-sm flex items-center space-x-1"
-						on:click={() => {
-							showAddUserModal = !showAddUserModal;
-						}}
-					>
-						<Plus className="size-3.5" />
-					</button>
-				</Tooltip>
-			</div>
 		</div>
-	</div>
-</div>
 
-<div
+		<div class="flex gap-1">
-	class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full rounded-sm pt-0.5"
+			<div class=" flex w-full space-x-2">
->
+				<div class="flex flex-1">
-	<table
+					<div class=" self-center ml-1 mr-3">
-		class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto max-w-full rounded-sm"
+						<svg
-	>
+							xmlns="http://www.w3.org/2000/svg"
-		<thead
+							viewBox="0 0 20 20"
-			class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-850 dark:text-gray-400 -translate-y-0.5"
+							fill="currentColor"
-		>
+							class="w-4 h-4"
-			<tr class="">
+						>
-				<th
+							<path
-					scope="col"
+								fill-rule="evenodd"
-					class="px-3 py-1.5 cursor-pointer select-none"
+								d="M9 3.5a5.5 5.5 0 100 11 5.5 5.5 0 000-11zM2 9a7 7 0 1112.452 4.391l3.328 3.329a.75.75 0 11-1.06 1.06l-3.329-3.328A7 7 0 012 9z"
-					on:click={() => setSortKey('role')}
+								clip-rule="evenodd"
-				>
+							/>
-					<div class="flex gap-1.5 items-center">
+						</svg>
-						{$i18n.t('Role')}
-
-						{#if orderBy === 'role'}
-							<span class="font-normal"
-								>{#if direction === 'asc'}
-									<ChevronUp className="size-2" />
-								{:else}
-									<ChevronDown className="size-2" />
-								{/if}
-							</span>
-						{:else}
-							<span class="invisible">
-								<ChevronUp className="size-2" />
-							</span>
-						{/if}
 					</div>
-				</th>
+					<input
-				<th
+						class=" w-full text-sm pr-4 py-1 rounded-r-xl outline-hidden bg-transparent"
-					scope="col"
+						bind:value={query}
-					class="px-3 py-1.5 cursor-pointer select-none"
+						placeholder={$i18n.t('Search')}
-					on:click={() => setSortKey('name')}
+					/>
-				>
+				</div>
-					<div class="flex gap-1.5 items-center">
-						{$i18n.t('Name')}
 
-						{#if orderBy === 'name'}
+				<div>
-							<span class="font-normal"
+					<Tooltip content={$i18n.t('Add User')}>
-								>{#if direction === 'asc'}
-									<ChevronUp className="size-2" />
-								{:else}
-									<ChevronDown className="size-2" />
-								{/if}
-							</span>
-						{:else}
-							<span class="invisible">
-								<ChevronUp className="size-2" />
-							</span>
-						{/if}
-					</div>
-				</th>
-				<th
-					scope="col"
-					class="px-3 py-1.5 cursor-pointer select-none"
-					on:click={() => setSortKey('email')}
-				>
-					<div class="flex gap-1.5 items-center">
-						{$i18n.t('Email')}
-
-						{#if orderBy === 'email'}
-							<span class="font-normal"
-								>{#if direction === 'asc'}
-									<ChevronUp className="size-2" />
-								{:else}
-									<ChevronDown className="size-2" />
-								{/if}
-							</span>
-						{:else}
-							<span class="invisible">
-								<ChevronUp className="size-2" />
-							</span>
-						{/if}
-					</div>
-				</th>
-
-				<th
-					scope="col"
-					class="px-3 py-1.5 cursor-pointer select-none"
-					on:click={() => setSortKey('last_active_at')}
-				>
-					<div class="flex gap-1.5 items-center">
-						{$i18n.t('Last Active')}
-
-						{#if orderBy === 'last_active_at'}
-							<span class="font-normal"
-								>{#if direction === 'asc'}
-									<ChevronUp className="size-2" />
-								{:else}
-									<ChevronDown className="size-2" />
-								{/if}
-							</span>
-						{:else}
-							<span class="invisible">
-								<ChevronUp className="size-2" />
-							</span>
-						{/if}
-					</div>
-				</th>
-				<th
-					scope="col"
-					class="px-3 py-1.5 cursor-pointer select-none"
-					on:click={() => setSortKey('created_at')}
-				>
-					<div class="flex gap-1.5 items-center">
-						{$i18n.t('Created at')}
-						{#if orderBy === 'created_at'}
-							<span class="font-normal"
-								>{#if direction === 'asc'}
-									<ChevronUp className="size-2" />
-								{:else}
-									<ChevronDown className="size-2" />
-								{/if}
-							</span>
-						{:else}
-							<span class="invisible">
-								<ChevronUp className="size-2" />
-							</span>
-						{/if}
-					</div>
-				</th>
-
-				<th
-					scope="col"
-					class="px-3 py-1.5 cursor-pointer select-none"
-					on:click={() => setSortKey('oauth_sub')}
-				>
-					<div class="flex gap-1.5 items-center">
-						{$i18n.t('OAuth ID')}
-
-						{#if orderBy === 'oauth_sub'}
-							<span class="font-normal"
-								>{#if direction === 'asc'}
-									<ChevronUp className="size-2" />
-								{:else}
-									<ChevronDown className="size-2" />
-								{/if}
-							</span>
-						{:else}
-							<span class="invisible">
-								<ChevronUp className="size-2" />
-							</span>
-						{/if}
-					</div>
-				</th>
-
-				<th scope="col" class="px-3 py-2 text-right" />
-			</tr>
-		</thead>
-		<tbody class="">
-			{#each users as user, userIdx}
-				<tr class="bg-white dark:bg-gray-900 dark:border-gray-850 text-xs">
-					<td class="px-3 py-1 min-w-[7rem] w-28">
 						<button
-							class=" translate-y-0.5"
+							class=" p-2 rounded-xl hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 transition font-medium text-sm flex items-center space-x-1"
 							on:click={() => {
-								selectedUser = user;
+								showAddUserModal = !showAddUserModal;
-								showUpdateRoleModal = true;
 							}}
 						>
-							<Badge
+							<Plus className="size-3.5" />
-								type={user.role === 'admin' ? 'info' : user.role === 'user' ? 'success' : 'muted'}
-								content={$i18n.t(user.role)}
-							/>
 						</button>
-					</td>
+					</Tooltip>
-					<td class="px-3 py-1 font-medium text-gray-900 dark:text-white w-max">
+				</div>
-						<div class="flex flex-row w-max">
+			</div>
-							<img
+		</div>
-								class=" rounded-full w-6 h-6 object-cover mr-2.5"
+	</div>
-								src={user.profile_image_url.startsWith(WEBUI_BASE_URL) ||
-								user.profile_image_url.startsWith('https://www.gravatar.com/avatar/') ||
-								user.profile_image_url.startsWith('data:')
-									? user.profile_image_url
-									: `/user.png`}
-								alt="user"
-							/>
 
-							<div class=" font-medium self-center">{user.name}</div>
+	<div
-						</div>
+		class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full rounded-sm pt-0.5"
-					</td>
+	>
-					<td class=" px-3 py-1"> {user.email} </td>
+		<table
+			class="w-full text-sm text-left text-gray-500 dark:text-gray-400 table-auto max-w-full rounded-sm"
+		>
+			<thead
+				class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-850 dark:text-gray-400 -translate-y-0.5"
+			>
+				<tr class="">
+					<th
+						scope="col"
+						class="px-3 py-1.5 cursor-pointer select-none"
+						on:click={() => setSortKey('role')}
+					>
+						<div class="flex gap-1.5 items-center">
+							{$i18n.t('Role')}
 
-					<td class=" px-3 py-1">
+							{#if orderBy === 'role'}
-						{dayjs(user.last_active_at * 1000).fromNow()}
+								<span class="font-normal"
-					</td>
+									>{#if direction === 'asc'}
-
+										<ChevronUp className="size-2" />
-					<td class=" px-3 py-1">
+									{:else}
-						{dayjs(user.created_at * 1000).format('LL')}
+										<ChevronDown className="size-2" />
-					</td>
+									{/if}
-
+								</span>
-					<td class=" px-3 py-1"> {user.oauth_sub ?? ''} </td>
+							{:else}
-
+								<span class="invisible">
-					<td class="px-3 py-1 text-right">
+									<ChevronUp className="size-2" />
-						<div class="flex justify-end w-full">
+								</span>
-							{#if $config.features.enable_admin_chat_access && user.role !== 'admin'}
-								<Tooltip content={$i18n.t('Chats')}>
-									<button
-										class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
-										on:click={async () => {
-											showUserChatsModal = !showUserChatsModal;
-											selectedUser = user;
-										}}
-									>
-										<ChatBubbles />
-									</button>
-								</Tooltip>
 							{/if}
+						</div>
+					</th>
+					<th
+						scope="col"
+						class="px-3 py-1.5 cursor-pointer select-none"
+						on:click={() => setSortKey('name')}
+					>
+						<div class="flex gap-1.5 items-center">
+							{$i18n.t('Name')}
 
-							<Tooltip content={$i18n.t('Edit User')}>
+							{#if orderBy === 'name'}
-								<button
+								<span class="font-normal"
-									class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+									>{#if direction === 'asc'}
-									on:click={async () => {
+										<ChevronUp className="size-2" />
-										showEditUserModal = !showEditUserModal;
+									{:else}
-										selectedUser = user;
+										<ChevronDown className="size-2" />
-									}}
+									{/if}
-								>
+								</span>
-									<svg
+							{:else}
-										xmlns="http://www.w3.org/2000/svg"
+								<span class="invisible">
-										fill="none"
+									<ChevronUp className="size-2" />
-										viewBox="0 0 24 24"
+								</span>
-										stroke-width="1.5"
+							{/if}
-										stroke="currentColor"
+						</div>
-										class="w-4 h-4"
+					</th>
-									>
+					<th
-										<path
+						scope="col"
-											stroke-linecap="round"
+						class="px-3 py-1.5 cursor-pointer select-none"
-											stroke-linejoin="round"
+						on:click={() => setSortKey('email')}
-											d="m16.862 4.487 1.687-1.688a1.875 1.875 0 1 1 2.652 2.652L6.832 19.82a4.5 4.5 0 0 1-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 0 1 1.13-1.897L16.863 4.487Zm0 0L19.5 7.125"
+					>
-										/>
+						<div class="flex gap-1.5 items-center">
-									</svg>
+							{$i18n.t('Email')}
-								</button>
-							</Tooltip>
 
-							{#if user.role !== 'admin'}
+							{#if orderBy === 'email'}
-								<Tooltip content={$i18n.t('Delete User')}>
+								<span class="font-normal"
+									>{#if direction === 'asc'}
+										<ChevronUp className="size-2" />
+									{:else}
+										<ChevronDown className="size-2" />
+									{/if}
+								</span>
+							{:else}
+								<span class="invisible">
+									<ChevronUp className="size-2" />
+								</span>
+							{/if}
+						</div>
+					</th>
+
+					<th
+						scope="col"
+						class="px-3 py-1.5 cursor-pointer select-none"
+						on:click={() => setSortKey('last_active_at')}
+					>
+						<div class="flex gap-1.5 items-center">
+							{$i18n.t('Last Active')}
+
+							{#if orderBy === 'last_active_at'}
+								<span class="font-normal"
+									>{#if direction === 'asc'}
+										<ChevronUp className="size-2" />
+									{:else}
+										<ChevronDown className="size-2" />
+									{/if}
+								</span>
+							{:else}
+								<span class="invisible">
+									<ChevronUp className="size-2" />
+								</span>
+							{/if}
+						</div>
+					</th>
+					<th
+						scope="col"
+						class="px-3 py-1.5 cursor-pointer select-none"
+						on:click={() => setSortKey('created_at')}
+					>
+						<div class="flex gap-1.5 items-center">
+							{$i18n.t('Created at')}
+							{#if orderBy === 'created_at'}
+								<span class="font-normal"
+									>{#if direction === 'asc'}
+										<ChevronUp className="size-2" />
+									{:else}
+										<ChevronDown className="size-2" />
+									{/if}
+								</span>
+							{:else}
+								<span class="invisible">
+									<ChevronUp className="size-2" />
+								</span>
+							{/if}
+						</div>
+					</th>
+
+					<th
+						scope="col"
+						class="px-3 py-1.5 cursor-pointer select-none"
+						on:click={() => setSortKey('oauth_sub')}
+					>
+						<div class="flex gap-1.5 items-center">
+							{$i18n.t('OAuth ID')}
+
+							{#if orderBy === 'oauth_sub'}
+								<span class="font-normal"
+									>{#if direction === 'asc'}
+										<ChevronUp className="size-2" />
+									{:else}
+										<ChevronDown className="size-2" />
+									{/if}
+								</span>
+							{:else}
+								<span class="invisible">
+									<ChevronUp className="size-2" />
+								</span>
+							{/if}
+						</div>
+					</th>
+
+					<th scope="col" class="px-3 py-2 text-right" />
+				</tr>
+			</thead>
+			<tbody class="">
+				{#each users as user, userIdx}
+					<tr class="bg-white dark:bg-gray-900 dark:border-gray-850 text-xs">
+						<td class="px-3 py-1 min-w-[7rem] w-28">
+							<button
+								class=" translate-y-0.5"
+								on:click={() => {
+									selectedUser = user;
+									showUpdateRoleModal = true;
+								}}
+							>
+								<Badge
+									type={user.role === 'admin' ? 'info' : user.role === 'user' ? 'success' : 'muted'}
+									content={$i18n.t(user.role)}
+								/>
+							</button>
+						</td>
+						<td class="px-3 py-1 font-medium text-gray-900 dark:text-white w-max">
+							<div class="flex flex-row w-max">
+								<img
+									class=" rounded-full w-6 h-6 object-cover mr-2.5"
+									src={user.profile_image_url.startsWith(WEBUI_BASE_URL) ||
+									user.profile_image_url.startsWith('https://www.gravatar.com/avatar/') ||
+									user.profile_image_url.startsWith('data:')
+										? user.profile_image_url
+										: `/user.png`}
+									alt="user"
+								/>
+
+								<div class=" font-medium self-center">{user.name}</div>
+							</div>
+						</td>
+						<td class=" px-3 py-1"> {user.email} </td>
+
+						<td class=" px-3 py-1">
+							{dayjs(user.last_active_at * 1000).fromNow()}
+						</td>
+
+						<td class=" px-3 py-1">
+							{dayjs(user.created_at * 1000).format('LL')}
+						</td>
+
+						<td class=" px-3 py-1"> {user.oauth_sub ?? ''} </td>
+
+						<td class="px-3 py-1 text-right">
+							<div class="flex justify-end w-full">
+								{#if $config.features.enable_admin_chat_access && user.role !== 'admin'}
+									<Tooltip content={$i18n.t('Chats')}>
+										<button
+											class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+											on:click={async () => {
+												showUserChatsModal = !showUserChatsModal;
+												selectedUser = user;
+											}}
+										>
+											<ChatBubbles />
+										</button>
+									</Tooltip>
+								{/if}
+
+								<Tooltip content={$i18n.t('Edit User')}>
 									<button
 										class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
 										on:click={async () => {
-											showDeleteConfirmDialog = true;
+											showEditUserModal = !showEditUserModal;
 											selectedUser = user;
 										}}
 									>
@@ -503,25 +483,52 @@
 											<path
 												stroke-linecap="round"
 												stroke-linejoin="round"
-												d="m14.74 9-.346 9m-4.788 0L9.26 9m9.968-3.21c.342.052.682.107 1.022.166m-1.022-.165L18.16 19.673a2.25 2.25 0 0 1-2.244 2.077H8.084a2.25 2.25 0 0 1-2.244-2.077L4.772 5.79m14.456 0a48.108 48.108 0 0 0-3.478-.397m-12 .562c.34-.059.68-.114 1.022-.165m0 0a48.11 48.11 0 0 1 3.478-.397m7.5 0v-.916c0-1.18-.91-2.164-2.09-2.201a51.964 51.964 0 0 0-3.32 0c-1.18.037-2.09 1.022-2.09 2.201v.916m7.5 0a48.667 48.667 0 0 0-7.5 0"
+												d="m16.862 4.487 1.687-1.688a1.875 1.875 0 1 1 2.652 2.652L6.832 19.82a4.5 4.5 0 0 1-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 0 1 1.13-1.897L16.863 4.487Zm0 0L19.5 7.125"
 											/>
 										</svg>
 									</button>
 								</Tooltip>
-							{/if}
-						</div>
-					</td>
-				</tr>
-			{/each}
-		</tbody>
-	</table>
-</div>
 
-<div class=" text-gray-500 text-xs mt-1.5 text-right">
+								{#if user.role !== 'admin'}
-	ⓘ {$i18n.t("Click on the user role button to change a user's role.")}
+									<Tooltip content={$i18n.t('Delete User')}>
-</div>
+										<button
+											class="self-center w-fit text-sm px-2 py-2 hover:bg-black/5 dark:hover:bg-white/5 rounded-xl"
+											on:click={async () => {
+												showDeleteConfirmDialog = true;
+												selectedUser = user;
+											}}
+										>
+											<svg
+												xmlns="http://www.w3.org/2000/svg"
+												fill="none"
+												viewBox="0 0 24 24"
+												stroke-width="1.5"
+												stroke="currentColor"
+												class="w-4 h-4"
+											>
+												<path
+													stroke-linecap="round"
+													stroke-linejoin="round"
+													d="m14.74 9-.346 9m-4.788 0L9.26 9m9.968-3.21c.342.052.682.107 1.022.166m-1.022-.165L18.16 19.673a2.25 2.25 0 0 1-2.244 2.077H8.084a2.25 2.25 0 0 1-2.244-2.077L4.772 5.79m14.456 0a48.108 48.108 0 0 0-3.478-.397m-12 .562c.34-.059.68-.114 1.022-.165m0 0a48.11 48.11 0 0 1 3.478-.397m7.5 0v-.916c0-1.18-.91-2.164-2.09-2.201a51.964 51.964 0 0 0-3.32 0c-1.18.037-2.09 1.022-2.09 2.201v.916m7.5 0a48.667 48.667 0 0 0-7.5 0"
+												/>
+											</svg>
+										</button>
+									</Tooltip>
+								{/if}
+							</div>
+						</td>
+					</tr>
+				{/each}
+			</tbody>
+		</table>
+	</div>
 
-<Pagination bind:page count={total} perPage={10} />
+	<div class=" text-gray-500 text-xs mt-1.5 text-right">
+		ⓘ {$i18n.t("Click on the user role button to change a user's role.")}
+	</div>
+
+	<Pagination bind:page count={total} perPage={30} />
+{/if}
 
 {#if !$config?.license_metadata}
 	{#if total > 50}

src/lib/components/chat/Chat.svelte

@@ -440,8 +440,10 @@
 			}
 		}
 
-		loading = false;
+		if (!chatIdProp) {
-		await tick();
+			loading = false;
+			await tick();
+		}
 
 		showControls.subscribe(async (value) => {
 			if (controlPane && !$mobile) {

src/lib/components/chat/MessageInput.svelte

@@ -86,7 +86,7 @@
 
 	$: onChange({
 		prompt,
-		files,
+		files: files.filter((file) => file.type !== 'image'),
 		selectedToolIds,
 		imageGenerationEnabled,
 		webSearchEnabled,
@@ -604,7 +604,7 @@
 								<div class="px-2.5">
 									{#if $settings?.richTextInput ?? true}
 										<div
-											class="scrollbar-hidden text-left bg-transparent dark:text-gray-100 outline-hidden w-full pt-3 px-1 resize-none h-fit max-h-80 overflow-auto"
+											class="scrollbar-hidden rtl:text-right ltr:text-left bg-transparent dark:text-gray-100 outline-hidden w-full pt-3 px-1 resize-none h-fit max-h-80 overflow-auto"
 											id="chat-input-container"
 										>
 											<RichTextInput

src/lib/components/chat/MessageInput/InputMenu.svelte

@@ -33,6 +33,7 @@
 
 	let tools = {};
 	let show = false;
+	let showAllTools = false;
 
 	$: if (show) {
 		init();
@@ -102,7 +103,7 @@
 			transition={flyAndScale}
 		>
 			{#if Object.keys(tools).length > 0}
-				<div class="  max-h-28 overflow-y-auto scrollbar-hidden">
+				<div class="{showAllTools ? '' : 'max-h-28'} overflow-y-auto scrollbar-thin">
 					{#each Object.keys(tools) as toolId}
 						<button
 							class="flex w-full justify-between gap-2 items-center px-3 py-2 text-sm font-medium cursor-pointer rounded-xl"
@@ -141,7 +142,29 @@
 						</button>
 					{/each}
 				</div>
-
+				{#if Object.keys(tools).length > 3}
+					<button
+						class="flex w-full justify-center items-center text-sm font-medium cursor-pointer rounded-lg hover:bg-gray-50 dark:hover:bg-gray-800"
+						on:click={() => {
+							showAllTools = !showAllTools;
+						}}
+						title={showAllTools ? $i18n.t('Show Less') : $i18n.t('Show All')}
+					>
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							fill="none"
+							viewBox="0 0 24 24"
+							stroke-width="2.5"
+							stroke="currentColor"
+							class="size-3 transition-transform duration-200 {showAllTools
+								? 'rotate-180'
+								: ''} text-gray-300 dark:text-gray-600"
+						>
+							<path stroke-linecap="round" stroke-linejoin="round" d="m19.5 8.25-7.5 7.5-7.5-7.5"
+							></path>
+						</svg>
+					</button>
+				{/if}
 				<hr class="border-black/5 dark:border-white/5 my-1" />
 			{/if}
 

src/lib/components/chat/Messages/Markdown/HTMLToken.svelte

@@ -32,6 +32,7 @@
 				title="Video player"
 				frameborder="0"
 				referrerpolicy="strict-origin-when-cross-origin"
+				controls
 				allowfullscreen
 			></video>
 		{:else}

src/lib/components/chat/Settings/Interface.svelte

@@ -54,6 +54,9 @@
 		height: ''
 	};
 
+	// chat export
+	let stylizedPdfExport = true;
+
 	// Admin - Show Update Available Toast
 	let showUpdateToast = true;
 	let showChangelog = true;
@@ -152,6 +155,11 @@
 		saveSettings({ hapticFeedback: hapticFeedback });
 	};
 
+	const toggleStylizedPdfExport = async () => {
+		stylizedPdfExport = !stylizedPdfExport;
+		saveSettings({ stylizedPdfExport: stylizedPdfExport });
+	};
+
 	const toggleUserLocation = async () => {
 		userLocation = !userLocation;
 
@@ -302,6 +310,11 @@
 		notificationSound = $settings?.notificationSound ?? true;
 		notificationSoundAlways = $settings?.notificationSoundAlways ?? false;
 
+		iframeSandboxAllowSameOrigin = $settings?.iframeSandboxAllowSameOrigin ?? false;
+		iframeSandboxAllowForms = $settings?.iframeSandboxAllowForms ?? false;
+
+		stylizedPdfExport = $settings?.stylizedPdfExport ?? true;
+
 		hapticFeedback = $settings.hapticFeedback ?? false;
 		ctrlEnterToSend = $settings.ctrlEnterToSend ?? false;
 
@@ -964,6 +977,28 @@
 				</div>
 			</div>
 
+			<div>
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs">
+						{$i18n.t('Stylized PDF Export')}
+					</div>
+
+					<button
+						class="p-1 px-3 text-xs flex rounded-sm transition"
+						on:click={() => {
+							toggleStylizedPdfExport();
+						}}
+						type="button"
+					>
+						{#if stylizedPdfExport === true}
+							<span class="ml-2 self-center">{$i18n.t('On')}</span>
+						{:else}
+							<span class="ml-2 self-center">{$i18n.t('Off')}</span>
+						{/if}
+					</button>
+				</div>
+			</div>
+
 			<div class=" my-1.5 text-sm font-medium">{$i18n.t('Voice')}</div>
 
 			<div>

src/lib/components/common/Modal.svelte

@@ -3,7 +3,7 @@
 	import { fade } from 'svelte/transition';
 
 	import { flyAndScale } from '$lib/utils/transitions';
-
+	import * as FocusTrap from 'focus-trap';
 	export let show = true;
 	export let size = 'md';
 	export let containerClassName = 'p-3';
@@ -11,6 +11,10 @@
 
 	let modalElement = null;
 	let mounted = false;
+	// Create focus trap to trap user tabs inside modal
+	// https://www.w3.org/WAI/WCAG21/Understanding/focus-order.html
+	// https://www.w3.org/WAI/WCAG21/Understanding/keyboard.html
+	let focusTrap: FocusTrap.FocusTrap | null = null;
 
 	const sizeToWidth = (size) => {
 		if (size === 'full') {
@@ -45,9 +49,12 @@
 
 	$: if (show && modalElement) {
 		document.body.appendChild(modalElement);
+		focusTrap = FocusTrap.createFocusTrap(modalElement);
+		focusTrap.activate();
 		window.addEventListener('keydown', handleKeyDown);
 		document.body.style.overflow = 'hidden';
 	} else if (modalElement) {
+		focusTrap.deactivate();
 		window.removeEventListener('keydown', handleKeyDown);
 		document.body.removeChild(modalElement);
 		document.body.style.overflow = 'unset';
@@ -55,6 +62,9 @@
 
 	onDestroy(() => {
 		show = false;
+		if (focusTrap) {
+			focusTrap.deactivate();
+		}
 		if (modalElement) {
 			document.body.removeChild(modalElement);
 		}
@@ -66,6 +76,8 @@
 	<!-- svelte-ignore a11y-no-static-element-interactions -->
 	<div
 		bind:this={modalElement}
+		aria-modal="true"
+		role="dialog"
 		class="modal fixed top-0 right-0 left-0 bottom-0 bg-black/60 w-full h-screen max-h-[100dvh] {containerClassName} flex justify-center z-9999 overflow-y-auto overscroll-contain"
 		in:fade={{ duration: 10 }}
 		on:mousedown={() => {

src/lib/components/layout/Navbar/Menu.svelte

@@ -19,7 +19,8 @@
 		mobile,
 		temporaryChatEnabled,
 		theme,
-		user
+		user,
+		settings
 	} from '$lib/stores';
 	import { flyAndScale } from '$lib/utils/transitions';
 
@@ -63,75 +64,124 @@
 	};
 
 	const downloadPdf = async () => {
-		const containerElement = document.getElementById('messages-container');
+		if ($settings?.stylizedPdfExport ?? true) {
+			const containerElement = document.getElementById('messages-container');
 
-		if (containerElement) {
+			if (containerElement) {
-			try {
+				try {
-				const isDarkMode = document.documentElement.classList.contains('dark');
+					const isDarkMode = document.documentElement.classList.contains('dark');
+					const virtualWidth = 800; // Fixed width in px
+					const pagePixelHeight = 1200; // Each slice height (adjust to avoid canvas bugs; generally 2–4k is safe)
 
-				console.log('isDarkMode', isDarkMode);
+					// Clone & style once
+					const clonedElement = containerElement.cloneNode(true);
+					clonedElement.classList.add('text-black');
+					clonedElement.classList.add('dark:text-white');
+					clonedElement.style.width = `${virtualWidth}px`;
+					clonedElement.style.position = 'absolute';
+					clonedElement.style.left = '-9999px'; // Offscreen
+					clonedElement.style.height = 'auto';
+					document.body.appendChild(clonedElement);
 
-				// Define a fixed virtual screen size
+					// Get total height after attached to DOM
-				const virtualWidth = 800; // Fixed width (adjust as needed)
+					const totalHeight = clonedElement.scrollHeight;
-				// Clone the container to avoid layout shifts
+					let offsetY = 0;
-				const clonedElement = containerElement.cloneNode(true);
+					let page = 0;
-				clonedElement.classList.add('text-black');
-				clonedElement.classList.add('dark:text-white');
-				clonedElement.style.width = `${virtualWidth}px`; // Apply fixed width
-				clonedElement.style.height = 'auto'; // Allow content to expand
 
-				document.body.appendChild(clonedElement); // Temporarily add to DOM
+					// Prepare PDF
+					const pdf = new jsPDF('p', 'mm', 'a4');
+					const imgWidth = 210; // A4 mm
+					const pageHeight = 297; // A4 mm
 
-				// Render to canvas with predefined width
+					while (offsetY < totalHeight) {
-				const canvas = await html2canvas(clonedElement, {
+						// For each slice, adjust scrollTop to show desired part
-					backgroundColor: isDarkMode ? '#000' : '#fff',
+						clonedElement.scrollTop = offsetY;
-					useCORS: true,
-					scale: 2, // Keep at 1x to avoid unexpected enlargements
-					width: virtualWidth, // Set fixed virtual screen width
-					windowWidth: virtualWidth // Ensure consistent rendering
-				});
 
-				document.body.removeChild(clonedElement); // Clean up temp element
+						// Optionally: mask/hide overflowing content via CSS if needed
+						clonedElement.style.maxHeight = `${pagePixelHeight}px`;
+						// Only render the visible part
+						const canvas = await html2canvas(clonedElement, {
+							backgroundColor: isDarkMode ? '#000' : '#fff',
+							useCORS: true,
+							scale: 2,
+							width: virtualWidth,
+							height: Math.min(pagePixelHeight, totalHeight - offsetY),
+							// Optionally: y offset for correct region?
+							windowWidth: virtualWidth
+							//windowHeight: pagePixelHeight,
+						});
+						const imgData = canvas.toDataURL('image/png');
+						// Maintain aspect ratio
+						const imgHeight = (canvas.height * imgWidth) / canvas.width;
+						const position = 0; // Always first line, since we've clipped vertically
 
-				const imgData = canvas.toDataURL('image/png');
+						if (page > 0) pdf.addPage();
 
-				// A4 page settings
+						// Set page background for dark mode
-				const pdf = new jsPDF('p', 'mm', 'a4');
+						if (isDarkMode) {
-				const imgWidth = 210; // A4 width in mm
+							pdf.setFillColor(0, 0, 0);
-				const pageHeight = 297; // A4 height in mm
+							pdf.rect(0, 0, imgWidth, pageHeight, 'F'); // black bg
+						}
 
-				// Maintain aspect ratio
+						pdf.addImage(imgData, 'PNG', 0, position, imgWidth, imgHeight);
-				const imgHeight = (canvas.height * imgWidth) / canvas.width;
-				let heightLeft = imgHeight;
-				let position = 0;
 
-				// Set page background for dark mode
+						offsetY += pagePixelHeight;
-				if (isDarkMode) {
+						page++;
-					pdf.setFillColor(0, 0, 0);
-					pdf.rect(0, 0, imgWidth, pageHeight, 'F'); // Apply black bg
-				}
-
-				pdf.addImage(imgData, 'PNG', 0, position, imgWidth, imgHeight);
-				heightLeft -= pageHeight;
-
-				// Handle additional pages
-				while (heightLeft > 0) {
-					position -= pageHeight;
-					pdf.addPage();
-
-					if (isDarkMode) {
-						pdf.setFillColor(0, 0, 0);
-						pdf.rect(0, 0, imgWidth, pageHeight, 'F');
 					}
 
-					pdf.addImage(imgData, 'PNG', 0, position, imgWidth, imgHeight);
+					document.body.removeChild(clonedElement);
-					heightLeft -= pageHeight;
-				}
 
-				pdf.save(`chat-${chat.chat.title}.pdf`);
+					pdf.save(`chat-${chat.chat.title}.pdf`);
-			} catch (error) {
+				} catch (error) {
-				console.error('Error generating PDF', error);
+					console.error('Error generating PDF', error);
+				}
 			}
+		} else {
+			console.log('Downloading PDF');
+
+			const chatText = await getChatAsText();
+
+			const doc = new jsPDF();
+
+			// Margins
+			const left = 15;
+			const top = 20;
+			const right = 15;
+			const bottom = 20;
+
+			const pageWidth = doc.internal.pageSize.getWidth();
+			const pageHeight = doc.internal.pageSize.getHeight();
+			const usableWidth = pageWidth - left - right;
+			const usableHeight = pageHeight - top - bottom;
+
+			// Font size and line height
+			const fontSize = 8;
+			doc.setFontSize(fontSize);
+			const lineHeight = fontSize * 1; // adjust if needed
+
+			// Split the markdown into lines (handles \n)
+			const paragraphs = chatText.split('\n');
+
+			let y = top;
+
+			for (let paragraph of paragraphs) {
+				// Wrap each paragraph to fit the width
+				const lines = doc.splitTextToSize(paragraph, usableWidth);
+
+				for (let line of lines) {
+					// If the line would overflow the bottom, add a new page
+					if (y + lineHeight > pageHeight - bottom) {
+						doc.addPage();
+						y = top;
+					}
+					doc.text(line, left, y);
+					y += lineHeight * 0.5;
+				}
+				// Add empty line at paragraph breaks
+				y += lineHeight * 0.1;
+			}
+
+			doc.save(`chat-${chat.chat.title}.pdf`);
 		}
 	};
 

src/lib/components/layout/Sidebar/ChatMenu.svelte

@@ -26,7 +26,7 @@
 		getChatPinnedStatusById,
 		toggleChatPinnedStatusById
 	} from '$lib/apis/chats';
-	import { chats, theme, user } from '$lib/stores';
+	import { chats, settings, theme, user } from '$lib/stores';
 	import { createMessagesList } from '$lib/utils';
 	import { downloadChatAsPDF } from '$lib/apis/utils';
 	import Download from '$lib/components/icons/Download.svelte';
@@ -81,74 +81,124 @@
 	const downloadPdf = async () => {
 		const chat = await getChatById(localStorage.token, chatId);
 
-		const containerElement = document.getElementById('messages-container');
+		if ($settings?.stylizedPdfExport ?? true) {
+			const containerElement = document.getElementById('messages-container');
 
-		if (containerElement) {
+			if (containerElement) {
-			try {
+				try {
-				const isDarkMode = $theme.includes('dark'); // Check theme mode
+					const isDarkMode = document.documentElement.classList.contains('dark');
+					const virtualWidth = 800; // Fixed width in px
+					const pagePixelHeight = 1200; // Each slice height (adjust to avoid canvas bugs; generally 2–4k is safe)
 
-				// Define a fixed virtual screen size
+					// Clone & style once
-				const virtualWidth = 1024; // Fixed width (adjust as needed)
+					const clonedElement = containerElement.cloneNode(true);
-				const virtualHeight = 1400; // Fixed height (adjust as needed)
+					clonedElement.classList.add('text-black');
+					clonedElement.classList.add('dark:text-white');
+					clonedElement.style.width = `${virtualWidth}px`;
+					clonedElement.style.position = 'absolute';
+					clonedElement.style.left = '-9999px'; // Offscreen
+					clonedElement.style.height = 'auto';
+					document.body.appendChild(clonedElement);
 
-				// Clone the container to avoid layout shifts
+					// Get total height after attached to DOM
-				const clonedElement = containerElement.cloneNode(true);
+					const totalHeight = clonedElement.scrollHeight;
-				clonedElement.style.width = `${virtualWidth}px`; // Apply fixed width
+					let offsetY = 0;
-				clonedElement.style.height = 'auto'; // Allow content to expand
+					let page = 0;
 
-				document.body.appendChild(clonedElement); // Temporarily add to DOM
+					// Prepare PDF
+					const pdf = new jsPDF('p', 'mm', 'a4');
+					const imgWidth = 210; // A4 mm
+					const pageHeight = 297; // A4 mm
 
-				// Render to canvas with predefined width
+					while (offsetY < totalHeight) {
-				const canvas = await html2canvas(clonedElement, {
+						// For each slice, adjust scrollTop to show desired part
-					backgroundColor: isDarkMode ? '#000' : '#fff',
+						clonedElement.scrollTop = offsetY;
-					useCORS: true,
-					scale: 2, // Keep at 1x to avoid unexpected enlargements
-					width: virtualWidth, // Set fixed virtual screen width
-					windowWidth: virtualWidth, // Ensure consistent rendering
-					windowHeight: virtualHeight
-				});
 
-				document.body.removeChild(clonedElement); // Clean up temp element
+						// Optionally: mask/hide overflowing content via CSS if needed
+						clonedElement.style.maxHeight = `${pagePixelHeight}px`;
+						// Only render the visible part
+						const canvas = await html2canvas(clonedElement, {
+							backgroundColor: isDarkMode ? '#000' : '#fff',
+							useCORS: true,
+							scale: 2,
+							width: virtualWidth,
+							height: Math.min(pagePixelHeight, totalHeight - offsetY),
+							// Optionally: y offset for correct region?
+							windowWidth: virtualWidth
+							//windowHeight: pagePixelHeight,
+						});
+						const imgData = canvas.toDataURL('image/png');
+						// Maintain aspect ratio
+						const imgHeight = (canvas.height * imgWidth) / canvas.width;
+						const position = 0; // Always first line, since we've clipped vertically
 
-				const imgData = canvas.toDataURL('image/png');
+						if (page > 0) pdf.addPage();
 
-				// A4 page settings
+						// Set page background for dark mode
-				const pdf = new jsPDF('p', 'mm', 'a4');
+						if (isDarkMode) {
-				const imgWidth = 210; // A4 width in mm
+							pdf.setFillColor(0, 0, 0);
-				const pageHeight = 297; // A4 height in mm
+							pdf.rect(0, 0, imgWidth, pageHeight, 'F'); // black bg
+						}
 
-				// Maintain aspect ratio
+						pdf.addImage(imgData, 'PNG', 0, position, imgWidth, imgHeight);
-				const imgHeight = (canvas.height * imgWidth) / canvas.width;
-				let heightLeft = imgHeight;
-				let position = 0;
 
-				// Set page background for dark mode
+						offsetY += pagePixelHeight;
-				if (isDarkMode) {
+						page++;
-					pdf.setFillColor(0, 0, 0);
-					pdf.rect(0, 0, imgWidth, pageHeight, 'F'); // Apply black bg
-				}
-
-				pdf.addImage(imgData, 'PNG', 0, position, imgWidth, imgHeight);
-				heightLeft -= pageHeight;
-
-				// Handle additional pages
-				while (heightLeft > 0) {
-					position -= pageHeight;
-					pdf.addPage();
-
-					if (isDarkMode) {
-						pdf.setFillColor(0, 0, 0);
-						pdf.rect(0, 0, imgWidth, pageHeight, 'F');
 					}
 
-					pdf.addImage(imgData, 'PNG', 0, position, imgWidth, imgHeight);
+					document.body.removeChild(clonedElement);
-					heightLeft -= pageHeight;
-				}
 
-				pdf.save(`chat-${chat.chat.title}.pdf`);
+					pdf.save(`chat-${chat.chat.title}.pdf`);
-			} catch (error) {
+				} catch (error) {
-				console.error('Error generating PDF', error);
+					console.error('Error generating PDF', error);
+				}
 			}
+		} else {
+			console.log('Downloading PDF');
+
+			const chatText = await getChatAsText(chat);
+
+			const doc = new jsPDF();
+
+			// Margins
+			const left = 15;
+			const top = 20;
+			const right = 15;
+			const bottom = 20;
+
+			const pageWidth = doc.internal.pageSize.getWidth();
+			const pageHeight = doc.internal.pageSize.getHeight();
+			const usableWidth = pageWidth - left - right;
+			const usableHeight = pageHeight - top - bottom;
+
+			// Font size and line height
+			const fontSize = 8;
+			doc.setFontSize(fontSize);
+			const lineHeight = fontSize * 1; // adjust if needed
+
+			// Split the markdown into lines (handles \n)
+			const paragraphs = chatText.split('\n');
+
+			let y = top;
+
+			for (let paragraph of paragraphs) {
+				// Wrap each paragraph to fit the width
+				const lines = doc.splitTextToSize(paragraph, usableWidth);
+
+				for (let line of lines) {
+					// If the line would overflow the bottom, add a new page
+					if (y + lineHeight > pageHeight - bottom) {
+						doc.addPage();
+						y = top;
+					}
+					doc.text(line, left, y);
+					y += lineHeight;
+				}
+				// Add empty line at paragraph breaks
+				y += lineHeight * 0.5;
+			}
+
+			doc.save(`chat-${chat.chat.title}.pdf`);
 		}
 	};
 

src/lib/components/notes/NoteEditor.svelte

@@ -180,7 +180,10 @@
 			return;
 		}
 
-		const model = $models.find((model) => model.id === selectedModelId);
+		const model = $models
+			.filter((model) => model.id === selectedModelId && !(model?.info?.meta?.hidden ?? false))
+			.find((model) => model.id === selectedModelId);
+
 		if (!model) {
 			selectedModelId = '';
 			return;
@@ -599,6 +602,16 @@ Provide the enhanced notes in markdown format. Use markdown syntax for headings,
 			selectedModelId = '';
 		}
 
+		if (selectedModelId) {
+			const model = $models
+				.filter((model) => model.id === selectedModelId && !(model?.info?.meta?.hidden ?? false))
+				.find((model) => model.id === selectedModelId);
+
+			if (!model) {
+				selectedModelId = '';
+			}
+		}
+
 		const dropzoneElement = document.getElementById('note-editor');
 
 		dropzoneElement?.addEventListener('dragover', onDragOver);
@@ -660,7 +673,10 @@ Provide the enhanced notes in markdown format. Use markdown syntax for headings,
 							class="w-full bg-transparent text-sm outline-hidden"
 							bind:value={selectedModelId}
 						>
-							{#each $models as model}
+							<option value="" class="bg-gray-50 dark:bg-gray-700" disabled>
+								{$i18n.t('Select a model')}
+							</option>
+							{#each $models.filter((model) => !(model?.info?.meta?.hidden ?? false)) as model}
 								<option value={model.id} class="bg-gray-50 dark:bg-gray-700">{model.name}</option>
 							{/each}
 						</select>

src/lib/components/workspace/Knowledge/KnowledgeBase.svelte

@@ -764,7 +764,7 @@
 										className="input-prose-sm"
 										bind:value={selectedFileContent}
 										placeholder={$i18n.t('Add content here')}
-										preserveBreaks={true}
+										preserveBreaks={false}
 									/>
 								{/key}
 							</div>
@@ -822,7 +822,7 @@
 										className="input-prose-sm"
 										bind:value={selectedFileContent}
 										placeholder={$i18n.t('Add content here')}
-										preserveBreaks={true}
+										preserveBreaks={false}
 									/>
 								{/key}
 							</div>

src/lib/i18n/locales/ar-BH/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "وضع الطلب",
+	"Reranking Engine": "",
 	"Reranking Model": "إعادة تقييم النموذج",
-	"Reranking model disabled": "تم تعطيل نموذج إعادة الترتيب",
-	"Reranking model set to \"{{reranking_model}}\"": "تم ضبط نموذج إعادة الترتيب على \"{{reranking_model}}\"",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "عرض",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "إظهار الاختصارات",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "STT اعدادات",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "(e.g. about the Roman Empire) الترجمة",
 	"Success": "نجاح",
 	"Successfully updated.": "تم التحديث بنجاح",

src/lib/i18n/locales/ar/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "عقوبة التكرار (Ollama)",
 	"Reply in Thread": "الرد داخل سلسلة الرسائل",
 	"Request Mode": "وضع الطلب",
+	"Reranking Engine": "",
 	"Reranking Model": "إعادة تقييم النموذج",
-	"Reranking model disabled": "تم تعطيل نموذج إعادة الترتيب",
-	"Reranking model set to \"{{reranking_model}}\"": "تم ضبط نموذج إعادة الترتيب على \"{{reranking_model}}\"",
 	"Reset": "إعادة تعيين",
 	"Reset All Models": "إعادة تعيين جميع النماذج",
 	"Reset Upload Directory": "إعادة تعيين مجلد التحميل",
@@ -1069,6 +1068,8 @@
 	"Show": "عرض",
 	"Show \"What's New\" modal on login": "عرض نافذة \"ما الجديد\" عند تسجيل الدخول",
 	"Show Admin Details in Account Pending Overlay": "عرض تفاصيل المشرف في نافذة \"الحساب قيد الانتظار\"",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "إظهار الاختصارات",
 	"Show your support!": "أظهر دعمك!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "بث استجابة الدردشة",
 	"STT Model": "نموذج تحويل الصوت إلى نص (STT)",
 	"STT Settings": "STT اعدادات",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "(e.g. about the Roman Empire) الترجمة",
 	"Success": "نجاح",
 	"Successfully updated.": "تم التحديث بنجاح",

src/lib/i18n/locales/bg-BG/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Наказание за повторение (Ollama)",
 	"Reply in Thread": "Отговори в тред",
 	"Request Mode": "Режим на заявка",
+	"Reranking Engine": "",
 	"Reranking Model": "Модел за преподреждане",
-	"Reranking model disabled": "Моделът за преподреждане е деактивиран",
-	"Reranking model set to \"{{reranking_model}}\"": "Моделът за преподреждане е зададен на \"{{reranking_model}}\"",
 	"Reset": "Нулиране",
 	"Reset All Models": "Нулиране на всички модели",
 	"Reset Upload Directory": "Нулиране на директорията за качване",
@@ -1069,6 +1068,8 @@
 	"Show": "Покажи",
 	"Show \"What's New\" modal on login": "Покажи модалния прозорец \"Какво е ново\" при вписване",
 	"Show Admin Details in Account Pending Overlay": "Покажи детайлите на администратора в наслагването на изчакващ акаунт",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Покажи преки пътища",
 	"Show your support!": "Покажете вашата подкрепа!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Поточен чат отговор",
 	"STT Model": "STT Модел",
 	"STT Settings": "STT Настройки",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Подтитул (напр. за Римска империя)",
 	"Success": "Успех",
 	"Successfully updated.": "Успешно обновено.",

src/lib/i18n/locales/bn-BD/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "রিকোয়েস্ট মোড",
+	"Reranking Engine": "",
 	"Reranking Model": "রির্যাক্টিং মডেল",
-	"Reranking model disabled": "রির্যাক্টিং মডেল নিষ্ক্রিয় করা",
-	"Reranking model set to \"{{reranking_model}}\"": "রির ্যাঙ্কিং মডেল \"{{reranking_model}}\" -এ সেট করা আছে",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "দেখান",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "শর্টকাটগুলো দেখান",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "STT সেটিংস",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "সাবটাইটল (রোমান ইম্পার্টের সম্পর্কে)",
 	"Success": "সফল",
 	"Successfully updated.": "সফলভাবে আপডেট হয়েছে",

src/lib/i18n/locales/bo-TB/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "བསྐྱར་ཟློས་ཀྱི་ཆད་པ། (Ollama)",
 	"Reply in Thread": "བརྗོད་གཞིའི་ནང་ལན་འདེབས།",
 	"Request Mode": "རེ་ཞུའི་མ་དཔེ།",
+	"Reranking Engine": "",
 	"Reranking Model": "བསྐྱར་སྒྲིག་དཔེ་དབྱིབས།",
-	"Reranking model disabled": "བསྐྱར་སྒྲིག་དཔེ་དབྱིབས་ནུས་མེད་བཏང་།",
-	"Reranking model set to \"{{reranking_model}}\"": "བསྐྱར་སྒྲིག་དཔེ་དབྱིབས་ \"{{reranking_model}}\" ལ་བཀོད་སྒྲིག་བྱས།",
 	"Reset": "སླར་སྒྲིག",
 	"Reset All Models": "དཔེ་དབྱིབས་ཡོངས་རྫོགས་སླར་སྒྲིག",
 	"Reset Upload Directory": "སྤར་བའི་ཐོ་འཚོལ་སླར་སྒྲིག",
@@ -1069,6 +1068,8 @@
 	"Show": "སྟོན་པ།",
 	"Show \"What's New\" modal on login": "ནང་འཛུལ་སྐབས་ \"གསར་པ་ཅི་ཡོད\" modal སྟོན་པ།",
 	"Show Admin Details in Account Pending Overlay": "རྩིས་ཁྲ་སྒུག་བཞིན་པའི་གཏོགས་ངོས་སུ་དོ་དམ་པའི་ཞིབ་ཕྲ་སྟོན་པ།",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "དཔེ་དབྱིབས་སྟོན་པ།",
 	"Show shortcuts": "མྱུར་ལམ་སྟོན་པ།",
 	"Show your support!": "ཁྱེད་ཀྱི་རྒྱབ་སྐྱོར་སྟོན་པ།",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "ཁ་བརྡའི་ལན་རྒྱུག་པ།",
 	"STT Model": "STT དཔེ་དབྱིབས།",
 	"STT Settings": "STT སྒྲིག་འགོད།",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "ཁ་བྱང་ཕལ་པ། (དཔེར་ན། རོམ་མའི་གོང་མའི་རྒྱལ་ཁབ་སྐོར།)",
 	"Success": "ལེགས་འགྲུབ།",
 	"Successfully updated.": "ལེགས་པར་གསར་སྒྱུར་བྱས།",

src/lib/i18n/locales/ca-ES/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Penalització per repetició (Ollama)",
 	"Reply in Thread": "Respondre al fil",
 	"Request Mode": "Mode de sol·licitud",
+	"Reranking Engine": "",
 	"Reranking Model": "Model de reavaluació",
-	"Reranking model disabled": "Model de reavaluació desactivat",
-	"Reranking model set to \"{{reranking_model}}\"": "Model de reavaluació establert a \"{{reranking_model}}\"",
 	"Reset": "Restableix",
 	"Reset All Models": "Restablir tots els models",
 	"Reset Upload Directory": "Restableix el directori de pujades",
@@ -1069,6 +1068,8 @@
 	"Show": "Mostrar",
 	"Show \"What's New\" modal on login": "Veure 'Què hi ha de nou' a l'entrada",
 	"Show Admin Details in Account Pending Overlay": "Mostrar els detalls de l'administrador a la superposició del compte pendent",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Mostrar el model",
 	"Show shortcuts": "Mostrar dreceres",
 	"Show your support!": "Mostra el teu suport!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Fer streaming de la resposta del xat",
 	"STT Model": "Model SST",
 	"STT Settings": "Preferències de STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtítol (per exemple, sobre l'Imperi Romà)",
 	"Success": "Èxit",
 	"Successfully updated.": "Actualitzat correctament.",

src/lib/i18n/locales/ceb-PH/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Query mode",
+	"Reranking Engine": "",
 	"Reranking Model": "",
-	"Reranking model disabled": "",
-	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "Pagpakita",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Ipakita ang mga shortcut",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "Mga setting sa STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
 	"Success": "Kalampusan",
 	"Successfully updated.": "Malampuson nga na-update.",

src/lib/i18n/locales/cs-CZ/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Režim žádosti",
+	"Reranking Engine": "",
 	"Reranking Model": "Model pro přehodnocení pořadí",
-	"Reranking model disabled": "Přeřazovací model je deaktivován",
-	"Reranking model set to \"{{reranking_model}}\"": "Model pro přeřazení nastaven na \"{{reranking_model}}\"",
 	"Reset": "režim Reset",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Resetovat adresář nahrávání",
@@ -1069,6 +1068,8 @@
 	"Show": "Zobrazit",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Zobrazit podrobnosti administrátora v překryvném okně s čekajícím účtem",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Zobrazit klávesové zkratky",
 	"Show your support!": "Vyjadřete svou podporu!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Odezva chatu Stream",
 	"STT Model": "Model rozpoznávání řeči na text (STT)",
 	"STT Settings": "Nastavení STT (Rozpoznávání řeči)",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Titulky (např. o Římské říši)",
 	"Success": "Úspěch",
 	"Successfully updated.": "Úspěšně aktualizováno.",

src/lib/i18n/locales/de-DE/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Wiederholungsstrafe (Ollama)",
 	"Reply in Thread": "Im Thread antworten",
 	"Request Mode": "Anforderungsmodus",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking-Modell",
-	"Reranking model disabled": "Reranking-Modell deaktiviert",
-	"Reranking model set to \"{{reranking_model}}\"": "Reranking-Modell \"{{reranking_model}}\" fesgelegt",
 	"Reset": "Zurücksetzen",
 	"Reset All Models": "Alle Modelle zurücksetzen",
 	"Reset Upload Directory": "Upload-Verzeichnis zurücksetzen",
@@ -1069,6 +1068,8 @@
 	"Show": "Anzeigen",
 	"Show \"What's New\" modal on login": "\"Was gibt's Neues\"-Modal beim Anmelden anzeigen",
 	"Show Admin Details in Account Pending Overlay": "Admin-Details im Account-Pending-Overlay anzeigen",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Modell anzeigen",
 	"Show shortcuts": "Verknüpfungen anzeigen",
 	"Show your support!": "Zeigen Sie Ihre Unterstützung!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Chat-Antwort streamen",
 	"STT Model": "STT-Modell",
 	"STT Settings": "STT-Einstellungen",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Untertitel (z. B. über das Römische Reich)",
 	"Success": "Erfolg",
 	"Successfully updated.": "Erfolgreich aktualisiert.",

src/lib/i18n/locales/dg-DG/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Request Bark",
+	"Reranking Engine": "",
 	"Reranking Model": "",
-	"Reranking model disabled": "",
-	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "Show much show",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Show shortcuts much shortcut",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "STT Settings very settings",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
 	"Success": "Success very success",
 	"Successfully updated.": "Successfully updated. Very updated.",

src/lib/i18n/locales/el-GR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Λειτουργία Αιτήματος",
+	"Reranking Engine": "",
 	"Reranking Model": "Μοντέλο Επαναταξινόμησης",
-	"Reranking model disabled": "Το μοντέλο επαναταξινόμησης απενεργοποιήθηκε",
-	"Reranking model set to \"{{reranking_model}}\"": "Το μοντέλο επαναταξινόμησης ορίστηκε σε \"{{reranking_model}}\"",
 	"Reset": "Επαναφορά",
 	"Reset All Models": "Επαναφορά Όλων των Μοντέλων",
 	"Reset Upload Directory": "Επαναφορά Καταλόγου Ανεβάσματος",
@@ -1069,6 +1068,8 @@
 	"Show": "Εμφάνιση",
 	"Show \"What's New\" modal on login": "Εμφάνιση του παράθυρου \"Τι νέο υπάρχει\" κατά την είσοδο",
 	"Show Admin Details in Account Pending Overlay": "Εμφάνιση Λεπτομερειών Διαχειριστή στο Υπέρθεση Εκκρεμής Λογαριασμού",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Εμφάνιση συντομεύσεων",
 	"Show your support!": "Δείξτε την υποστήριξή σας!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Συνομιλία Ροής Απάντησης",
 	"STT Model": "Μοντέλο STT",
 	"STT Settings": "Ρυθμίσεις STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Υπότιτλος (π.χ. για την Ρωμαϊκή Αυτοκρατορία)",
 	"Success": "Επιτυχία",
 	"Successfully updated.": "Επιτυχώς ενημερώθηκε.",

src/lib/i18n/locales/en-GB/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "",
+	"Reranking Engine": "",
 	"Reranking Model": "",
-	"Reranking model disabled": "",
-	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
 	"Success": "",
 	"Successfully updated.": "",

src/lib/i18n/locales/en-US/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "",
+	"Reranking Engine": "",
 	"Reranking Model": "",
-	"Reranking model disabled": "",
-	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
 	"Success": "",
 	"Successfully updated.": "",

src/lib/i18n/locales/es-ES/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Penalización Repetición (Ollama)",
 	"Reply in Thread": "Responder en Hilo",
 	"Request Mode": "Modo de Petición",
+	"Reranking Engine": "",
 	"Reranking Model": "Modelo de Reclasificación",
-	"Reranking model disabled": "Modelo de reclasificacioń deshabilitado",
-	"Reranking model set to \"{{reranking_model}}\"": "Modelo de reclasificación establecido a \"{{reranking_model}}\"",
 	"Reset": "Reiniciar",
 	"Reset All Models": "Reiniciar Todos los Modelos",
 	"Reset Upload Directory": "Reiniciar Directorio de Subidas",
@@ -1069,6 +1068,8 @@
 	"Show": "Mostrar",
 	"Show \"What's New\" modal on login": "Mostrar modal \"Qué hay de Nuevo\" al iniciar sesión",
 	"Show Admin Details in Account Pending Overlay": "Mostrar Detalles Admin en la sobrecapa de 'Cuenta Pendiente'",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Mostrar Modelo",
 	"Show shortcuts": "Mostrar Atajos",
 	"Show your support!": "¡Muestra tu apoyo!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Transmisión Directa de la  Respuesta del Chat",
 	"STT Model": "Modelo STT",
 	"STT Settings": "Ajustes Voz a Texto (STT)",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtítulo (p.ej. sobre el Imperio Romano)",
 	"Success": "Correcto",
 	"Successfully updated.": "Actualizado correctamente.",

src/lib/i18n/locales/et-EE/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Korduse karistus (Ollama)",
 	"Reply in Thread": "Vasta lõimes",
 	"Request Mode": "Päringu režiim",
+	"Reranking Engine": "",
 	"Reranking Model": "Ümberjärjestamise mudel",
-	"Reranking model disabled": "Ümberjärjestamise mudel keelatud",
-	"Reranking model set to \"{{reranking_model}}\"": "Ümberjärjestamise mudel määratud kui \"{{reranking_model}}\"",
 	"Reset": "Lähtesta",
 	"Reset All Models": "Lähtesta kõik mudelid",
 	"Reset Upload Directory": "Lähtesta üleslaadimiste kataloog",
@@ -1069,6 +1068,8 @@
 	"Show": "Näita",
 	"Show \"What's New\" modal on login": "Näita \"Mis on uut\" modaalakent sisselogimisel",
 	"Show Admin Details in Account Pending Overlay": "Näita administraatori üksikasju konto ootel kattekihil",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Näita otseteid",
 	"Show your support!": "Näita oma toetust!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Voogedasta vestluse vastust",
 	"STT Model": "STT mudel",
 	"STT Settings": "STT seaded",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Alampealkiri (nt Rooma impeeriumi kohta)",
 	"Success": "Õnnestus",
 	"Successfully updated.": "Edukalt uuendatud.",

src/lib/i18n/locales/eu-ES/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Eskaera modua",
+	"Reranking Engine": "",
 	"Reranking Model": "Berrantolatze modeloa",
-	"Reranking model disabled": "Berrantolatze modeloa desgaituta",
-	"Reranking model set to \"{{reranking_model}}\"": "Berrantolatze modeloa \"{{reranking_model}}\"-era ezarrita",
 	"Reset": "Berrezarri",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Berrezarri karga direktorioa",
@@ -1069,6 +1068,8 @@
 	"Show": "Erakutsi",
 	"Show \"What's New\" modal on login": "Erakutsi \"Berritasunak\" modala saioa hastean",
 	"Show Admin Details in Account Pending Overlay": "Erakutsi administratzaile xehetasunak kontu zain geruzan",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Erakutsi lasterbideak",
 	"Show your support!": "Erakutsi zure babesa!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Transmititu txat erantzuna",
 	"STT Model": "STT modeloa",
 	"STT Settings": "STT ezarpenak",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Azpititulua (adib. Erromatar Inperioari buruz)",
 	"Success": "Arrakasta",
 	"Successfully updated.": "Ongi eguneratu da.",

src/lib/i18n/locales/fa-IR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "جریمه تکرار (ollama)",
 	"Reply in Thread": "پاسخ در رشته",
 	"Request Mode": "حالت درخواست",
+	"Reranking Engine": "",
 	"Reranking Model": "مدل ری\u200cشناسی مجدد غیرفعال است",
-	"Reranking model disabled": "مدل ری\u200cشناسی مجدد غیرفعال است",
-	"Reranking model set to \"{{reranking_model}}\"": "مدل ری\u200cشناسی مجدد به \"{{reranking_model}}\" تنظیم شده است",
 	"Reset": "بازنشانی",
 	"Reset All Models": "بازنشانی همه مدل\u200cها",
 	"Reset Upload Directory": "بازنشانی پوشه آپلود",
@@ -1069,6 +1068,8 @@
 	"Show": "نمایش",
 	"Show \"What's New\" modal on login": "نمایش مودال \"موارد جدید\" هنگام ورود",
 	"Show Admin Details in Account Pending Overlay": "نمایش جزئیات مدیر در پوشش حساب در انتظار",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "نمایش مدل",
 	"Show shortcuts": "نمایش میانبرها",
 	"Show your support!": "حمایت خود را نشان دهید!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "پاسخ چت جریانی",
 	"STT Model": "مدل تبدیل صدا به متن",
 	"STT Settings": "تنظیمات تبدیل صدا به متن",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "زیرنویس (برای مثال: درباره رمانی)",
 	"Success": "موفقیت",
 	"Successfully updated.": "با موفقیت به\u200cروز شد",

src/lib/i18n/locales/fi-FI/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Toisto rangaistus (Ollama)",
 	"Reply in Thread": "Vastauksia ",
 	"Request Mode": "Pyyntötila",
+	"Reranking Engine": "",
 	"Reranking Model": "Uudelleenpisteytymismalli",
-	"Reranking model disabled": "Uudelleenpisteytymismalli poistettu käytöstä",
-	"Reranking model set to \"{{reranking_model}}\"": "\"{{reranking_model}}\" valittu uudelleenpisteytysmalliksi",
 	"Reset": "Palauta",
 	"Reset All Models": "Palauta kaikki mallit",
 	"Reset Upload Directory": "Palauta latauspolku",
@@ -1069,6 +1068,8 @@
 	"Show": "Näytä",
 	"Show \"What's New\" modal on login": "Näytä \"Mitä uutta\" -modaali kirjautumisen yhteydessä",
 	"Show Admin Details in Account Pending Overlay": "Näytä ylläpitäjän tiedot odottavan tilin päällä",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Näytä malli",
 	"Show shortcuts": "Näytä pikanäppäimet",
 	"Show your support!": "Osoita tukesi!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Streamaa keskusteluvastaus",
 	"STT Model": "Puheentunnistusmalli",
 	"STT Settings": "Puheentunnistuksen asetukset",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Alaotsikko (esim. Rooman valtakunta)",
 	"Success": "Onnistui",
 	"Successfully updated.": "Päivitetty onnistuneesti.",

src/lib/i18n/locales/fr-CA/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Mode de Requête",
+	"Reranking Engine": "",
 	"Reranking Model": "Modèle de ré-ranking",
-	"Reranking model disabled": "Modèle de ré-ranking désactivé",
-	"Reranking model set to \"{{reranking_model}}\"": "Modèle de ré-ranking défini sur « {{reranking_model}} »",
 	"Reset": "Réinitialiser",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Répertoire de téléchargement réinitialisé",
@@ -1069,6 +1068,8 @@
 	"Show": "Montrer",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Afficher les détails de l'administrateur dans la superposition en attente du compte",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Afficher les raccourcis",
 	"Show your support!": "Montre ton soutien !",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "Modèle de STT",
 	"STT Settings": "Paramètres de STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Sous-titres (par ex. sur l'Empire romain)",
 	"Success": "Réussite",
 	"Successfully updated.": "Mise à jour réussie.",

src/lib/i18n/locales/fr-FR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Pénalité de répétition (Ollama)",
 	"Reply in Thread": "Répondre dans le fil de discussion",
 	"Request Mode": "Mode de requête",
+	"Reranking Engine": "",
 	"Reranking Model": "Modèle de ré-ranking",
-	"Reranking model disabled": "Modèle de ré-ranking désactivé",
-	"Reranking model set to \"{{reranking_model}}\"": "Modèle de ré-ranking défini sur « {{reranking_model}} »",
 	"Reset": "Réinitialiser",
 	"Reset All Models": "Réinitialiser tous les modèles",
 	"Reset Upload Directory": "Réinitialiser le répertoire de téléchargement",
@@ -1069,6 +1068,8 @@
 	"Show": "Afficher",
 	"Show \"What's New\" modal on login": "Afficher la fenêtre modale \"Quoi de neuf\" lors de la connexion",
 	"Show Admin Details in Account Pending Overlay": "Afficher les coordonnées de l'administrateur aux comptes en attente",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Afficher le model",
 	"Show shortcuts": "Afficher les raccourcis",
 	"Show your support!": "Montrez votre soutien !",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Streamer la réponse de la conversation",
 	"STT Model": "Modèle de Speech-to-Text",
 	"STT Settings": "Paramètres de Speech-to-Text",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Sous-titres (par ex. sur l'Empire romain)",
 	"Success": "Réussite",
 	"Successfully updated.": "Mise à jour réussie.",

src/lib/i18n/locales/he-IL/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "מצב בקשה",
+	"Reranking Engine": "",
 	"Reranking Model": "מודל דירוג מחדש",
-	"Reranking model disabled": "מודל דירוג מחדש מושבת",
-	"Reranking model set to \"{{reranking_model}}\"": "מודל דירוג מחדש הוגדר ל-\"{{reranking_model}}\"",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "הצג",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "הצג קיצורי דרך",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "הגדרות חקירה של TTS",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "תחקור (לדוגמה: על מעמד הרומי)",
 	"Success": "הצלחה",
 	"Successfully updated.": "עדכון הצלחה.",

src/lib/i18n/locales/hi-IN/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "अनुरोध मोड",
+	"Reranking Engine": "",
 	"Reranking Model": "रीरैकिंग मोड",
-	"Reranking model disabled": "पुनर्रैंकिंग मॉडल अक्षम किया गया",
-	"Reranking model set to \"{{reranking_model}}\"": "रीरैंकिंग मॉडल को \"{{reranking_model}}\" पर \u200b\u200bसेट किया गया",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "दिखाओ",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "शॉर्टकट दिखाएँ",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "STT सेटिंग्स ",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "उपशीर्षक (जैसे रोमन साम्राज्य के बारे में)",
 	"Success": "संपन्न",
 	"Successfully updated.": "सफलतापूर्वक उत्परिवर्तित।",

src/lib/i18n/locales/hr-HR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Način zahtjeva",
+	"Reranking Engine": "",
 	"Reranking Model": "Model za ponovno rangiranje",
-	"Reranking model disabled": "Model za ponovno rangiranje onemogućen",
-	"Reranking model set to \"{{reranking_model}}\"": "Model za ponovno rangiranje postavljen na \"{{reranking_model}}\"",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Poništi upload direktorij",
@@ -1069,6 +1068,8 @@
 	"Show": "Pokaži",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Pokaži prečace",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "STT model",
 	"STT Settings": "STT postavke",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Podnaslov (npr. o Rimskom carstvu)",
 	"Success": "Uspjeh",
 	"Successfully updated.": "Uspješno ažurirano.",

src/lib/i18n/locales/hu-HU/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Ismétlési büntetés (Ollama)",
 	"Reply in Thread": "Válasz szálban",
 	"Request Mode": "Kérési mód",
+	"Reranking Engine": "",
 	"Reranking Model": "Újrarangsoroló modell",
-	"Reranking model disabled": "Újrarangsoroló modell letiltva",
-	"Reranking model set to \"{{reranking_model}}\"": "Újrarangsoroló modell beállítva erre: \"{{reranking_model}}\"",
 	"Reset": "Visszaállítás",
 	"Reset All Models": "Minden modell visszaállítása",
 	"Reset Upload Directory": "Feltöltési könyvtár visszaállítása",
@@ -1069,6 +1068,8 @@
 	"Show": "Mutat",
 	"Show \"What's New\" modal on login": "\"Mi újság\" modal megjelenítése bejelentkezéskor",
 	"Show Admin Details in Account Pending Overlay": "Admin részletek megjelenítése a függő fiók átfedésben",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Modell megjelenítése",
 	"Show shortcuts": "Gyorsbillentyűk megjelenítése",
 	"Show your support!": "Mutassa meg támogatását!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Chat válasz streamelése",
 	"STT Model": "STT modell",
 	"STT Settings": "STT beállítások",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Alcím (pl. a Római Birodalomról)",
 	"Success": "Siker",
 	"Successfully updated.": "Sikeresen frissítve.",

src/lib/i18n/locales/id-ID/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Mode Permintaan",
+	"Reranking Engine": "",
 	"Reranking Model": "Model Pemeringkatan Ulang",
-	"Reranking model disabled": "Model pemeringkatan ulang dinonaktifkan",
-	"Reranking model set to \"{{reranking_model}}\"": "Model pemeringkatan diatur ke \"{{reranking_model}}\"",
 	"Reset": "Atur Ulang",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Setel Ulang Direktori Unggahan",
@@ -1069,6 +1068,8 @@
 	"Show": "Tampilkan",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Tampilkan Detail Admin di Hamparan Akun Tertunda",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Tampilkan pintasan",
 	"Show your support!": "Tunjukkan dukungan Anda!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "Model STT",
 	"STT Settings": "Pengaturan STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtitle (misalnya tentang Kekaisaran Romawi)",
 	"Success": "Berhasil",
 	"Successfully updated.": "Berhasil diperbarui.",

src/lib/i18n/locales/ie-GA/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Pionós Athrá (Ollama)",
 	"Reply in Thread": "Freagra i Snáithe",
 	"Request Mode": "Mód Iarratais",
+	"Reranking Engine": "",
 	"Reranking Model": "Múnla Athrangú",
-	"Reranking model disabled": "Samhail athrangú faoi mhíchumas",
-	"Reranking model set to \"{{reranking_model}}\"": "Samhail athrangú socraithe go \"{{reranking_model}}\"",
 	"Reset": "Athshocraigh",
 	"Reset All Models": "Athshocraigh Gach Múnla",
 	"Reset Upload Directory": "Athshocraigh Eolaire Uas",
@@ -1069,6 +1068,8 @@
 	"Show": "Taispeáin",
 	"Show \"What's New\" modal on login": "Taispeáin módúil \"Cad atá Nua\" ar logáil isteach",
 	"Show Admin Details in Account Pending Overlay": "Taispeáin Sonraí Riaracháin sa Chuntas ar Feitheamh Forleagan",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Taispeáin Múnla",
 	"Show shortcuts": "Taispeáin aicearraí",
 	"Show your support!": "Taispeáin do thacaíocht!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Freagra Comhrá Sruth",
 	"STT Model": "Múnla STT",
 	"STT Settings": "Socruithe STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Fotheideal (m.sh. faoin Impireacht Rómhánach)",
 	"Success": "Rath",
 	"Successfully updated.": "Nuashonraithe go rathúil.",

src/lib/i18n/locales/ja-JP/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "リクエストモード",
+	"Reranking Engine": "",
 	"Reranking Model": "モデルの再ランキング",
-	"Reranking model disabled": "再ランキングモデルが無効です",
-	"Reranking model set to \"{{reranking_model}}\"": "再ランキングモデルを \"{{reranking_model}}\" に設定しました",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "アップロードディレクトリをリセット",
@@ -1069,6 +1068,8 @@
 	"Show": "表示",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "表示",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "STTモデル",
 	"STT Settings": "STT設定",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "タイトル (例: ローマ帝国)",
 	"Success": "成功",
 	"Successfully updated.": "正常に更新されました。",

src/lib/i18n/locales/ka-GE/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "ნაკადში პასუხი",
 	"Request Mode": "მოთხოვნის რეჟიმი",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking მოდელი",
-	"Reranking model disabled": "Reranking მოდელი გათიშულია",
-	"Reranking model set to \"{{reranking_model}}\"": "Reranking model set to \"{{reranking_model}}\"",
 	"Reset": "ჩამოყრა",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "ჩვენება",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "მალსახმობების ჩვენება",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "STT-ის მორგება",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "სუბტიტრები (მაგ. რომის იმპერიის შესახებ)",
 	"Success": "წარმატება",
 	"Successfully updated.": "წარმატებით განახლდა.",

src/lib/i18n/locales/ko-KR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "스레드에 답글 달기",
 	"Request Mode": "요청 모드",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking 모델",
-	"Reranking model disabled": "Reranking 모델 비활성화",
-	"Reranking model set to \"{{reranking_model}}\"": "Reranking 모델을 \"{{reranking_model}}\"로 설정",
 	"Reset": "초기화",
 	"Reset All Models": "모든 모델 초기화",
 	"Reset Upload Directory": "업로드 디렉토리 초기화",
@@ -1069,6 +1068,8 @@
 	"Show": "보기",
 	"Show \"What's New\" modal on login": "로그인시 \"새로운 기능\" 모달 보기",
 	"Show Admin Details in Account Pending Overlay": "사용자용 계정 보류 설명창에, 관리자 상세 정보 노출",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "단축키 보기",
 	"Show your support!": "당신의 응원을 보내주세요!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "스트림 채팅 응답",
 	"STT Model": "STT 모델",
 	"STT Settings": "STT 설정",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "자막 (예: 로마 황제)",
 	"Success": "성공",
 	"Successfully updated.": "성공적으로 업데이트되었습니다.",

src/lib/i18n/locales/lt-LT/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Užklausos rėžimas",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking modelis",
-	"Reranking model disabled": "Reranking modelis neleidžiamas",
-	"Reranking model set to \"{{reranking_model}}\"": "Nustatytas rereanking modelis: \"{{reranking_model}}\"",
 	"Reset": "Atkurti",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Atkurti įkėlimų direktoiją",
@@ -1069,6 +1068,8 @@
 	"Show": "Rodyti",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Rodyti administratoriaus duomenis laukiant paskyros patvirtinimo",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Rodyti trumpinius",
 	"Show your support!": "Palaikykite",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "STT modelis",
 	"STT Settings": "STT nustatymai",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtitras",
 	"Success": "Sėkmingai",
 	"Successfully updated.": "Sėkmingai atnaujinta.",

src/lib/i18n/locales/ms-MY/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Mod Permintaan",
+	"Reranking Engine": "",
 	"Reranking Model": "Model 'Reranking'",
-	"Reranking model disabled": "Model 'Reranking' dilumpuhkan",
-	"Reranking model set to \"{{reranking_model}}\"": "Model 'Reranking' ditetapkan kepada \"{{reranking_model}}\"",
 	"Reset": "Tetapkan Semula",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Tetapkan Semula Direktori Muat Naik",
@@ -1069,6 +1068,8 @@
 	"Show": "Tunjukkan",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Tunjukkan Butiran Pentadbir dalam Akaun Menunggu Tindanan",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Tunjukkan pintasan",
 	"Show your support!": "Tunjukkan sokongan anda!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "Model STT",
 	"STT Settings": "Tetapan STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Sari kata (cth tentang Kesultanan Melaka)",
 	"Success": "Berjaya",
 	"Successfully updated.": "Berjaya Dikemaskini",

src/lib/i18n/locales/nb-NO/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Gjenta straff (Ollama)",
 	"Reply in Thread": "Svar i tråd",
 	"Request Mode": "Forespørselsmodus",
+	"Reranking Engine": "",
 	"Reranking Model": "Omrangeringsmodell",
-	"Reranking model disabled": "Omrangeringsmodell deaktivert",
-	"Reranking model set to \"{{reranking_model}}\"": "Omrangeringsmodell er angitt til \"{{reranking_model}}\"",
 	"Reset": "Tilbakestill",
 	"Reset All Models": "Tilbakestill alle modeller",
 	"Reset Upload Directory": "Tilbakestill opplastingskatalog",
@@ -1069,6 +1068,8 @@
 	"Show": "Vis",
 	"Show \"What's New\" modal on login": "Vis \"Hva er nytt\"-modal ved innlogging",
 	"Show Admin Details in Account Pending Overlay": "Vis administratordetaljer i ventende kontovisning",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Vis snarveier",
 	"Show your support!": "Vis din støtte!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Strømme chat-svar",
 	"STT Model": "STT-modell",
 	"STT Settings": "STT-innstillinger",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Undertittel (f.eks. om romerriket)",
 	"Success": "Suksess",
 	"Successfully updated.": "Oppdatert.",

src/lib/i18n/locales/nl-NL/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Herhalingsstraf (Ollama)",
 	"Reply in Thread": "Antwoord in draad",
 	"Request Mode": "Request Modus",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking Model",
-	"Reranking model disabled": "Reranking model uitgeschakeld",
-	"Reranking model set to \"{{reranking_model}}\"": "Reranking model ingesteld op \"{{reranking_model}}\"",
 	"Reset": "Herstellen",
 	"Reset All Models": "Herstel alle modellen",
 	"Reset Upload Directory": "Herstel Uploadmap",
@@ -1069,6 +1068,8 @@
 	"Show": "Toon",
 	"Show \"What's New\" modal on login": "Toon \"Wat is nieuw\" bij inloggen",
 	"Show Admin Details in Account Pending Overlay": "Admin-details weergeven in overlay in afwachting van account",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Toon model",
 	"Show shortcuts": "Toon snelkoppelingen",
 	"Show your support!": "Toon je steun",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Stream chat-antwoord",
 	"STT Model": "STT Model",
 	"STT Settings": "STT Instellingen",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Ondertitel (bijv. over de Romeinse Empire)",
 	"Success": "Succes",
 	"Successfully updated.": "Succesvol bijgewerkt.",

src/lib/i18n/locales/pa-IN/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "ਬੇਨਤੀ ਮੋਡ",
+	"Reranking Engine": "",
 	"Reranking Model": "ਮਾਡਲ ਮੁੜ ਰੈਂਕਿੰਗ",
-	"Reranking model disabled": "ਮਾਡਲ ਮੁੜ ਰੈਂਕਿੰਗ ਅਯੋਗ ਕੀਤਾ ਗਿਆ",
-	"Reranking model set to \"{{reranking_model}}\"": "ਮਾਡਲ ਮੁੜ ਰੈਂਕਿੰਗ ਨੂੰ \"{{reranking_model}}\" 'ਤੇ ਸੈੱਟ ਕੀਤਾ ਗਿਆ",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "ਦਿਖਾਓ",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "ਸ਼ਾਰਟਕਟ ਦਿਖਾਓ",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "STT ਸੈਟਿੰਗਾਂ",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "ਉਪਸਿਰਲੇਖ (ਉਦਾਹਰਣ ਲਈ ਰੋਮਨ ਸਾਮਰਾਜ ਬਾਰੇ)",
 	"Success": "ਸਫਲਤਾ",
 	"Successfully updated.": "ਸਫਲਤਾਪੂਰਵਕ ਅੱਪਡੇਟ ਕੀਤਾ ਗਿਆ।",

src/lib/i18n/locales/pl-PL/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Powtórzona kara (Ollama)",
 	"Reply in Thread": "Odpowiedz w wątku",
 	"Request Mode": "Tryb żądania",
+	"Reranking Engine": "",
 	"Reranking Model": "Poprawa rankingu modelu",
-	"Reranking model disabled": "Ponowny ranking modeli wyłączony",
-	"Reranking model set to \"{{reranking_model}}\"": "Ponowny ranking modeli ustawiony na \"{{reranking_model}}\".",
 	"Reset": "Resetuj",
 	"Reset All Models": "Resetuj wszystkie modele",
 	"Reset Upload Directory": "Resetuj katalog pobierania",
@@ -1069,6 +1068,8 @@
 	"Show": "Wyświetl",
 	"Show \"What's New\" modal on login": "Wyświetl okno dialogowe \"What's New\" podczas logowania",
 	"Show Admin Details in Account Pending Overlay": "Wyświetl szczegóły administratora w okienu informacyjnym o potrzebie zatwierdzenia przez administratora konta użytkownika",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Wyświetl skróty",
 	"Show your support!": "Wyraź swoje poparcie!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Strumieniowanie odpowiedzi z czatu",
 	"STT Model": "Model STT",
 	"STT Settings": "Ustawienia STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Podtytuł (np. o Imperium Rzymskim)",
 	"Success": "Sukces",
 	"Successfully updated.": "Uaktualniono pomyślnie.",

src/lib/i18n/locales/pt-BR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Modo de Solicitação",
+	"Reranking Engine": "",
 	"Reranking Model": "Modelo de Reclassificação",
-	"Reranking model disabled": "Modelo de Reclassificação desativado",
-	"Reranking model set to \"{{reranking_model}}\"": "Modelo de Reclassificação definido como \"{{reranking_model}}\"",
 	"Reset": "Redefinir",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Redefinir Diretório de Upload",
@@ -1069,6 +1068,8 @@
 	"Show": "Mostrar",
 	"Show \"What's New\" modal on login": "Mostrar \"O que há de Novo\" no login",
 	"Show Admin Details in Account Pending Overlay": "Mostrar Detalhes do Administrador na Sobreposição de Conta Pendentes",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Mostrar atalhos",
 	"Show your support!": "Mostre seu apoio!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Stream Resposta do Chat",
 	"STT Model": "Modelo STT",
 	"STT Settings": "Configurações STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtítulo (por exemplo, sobre o Império Romano)",
 	"Success": "Sucesso",
 	"Successfully updated.": "Atualizado com sucesso.",

src/lib/i18n/locales/pt-PT/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Modo de Pedido",
+	"Reranking Engine": "",
 	"Reranking Model": "Modelo de Reranking",
-	"Reranking model disabled": "Modelo de Reranking desativado",
-	"Reranking model set to \"{{reranking_model}}\"": "Modelo de Reranking definido como \"{{reranking_model}}\"",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Limpar Pasta de Carregamento",
@@ -1069,6 +1068,8 @@
 	"Show": "Mostrar",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Mostrar Detalhes do Administrador na sobreposição de Conta Pendente",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Mostrar atalhos",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "Modelo STT",
 	"STT Settings": "Configurações STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtítulo (ex.: sobre o Império Romano)",
 	"Success": "Sucesso",
 	"Successfully updated.": "Atualizado com sucesso.",

src/lib/i18n/locales/ro-RO/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Mod de Cerere",
+	"Reranking Engine": "",
 	"Reranking Model": "Model de Rearanjare",
-	"Reranking model disabled": "Modelul de Rearanjare este dezactivat",
-	"Reranking model set to \"{{reranking_model}}\"": "Modelul de Rearanjare setat la \"{{reranking_model}}\"",
 	"Reset": "Resetează",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Resetează Directorul de Încărcare",
@@ -1069,6 +1068,8 @@
 	"Show": "Afișează",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Afișează Detaliile Administratorului în Suprapunerea Contului În Așteptare",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Afișează scurtături",
 	"Show your support!": "Arată-ți susținerea!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Răspuns Stream Chat",
 	"STT Model": "Model STT",
 	"STT Settings": "Setări STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Subtitlu (de ex. despre Imperiul Roman)",
 	"Success": "Succes",
 	"Successfully updated.": "Actualizat cu succes.",

src/lib/i18n/locales/ru-RU/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Повторить наказание (Ollama)",
 	"Reply in Thread": "Ответить в обсуждении",
 	"Request Mode": "Режим запроса",
+	"Reranking Engine": "",
 	"Reranking Model": "Модель реранжирования",
-	"Reranking model disabled": "Модель реранжирования отключена",
-	"Reranking model set to \"{{reranking_model}}\"": "Модель реранжирования установлена на \"{{reranking_model}}\"",
 	"Reset": "Сбросить",
 	"Reset All Models": "Сбросить все модели",
 	"Reset Upload Directory": "Сбросить каталог загрузок",
@@ -1069,6 +1068,8 @@
 	"Show": "Показать",
 	"Show \"What's New\" modal on login": "Показывать окно «Что нового» при входе в систему",
 	"Show Admin Details in Account Pending Overlay": "Показывать данные администратора в оверлее ожидающей учетной записи",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Показать модель",
 	"Show shortcuts": "Показать горячие клавиши",
 	"Show your support!": "Поддержите нас!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Потоковый вывод ответа",
 	"STT Model": "Модель распознавания речи",
 	"STT Settings": "Настройки распознавания речи",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Подзаголовок (напр., о Римской империи)",
 	"Success": "Успех",
 	"Successfully updated.": "Успешно обновлено.",

src/lib/i18n/locales/sk-SK/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Režim žiadosti",
+	"Reranking Engine": "",
 	"Reranking Model": "Model na prehodnotenie poradia",
-	"Reranking model disabled": "Model na prehodnotenie poradia je deaktivovaný",
-	"Reranking model set to \"{{reranking_model}}\"": "Model na prehodnotenie poradia nastavený na \"{{reranking_model}}\"",
 	"Reset": "režim Reset",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Resetovať adresár nahrávania",
@@ -1069,6 +1068,8 @@
 	"Show": "Zobraziť",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Zobraziť podrobnosti administrátora v prekryvnom okne s čakajúcim účtom",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Zobraziť klávesové skratky",
 	"Show your support!": "Vyjadrite svoju podporu!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Odozva chatu Stream",
 	"STT Model": "Model rozpoznávania reči na text (STT)",
 	"STT Settings": "Nastavenia STT (Rozpoznávanie reči)",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Titulky (napr. o Rímskej ríši)",
 	"Success": "Úspech",
 	"Successfully updated.": "Úspešne aktualizované.",

src/lib/i18n/locales/sr-RS/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Режим захтева",
+	"Reranking Engine": "",
 	"Reranking Model": "Модел поновног рангирања",
-	"Reranking model disabled": "Модел поновног рангирања онемогућен",
-	"Reranking model set to \"{{reranking_model}}\"": "Модел поновног рангирања подешен на \"{{reranking_model}}\"",
 	"Reset": "Поврати",
 	"Reset All Models": "Поврати све моделе",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "Прикажи",
 	"Show \"What's New\" modal on login": "Прикажи \"Погледај шта је ново\" прозорче при пријави",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Прикажи пречице",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "STT модел",
 	"STT Settings": "STT подешавања",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Поднаслов (нпр. о Римском царству)",
 	"Success": "Успех",
 	"Successfully updated.": "Успешно ажурирано.",

src/lib/i18n/locales/sv-SE/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "Frågeläge",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking modell",
-	"Reranking model disabled": "Reranking modell inaktiverad",
-	"Reranking model set to \"{{reranking_model}}\"": "Reranking modell inställd på \"{{reranking_model}}\"",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "Återställ uppladdningskatalog",
@@ -1069,6 +1068,8 @@
 	"Show": "Visa",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "Visa administratörsinformation till väntande konton",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Visa genvägar",
 	"Show your support!": "Visa ditt stöd!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "Tal-till-text-modell",
 	"STT Settings": "Tal-till-text-inställningar",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Undertext (t.ex. om Romerska Imperiet)",
 	"Success": "Framgång",
 	"Successfully updated.": "Uppdaterades framgångsrikt.",

src/lib/i18n/locales/th-TH/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "โหมดคำขอ",
+	"Reranking Engine": "",
 	"Reranking Model": "จัดอันดับใหม่โมเดล",
-	"Reranking model disabled": "ปิดการใช้งานโมเดลการจัดอันดับใหม่",
-	"Reranking model set to \"{{reranking_model}}\"": "ตั้งค่าโมเดลการจัดอันดับใหม่เป็น \"{{reranking_model}}\"",
 	"Reset": "รีเซ็ต",
 	"Reset All Models": "",
 	"Reset Upload Directory": "รีเซ็ตไดเร็กทอรีการอัปโหลด",
@@ -1069,6 +1068,8 @@
 	"Show": "แสดง",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "แสดงรายละเอียดผู้ดูแลระบบในหน้าจอรอการอนุมัติบัญชี",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "แสดงทางลัด",
 	"Show your support!": "แสดงการสนับสนุนของคุณ!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "โมเดลแปลงเสียงเป็นข้อความ",
 	"STT Settings": "การตั้งค่าแปลงเสียงเป็นข้อความ",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "คำบรรยาย (เช่น เกี่ยวกับจักรวรรดิโรมัน)",
 	"Success": "สำเร็จ",
 	"Successfully updated.": "อัปเดตเรียบร้อยแล้ว",

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

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "",
+	"Reranking Engine": "",
 	"Reranking Model": "",
-	"Reranking model disabled": "",
-	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
 	"Reset All Models": "",
 	"Reset Upload Directory": "",
@@ -1069,6 +1068,8 @@
 	"Show": "",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "",
 	"Show your support!": "",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "",
 	"STT Model": "",
 	"STT Settings": "",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
 	"Success": "",
 	"Successfully updated.": "",

src/lib/i18n/locales/tr-TR/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "Konuya Yanıtla",
 	"Request Mode": "İstek Modu",
+	"Reranking Engine": "",
 	"Reranking Model": "Yeniden Sıralama Modeli",
-	"Reranking model disabled": "Yeniden sıralama modeli devre dışı bırakıldı",
-	"Reranking model set to \"{{reranking_model}}\"": "Yeniden sıralama modeli \"{{reranking_model}}\" olarak ayarlandı",
 	"Reset": "Sıfırla",
 	"Reset All Models": "Tüm Modelleri Sıfırla",
 	"Reset Upload Directory": "Yükleme Dizinini Sıfırla",
@@ -1069,6 +1068,8 @@
 	"Show": "Göster",
 	"Show \"What's New\" modal on login": "Girişte \"Yenilikler\" modalını göster",
 	"Show Admin Details in Account Pending Overlay": "Yönetici Ayrıntılarını Hesap Bekliyor Ekranında Göster",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "Kısayolları göster",
 	"Show your support!": "Desteğinizi gösterin!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "SAkış Sohbet Yanıtı",
 	"STT Model": "STT Modeli",
 	"STT Settings": "STT Ayarları",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Alt başlık (örn. Roma İmparatorluğu hakkında)",
 	"Success": "Başarılı",
 	"Successfully updated.": "Başarıyla güncellendi.",

src/lib/i18n/locales/uk-UA/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Штраф за повторення (Ollama)",
 	"Reply in Thread": "Відповісти в потоці",
 	"Request Mode": "Режим запиту",
+	"Reranking Engine": "",
 	"Reranking Model": "Модель переранжування",
-	"Reranking model disabled": "Модель переранжування вимкнена",
-	"Reranking model set to \"{{reranking_model}}\"": "Модель переранжування встановлено на \"{{reranking_model}}\"",
 	"Reset": "Скидання",
 	"Reset All Models": "Скинути усі моделі",
 	"Reset Upload Directory": "Скинути каталог завантажень",
@@ -1069,6 +1068,8 @@
 	"Show": "Показати",
 	"Show \"What's New\" modal on login": "Показати модальне вікно \"Що нового\" під час входу",
 	"Show Admin Details in Account Pending Overlay": "Відобразити дані адміна у вікні очікування облікового запису",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Показати модель",
 	"Show shortcuts": "Показати клавіатурні скорочення",
 	"Show your support!": "Підтримайте нас!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Відповідь стрім-чату",
 	"STT Model": "Модель STT ",
 	"STT Settings": "Налаштування STT",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Підзаголовок (напр., про Римську імперію)",
 	"Success": "Успіх",
 	"Successfully updated.": "Успішно оновлено.",

src/lib/i18n/locales/ur-PK/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "",
 	"Reply in Thread": "",
 	"Request Mode": "درخواست کا موڈ",
+	"Reranking Engine": "",
 	"Reranking Model": "دوبارہ درجہ بندی کا ماڈل",
-	"Reranking model disabled": "دوبارہ درجہ بندی کا ماڈل غیر فعال کر دیا گیا",
-	"Reranking model set to \"{{reranking_model}}\"": "دوبارہ درجہ بندی کا ماڈل \"{{reranking_model}}\" پر مقرر کر دیا گیا ہے",
 	"Reset": "ری سیٹ",
 	"Reset All Models": "",
 	"Reset Upload Directory": "اپلوڈ ڈائریکٹری کو ری سیٹ کریں",
@@ -1069,6 +1068,8 @@
 	"Show": "دکھائیں",
 	"Show \"What's New\" modal on login": "",
 	"Show Admin Details in Account Pending Overlay": "اکاؤنٹ پینڈنگ اوورلے میں ایڈمن کی تفصیلات دکھائیں",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "",
 	"Show shortcuts": "شارٹ کٹ دکھائیں",
 	"Show your support!": "اپنی حمایت دکھائیں!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "اسٹریم چیٹ جواب",
 	"STT Model": "ایس ٹی ٹی ماڈل",
 	"STT Settings": "ایس ٹی ٹی ترتیبات",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "ذیلی عنوان (جیسے رومن سلطنت کے بارے میں)",
 	"Success": "کامیابی",
 	"Successfully updated.": "کامیابی سے تازہ کاری ہو گئی",

src/lib/i18n/locales/vi-VN/translation.json

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "Hình phạt Lặp lại (Ollama)",
 	"Reply in Thread": "Trả lời trong Luồng",
 	"Request Mode": "Chế độ Yêu cầu",
+	"Reranking Engine": "",
 	"Reranking Model": "Reranking Model",
-	"Reranking model disabled": "Đã tắt mô hình reranking",
-	"Reranking model set to \"{{reranking_model}}\"": "Reranking model được đặt thành \"{{reranking_model}}\"",
 	"Reset": "Xóa toàn bộ",
 	"Reset All Models": "Đặt lại Tất cả Mô hình",
 	"Reset Upload Directory": "Xóa toàn bộ thư mục Upload",
@@ -1069,6 +1068,8 @@
 	"Show": "Hiển thị",
 	"Show \"What's New\" modal on login": "Hiển thị cửa sổ \"Có gì mới\" khi đăng nhập",
 	"Show Admin Details in Account Pending Overlay": "Hiển thị thông tin của Quản trị viên trên màn hình hiển thị Tài khoản đang chờ xử lý",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "Hiển thị Mô hình",
 	"Show shortcuts": "Hiển thị phím tắt",
 	"Show your support!": "Thể hiện sự ủng hộ của bạn!",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "Truyền trực tiếp Phản hồi Chat",
 	"STT Model": "Mô hình STT",
 	"STT Settings": "Cài đặt Nhận dạng Giọng nói",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "Phụ đề (ví dụ: về Đế chế La Mã)",
 	"Success": "Thành công",
 	"Successfully updated.": "Đã cập nhật thành công.",

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

@@ -105,7 +105,7 @@
 	"Are you sure you want to delete this channel?": "是否确认删除此频道？",
 	"Are you sure you want to delete this message?": "是否确认删除此消息？",
 	"Are you sure you want to unarchive all archived chats?": "是否确认取消所有已归档的对话？",
-	"Are you sure you want to update this user's role to **{{ROLE}}**?": "",
+	"Are you sure you want to update this user's role to **{{ROLE}}**?": "您确定要将此用户的角色更新为 **{{ROLE}}** 吗？",
 	"Are you sure?": "是否确定？",
 	"Arena Models": "启用竞技场匿名评价模型",
 	"Artifacts": "Artifacts",
@@ -148,7 +148,7 @@
 	"Bing Search V7 Subscription Key": "Bing 搜索 V7 订阅密钥",
 	"Bocha Search API Key": "Bocha Search API 密钥",
 	"Boosting or penalizing specific tokens for constrained responses. Bias values will be clamped between -100 and 100 (inclusive). (Default: none)": "为受限响应提升或惩罚特定标记。偏置值将被限制在 -100 到 100（包括两端）之间。（默认：无）",
-	"Both Docling OCR Engine and Language(s) must be provided or both left empty.": "",
+	"Both Docling OCR Engine and Language(s) must be provided or both left empty.": "必须提供 Docling OCR Engine 和语言，或者都留空。",
 	"Brave Search API Key": "Brave Search API 密钥",
 	"By {{name}}": "由 {{name}} 提供",
 	"Bypass Embedding and Retrieval": "绕过嵌入和检索",
@@ -159,7 +159,7 @@
 	"Cancel": "取消",
 	"Capabilities": "能力",
 	"Capture": "截图",
-	"Capture Audio": "",
+	"Capture Audio": "录制音频",
 	"Certificate Path": "证书路径",
 	"Change Password": "更改密码",
 	"Channel Name": "频道名称",
@@ -269,8 +269,8 @@
 	"Create Knowledge": "创建知识",
 	"Create new key": "创建新密钥",
 	"Create new secret key": "创建新安全密钥",
-	"Create Note": "",
+	"Create Note": "创建笔记",
-	"Create your first note by clicking on the plus button below.": "",
+	"Create your first note by clicking on the plus button below.": "单击下面的加号按钮创建您的第一个笔记。",
 	"Created at": "创建于",
 	"Created At": "创建于",
 	"Created by": "作者",
@@ -308,7 +308,7 @@
 	"Delete function?": "删除函数？",
 	"Delete Message": "删除消息",
 	"Delete message?": "删除消息？",
-	"Delete note?": "",
+	"Delete note?": "删除笔记？",
 	"Delete prompt?": "删除提示词？",
 	"delete this link": "此处删除这个链接",
 	"Delete tool?": "删除工具？",
@@ -364,7 +364,7 @@
 	"Download Database": "下载数据库",
 	"Drag and drop a file to upload or select a file to view": "拖动文件上传或选择文件查看",
 	"Draw": "平局",
-	"Drop any files here to upload": "",
+	"Drop any files here to upload": "将任何文件拖放到此处进行上传",
 	"e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.": "例如 '30s'，'10m'。有效的时间单位是秒：'s'，分：'m'，时：'h'。",
 	"e.g. \"json\" or a JSON schema": "例如 \"json\" 或一个 JSON schema",
 	"e.g. 60": "例如 '60'",
@@ -374,7 +374,7 @@
 	"e.g. my_filter": "例如：my_filter",
 	"e.g. my_tools": "例如：my_tools",
 	"e.g. Tools for performing various operations": "例如：用于执行各种操作的工具",
-	"e.g., 3, 4, 5 (leave blank for default)": "",
+	"e.g., 3, 4, 5 (leave blank for default)": "例如：3、4、5（留空为默认值）",
 	"e.g., en-US,ja-JP (leave blank for auto-detect)": "例如，'en-US,ja-JP'（留空以便自动检测）",
 	"e.g., westus (leave blank for eastus)": "",
 	"Edit": "编辑",
@@ -406,7 +406,7 @@
 	"Enabled": "启用",
 	"Endpoint URL": "",
 	"Enforce Temporary Chat": "强制临时聊天",
-	"Enhance": "",
+	"Enhance": "增强",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "确保您的 CSV 文件按以下顺序包含 4 列： 姓名、电子邮箱、密码、角色。",
 	"Enter {{role}} message here": "在此处输入 {{role}} 的对话内容",
 	"Enter a detail about yourself for your LLMs to recall": "输入一个关于你自己的详细信息，方便你的大语言模型记住这些内容",
@@ -423,8 +423,8 @@
 	"Enter Chunk Size": "输入块大小 (Chunk Size)",
 	"Enter comma-separated \"token:bias_value\" pairs (example: 5432:100, 413:-100)": "输入以逗号分隔的“token:bias_value”对（例如：5432:100, 413:-100）",
 	"Enter description": "输入简介描述",
-	"Enter Docling OCR Engine": "",
+	"Enter Docling OCR Engine": "输入 Docling OCR Engine",
-	"Enter Docling OCR Language(s)": "",
+	"Enter Docling OCR Language(s)": "输入 Docling OCR 语言",
 	"Enter Docling Server URL": "输入 Docling 服务器 URL",
 	"Enter Document Intelligence Endpoint": "输入 Document Intelligence 端点",
 	"Enter Document Intelligence Key": "输入 Document Intelligence 密钥",
@@ -451,7 +451,7 @@
 	"Enter Model ID": "输入模型 ID",
 	"Enter model tag (e.g. {{modelTag}})": "输入模型标签 (例如：{{modelTag}})",
 	"Enter Mojeek Search API Key": "输入 Mojeek Search API 密钥",
-	"Enter New Password": "",
+	"Enter New Password": "输入新密码",
 	"Enter Number of Steps (e.g. 50)": "输入步骤数 (Steps) (例如：50)",
 	"Enter Perplexity API Key": "输入 Perplexity API 密钥",
 	"Enter Playwright Timeout": "输入 Playwright 超时时间",
@@ -488,15 +488,15 @@
 	"Enter Top K Reranker": "输入 Top K Reranker",
 	"Enter URL (e.g. http://127.0.0.1:7860/)": "输入地址 (例如：http://127.0.0.1:7860/)",
 	"Enter URL (e.g. http://localhost:11434)": "输入地址 (例如：http://localhost:11434)",
-	"Enter Yacy Password": "",
+	"Enter Yacy Password": "输入 Yacy 密码",
-	"Enter Yacy URL (e.g. http://yacy.example.com:8090)": "",
+	"Enter Yacy URL (e.g. http://yacy.example.com:8090)": "输入 Yacy URL（例如：http://yacy.example.com:8090）",
-	"Enter Yacy Username": "",
+	"Enter Yacy Username": "输入 Yacy 用户名",
 	"Enter your current password": "输入当前密码",
 	"Enter Your Email": "输入您的电子邮箱",
 	"Enter Your Full Name": "输入您的名称",
 	"Enter your message": "输入您的消息",
 	"Enter your name": "输入您的名称",
-	"Enter Your Name": "",
+	"Enter Your Name": "输入你的名称",
 	"Enter your new password": "输入新的密码",
 	"Enter Your Password": "输入您的密码",
 	"Enter Your Role": "输入您的权限组",
@@ -505,8 +505,8 @@
 	"Error": "错误",
 	"ERROR": "错误",
 	"Error accessing Google Drive: {{error}}": "访问 Google 云端硬盘 出错： {{error}}",
-	"Error accessing media devices.": "",
+	"Error accessing media devices.": "访问媒体设备时出错。",
-	"Error starting recording.": "",
+	"Error starting recording.": "开始录制时出错。",
 	"Error uploading file: {{error}}": "上传文件时出错： {{error}}",
 	"Evaluations": "竞技场评估",
 	"Exa API Key": "Exa API 密钥",
@@ -545,7 +545,7 @@
 	"Failed to add file.": "添加文件失败。",
 	"Failed to connect to {{URL}} OpenAPI tool server": "无法连接到 {{URL}} OpenAPI 工具服务器",
 	"Failed to create API Key.": "无法创建 API 密钥。",
-	"Failed to delete note": "",
+	"Failed to delete note": "删除笔记失败",
 	"Failed to fetch models": "无法获取模型",
 	"Failed to load file content.": "无法加载文件内容。",
 	"Failed to read clipboard contents": "无法读取剪贴板内容",
@@ -603,12 +603,12 @@
 	"Gemini API Config": "Gemini API 配置",
 	"Gemini API Key is required.": "需要 Gemini API 密钥。",
 	"General": "通用",
-	"Generate": "",
+	"Generate": "生成",
 	"Generate an image": "生成图像",
 	"Generate Image": "生成图像",
 	"Generate prompt pair": "生成提示对",
 	"Generating search query": "生成搜索查询",
-	"Generating...": "",
+	"Generating...": "生成中...",
 	"Get started": "开始使用",
 	"Get started with {{WEBUI_NAME}}": "开始使用 {{WEBUI_NAME}}",
 	"Global": "全局",
@@ -655,7 +655,7 @@
 	"Import Config from JSON File": "导入 JSON 文件中的配置信息",
 	"Import Functions": "导入函数",
 	"Import Models": "导入模型",
-	"Import Notes": "",
+	"Import Notes": "导入笔记",
 	"Import Presets": "导入预设",
 	"Import Prompts": "导入提示词",
 	"Import Tools": "导入工具",
@@ -670,7 +670,7 @@
 	"Instant Auto-Send After Voice Transcription": "语音转录文字后即时自动发送",
 	"Integration": "集成",
 	"Interface": "界面",
-	"Invalid file content": "",
+	"Invalid file content": "无效的文件内容",
 	"Invalid file format.": "无效文件格式。",
 	"Invalid JSON schema": "无效的 JSON schema",
 	"Invalid Tag": "无效标签",
@@ -741,7 +741,7 @@
 	"Manage Pipelines": "管理 Pipeline",
 	"Manage Tool Servers": "管理工具服务器",
 	"March": "三月",
-	"Max Speakers": "",
+	"Max Speakers": "最大扬声器数量",
 	"Max Tokens (num_predict)": "最大 Token 数量 (num_predict)",
 	"Max Upload Count": "最大上传数量",
 	"Max Upload Size": "最大上传大小",
@@ -793,16 +793,16 @@
 	"Mojeek Search API Key": "Mojeek Search API 密钥",
 	"more": "更多",
 	"More": "更多",
-	"My Notes": "",
+	"My Notes": "我的笔记",
 	"Name": "名称",
 	"Name your knowledge base": "为您的知识库命名",
 	"Native": "原生",
 	"New Chat": "新对话",
 	"New Folder": "新文件夹",
-	"New Note": "",
+	"New Note": "新笔记",
 	"New Password": "新密码",
 	"new-channel": "新频道",
-	"No content": "",
+	"No content": "没有内容",
 	"No content found": "未发现内容",
 	"No content found in file.": "文件中未找到内容",
 	"No content to speak": "没有内容可朗读",
@@ -817,7 +817,7 @@
 	"No model IDs": "没有模型 ID",
 	"No models found": "未找到任何模型",
 	"No models selected": "未选择任何模型",
-	"No Notes": "",
+	"No Notes": "没有笔记",
 	"No results found": "未找到结果",
 	"No search query generated": "未生成搜索查询",
 	"No source available": "没有可用来源",
@@ -826,7 +826,7 @@
 	"None": "无",
 	"Not factually correct": "事实并非如此",
 	"Not helpful": "无帮助",
-	"Note deleted successfully": "",
+	"Note deleted successfully": "笔记删除成功",
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "注意：如果设置了最低分数，搜索只会返回分数大于或等于最低分数的文档。",
 	"Notes": "笔记",
 	"Notification Sound": "通知提示音",
@@ -849,7 +849,7 @@
 	"Only alphanumeric characters and hyphens are allowed": "只允许使用英文字母，数字 (0-9) 以及连字符 (-)",
 	"Only alphanumeric characters and hyphens are allowed in the command string.": "命令字符串中只允许使用英文字母，数字 (0-9) 以及连字符 (-)。",
 	"Only collections can be edited, create a new knowledge base to edit/add documents.": "只能编辑文件集，创建一个新的知识库来编辑/添加文件。",
-	"Only markdown files are allowed": "",
+	"Only markdown files are allowed": "仅允许使用 markdown 文件",
 	"Only select users and groups with permission can access": "只有具有权限的用户和组才能访问",
 	"Oops! Looks like the URL is invalid. Please double-check and try again.": "此链接似乎为无效链接。请检查后重试。",
 	"Oops! There are files still uploading. Please wait for the upload to complete.": "稍等！还有文件正在上传。请等待上传完成。",
@@ -895,8 +895,8 @@
 	"Pipelines": "Pipeline",
 	"Pipelines Not Detected": "未检测到 Pipeline",
 	"Pipelines Valves": "Pipeline 值",
-	"Plain text (.md)": "",
+	"Plain text (.md)": "纯文本文档（.md）",
-	"Plain text (.txt)": "TXT 文档 (.txt)",
+	"Plain text (.txt)": "纯文本文档 (.txt)",
 	"Playground": "AI 对话游乐场",
 	"Playwright Timeout (ms)": "Playwright 超时时间 (ms)",
 	"Playwright WebSocket URL": "Playwright WebSocket URL",
@@ -938,7 +938,7 @@
 	"Read": "只读",
 	"Read Aloud": "朗读",
 	"Reasoning Effort": "推理努力",
-	"Record": "",
+	"Record": "录制",
 	"Record voice": "录音",
 	"Redirecting you to Open WebUI Community": "正在将您重定向到 OpenWebUI 社区",
 	"Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative.": "降低生成无意义内容的概率。较高的值（如100）将产生更多样化的回答，而较低的值（如10）则更加保守。",
@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "重复惩罚 (Ollama)",
 	"Reply in Thread": "在主题中回复",
 	"Request Mode": "请求模式",
+	"Reranking Engine": "",
 	"Reranking Model": "重排模型",
-	"Reranking model disabled": "重排模型已禁用",
-	"Reranking model set to \"{{reranking_model}}\"": "重排模型设置为 \"{{reranking_model}}\"",
 	"Reset": "重置",
 	"Reset All Models": "重置所有模型",
 	"Reset Upload Directory": "重置上传目录",
@@ -1008,7 +1007,7 @@
 	"Searched {{count}} sites": "已搜索 {{count}} 个网站",
 	"Searching \"{{searchQuery}}\"": "搜索 \"{{searchQuery}}\" 中",
 	"Searching Knowledge for \"{{searchQuery}}\"": "检索有关 \"{{searchQuery}}\" 的知识中",
-	"Searching the web...": "",
+	"Searching the web...": "正在搜索网络...",
 	"Searxng Query URL": "Searxng 查询 URL",
 	"See readme.md for instructions": "查看 readme.md 以获取说明",
 	"See what's new": "查阅最新更新内容",
@@ -1069,6 +1068,8 @@
 	"Show": "显示",
 	"Show \"What's New\" modal on login": "在登录时显示“更新内容”弹窗",
 	"Show Admin Details in Account Pending Overlay": "在用户待激活界面中显示管理员邮箱等详细信息",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "显示模型",
 	"Show shortcuts": "显示快捷方式",
 	"Show your support!": "表达你的支持！",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "以流式返回对话响应",
 	"STT Model": "语音转文本模型",
 	"STT Settings": "语音转文本设置",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "副标题（例如：关于罗马帝国的副标题）",
 	"Success": "成功",
 	"Successfully updated.": "成功更新。",
@@ -1211,7 +1213,7 @@
 	"Unpin": "取消置顶",
 	"Unravel secrets": "解开秘密",
 	"Untagged": "无标签",
-	"Untitled": "",
+	"Untitled": "无标题",
 	"Update": "更新",
 	"Update and Copy Link": "更新和复制链接",
 	"Update for the latest features and improvements.": "更新来获得最新功能与改进。",
@@ -1222,7 +1224,7 @@
 	"Upgrade to a licensed plan for enhanced capabilities, including custom theming and branding, and dedicated support.": "升级到授权计划以获得增强功能，包括自定义主题与品牌以及专属支持。",
 	"Upload": "上传",
 	"Upload a GGUF model": "上传一个 GGUF 模型",
-	"Upload Audio": "",
+	"Upload Audio": "上传音频",
 	"Upload directory": "上传目录",
 	"Upload files": "上传文件",
 	"Upload Files": "上传文件",
@@ -1296,9 +1298,9 @@
 	"Write a summary in 50 words that summarizes [topic or keyword].": "用 50 个字写一个总结 [主题或关键词]。",
 	"Write something...": "单击以键入内容...",
 	"Write your model template content here": "在此写入模型模板内容",
-	"Yacy Instance URL": "",
+	"Yacy Instance URL": "Yacy Instance URL",
-	"Yacy Password": "",
+	"Yacy Password": "Yacy 密码",
-	"Yacy Username": "",
+	"Yacy Username": "Yacy 用户名",
 	"Yesterday": "昨天",
 	"You": "你",
 	"You are currently using a trial license. Please contact support to upgrade your license.": "当前为试用许可证，请联系支持人员升级许可证。",

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

@@ -959,9 +959,8 @@
 	"Repeat Penalty (Ollama)": "重複懲罰 (Ollama)",
 	"Reply in Thread": "在討論串中回覆",
 	"Request Mode": "請求模式",
+	"Reranking Engine": "",
 	"Reranking Model": "重新排序模型",
-	"Reranking model disabled": "已停用重新排序模型",
-	"Reranking model set to \"{{reranking_model}}\"": "重新排序模型已設定為 \"{{reranking_model}}\"",
 	"Reset": "重設",
 	"Reset All Models": "重設所有模型",
 	"Reset Upload Directory": "重設上傳目錄",
@@ -1069,6 +1068,8 @@
 	"Show": "顯示",
 	"Show \"What's New\" modal on login": "登入時顯示「新功能」對話框",
 	"Show Admin Details in Account Pending Overlay": "在帳號待審覆蓋層中顯示管理員詳細資訊",
+	"Show All": "",
+	"Show Less": "",
 	"Show Model": "顯示模型",
 	"Show shortcuts": "顯示快捷鍵",
 	"Show your support!": "表達您的支持！",
@@ -1092,6 +1093,7 @@
 	"Stream Chat Response": "串流式對話回應",
 	"STT Model": "語音轉文字 (STT) 模型",
 	"STT Settings": "語音轉文字 (STT) 設定",
+	"Stylized PDF Export": "",
 	"Subtitle (e.g. about the Roman Empire)": "副標題（例如：關於羅馬帝國）",
 	"Success": "成功",
 	"Successfully updated.": "更新成功。",

src/lib/utils/marked/katex-extension.ts

@@ -10,6 +10,10 @@ const DELIMITER_LIST = [
 	{ left: '\\begin{equation}', right: '\\end{equation}', display: true }
 ];
 
+// Defines characters that are allowed to immediately precede or follow a math delimiter.
+const ALLOWED_SURROUNDING_CHARS =
+	'\\s?。，、；!-\\/:-@\\[-`{-~\\p{Script=Han}\\p{Script=Hiragana}\\p{Script=Katakana}\\p{Script=Hangul}';
+
 // const DELIMITER_LIST = [
 //     { left: '$$', right: '$$', display: false },
 //     { left: '$', right: '$', display: false },
@@ -44,10 +48,13 @@ function generateRegexRules(delimiters) {
 
 	// Math formulas can end in special characters
 	const inlineRule = new RegExp(
-		`^(${inlinePatterns.join('|')})(?=[\\s?。，!-\/:-@[-\`{-~]|$)`,
+		`^(${inlinePatterns.join('|')})(?=[${ALLOWED_SURROUNDING_CHARS}]|$)`,
+		'u'
+	);
+	const blockRule = new RegExp(
+		`^(${blockPatterns.join('|')})(?=[${ALLOWED_SURROUNDING_CHARS}]|$)`,
 		'u'
 	);
-	const blockRule = new RegExp(`^(${blockPatterns.join('|')})(?=[\\s?。，!-\/:-@[-\`{-~]|$)`, 'u');
 
 	return { inlineRule, blockRule };
 }
@@ -91,7 +98,9 @@ function katexStart(src, displayMode: boolean) {
 
 		// Check if the delimiter is preceded by a special character.
 		// If it does, then it's potentially a math formula.
-		const f = index === 0 || indexSrc.charAt(index - 1).match(/[\s?。，!-\/:-@[-`{-~]/);
+		const f =
+			index === 0 ||
+			indexSrc.charAt(index - 1).match(new RegExp(`[${ALLOWED_SURROUNDING_CHARS}]`, 'u'));
 		if (f) {
 			const possibleKatex = indexSrc.substring(index);
 

src/lib/utils/onedrive-file-picker.ts

@@ -6,6 +6,7 @@ class OneDriveConfig {
 	private static instance: OneDriveConfig;
 	private clientId: string = '';
 	private sharepointUrl: string = '';
+	private sharepointTenantId: string = '';
 	private msalInstance: PublicClientApplication | null = null;
 	private currentAuthorityType: 'personal' | 'organizations' = 'personal';
 
@@ -48,6 +49,7 @@ class OneDriveConfig {
 
 		const newClientId = config.onedrive?.client_id;
 		const newSharepointUrl = config.onedrive?.sharepoint_url;
+		const newSharepointTenantId = config.onedrive?.sharepoint_tenant_id;
 
 		if (!newClientId) {
 			throw new Error('OneDrive configuration is incomplete');
@@ -55,6 +57,7 @@ class OneDriveConfig {
 
 		this.clientId = newClientId;
 		this.sharepointUrl = newSharepointUrl;
+		this.sharepointTenantId = newSharepointTenantId;
 	}
 
 	public async getMsalInstance(
@@ -64,7 +67,9 @@ class OneDriveConfig {
 
 		if (!this.msalInstance) {
 			const authorityEndpoint =
-				this.currentAuthorityType === 'organizations' ? 'common' : 'consumers';
+				this.currentAuthorityType === 'organizations'
+					? this.sharepointTenantId || 'common'
+					: 'consumers';
 			const msalParams = {
 				auth: {
 					authority: `https://login.microsoftonline.com/${authorityEndpoint}`,
@@ -89,6 +94,10 @@ class OneDriveConfig {
 		return this.sharepointUrl;
 	}
 
+	public getSharepointTenantId(): string {
+		return this.sharepointTenantId;
+	}
+
 	public getBaseUrl(): string {
 		if (this.currentAuthorityType === 'organizations') {
 			if (!this.sharepointUrl || this.sharepointUrl === '') {

src/routes/+layout.svelte

@@ -48,7 +48,6 @@
 	import NotificationToast from '$lib/components/NotificationToast.svelte';
 	import AppSidebar from '$lib/components/app/AppSidebar.svelte';
 	import { chatCompletion } from '$lib/apis/openai';
-	import { setupSocket } from '$lib/utils/websocket';
 
 	setContext('i18n', i18n);
 
@@ -59,6 +58,53 @@
 
 	const BREAKPOINT = 768;
 
+	const setupSocket = async (enableWebsocket) => {
+		const _socket = io(`${WEBUI_BASE_URL}` || undefined, {
+			reconnection: true,
+			reconnectionDelay: 1000,
+			reconnectionDelayMax: 5000,
+			randomizationFactor: 0.5,
+			path: '/ws/socket.io',
+			transports: enableWebsocket ? ['websocket'] : ['polling', 'websocket'],
+			auth: { token: localStorage.token }
+		});
+
+		await socket.set(_socket);
+
+		_socket.on('connect_error', (err) => {
+			console.log('connect_error', err);
+		});
+
+		_socket.on('connect', () => {
+			console.log('connected', _socket.id);
+		});
+
+		_socket.on('reconnect_attempt', (attempt) => {
+			console.log('reconnect_attempt', attempt);
+		});
+
+		_socket.on('reconnect_failed', () => {
+			console.log('reconnect_failed');
+		});
+
+		_socket.on('disconnect', (reason, details) => {
+			console.log(`Socket ${_socket.id} disconnected due to ${reason}`);
+			if (details) {
+				console.log('Additional details:', details);
+			}
+		});
+
+		_socket.on('user-list', (data) => {
+			console.log('user-list', data);
+			activeUserIds.set(data.user_ids);
+		});
+
+		_socket.on('usage', (data) => {
+			console.log('usage', data);
+			USAGE_POOL.set(data['models']);
+		});
+	};
+
 	const executePythonAsWorker = async (id, code, cb) => {
 		let result = null;
 		let stdout = null;
@@ -515,6 +561,8 @@
 			await WEBUI_NAME.set(backendConfig.name);
 
 			if ($config) {
+				await setupSocket($config.features?.enable_websocket ?? true);
+
 				const currentUrl = `${window.location.pathname}${window.location.search}`;
 				const encodedUrl = encodeURIComponent(currentUrl);
 
@@ -526,7 +574,6 @@
 					});
 
 					if (sessionUser) {
-						await setupSocket($config.features?.enable_websocket ?? true);
 						// Save Session User to Store
 						$socket.emit('user-join', { auth: { token: sessionUser.token } });
 

src/routes/auth/+page.svelte

@@ -12,7 +12,6 @@
 	import { WEBUI_NAME, config, user, socket } from '$lib/stores';
 
 	import { generateInitialsImage, canvasPixelTest } from '$lib/utils';
-	import { setupSocket } from '$lib/utils/websocket';
 
 	import Spinner from '$lib/components/common/Spinner.svelte';
 	import OnBoarding from '$lib/components/OnBoarding.svelte';
@@ -42,10 +41,6 @@
 			if (sessionUser.token) {
 				localStorage.token = sessionUser.token;
 			}
-			if (!$socket) {
-				await setupSocket($config.features?.enable_websocket ?? true);
-			}
-
 			$socket.emit('user-join', { auth: { token: sessionUser.token } });
 			await user.set(sessionUser);
 			await config.set(await getBackendConfig());
@@ -188,7 +183,7 @@
 						crossorigin="anonymous"
 						src="{WEBUI_BASE_URL}/static/splash.png"
 						class=" w-6 rounded-full"
-						alt="logo"
+						alt=""
 					/>
 				</div>
 			</div>
@@ -235,7 +230,7 @@
 								</div>
 
 								{#if $config?.onboarding ?? false}
-									<div class=" mt-1 text-xs font-medium text-gray-500">
+									<div class="mt-1 text-xs font-medium text-gray-600 dark:text-gray-500">
 										ⓘ {$WEBUI_NAME}
 										{$i18n.t(
 											'does not make any external connections, and your data stays securely on your locally hosted server.'
@@ -248,10 +243,13 @@
 								<div class="flex flex-col mt-4">
 									{#if mode === 'signup'}
 										<div class="mb-2">
-											<div class=" text-sm font-medium text-left mb-1">{$i18n.t('Name')}</div>
+											<label for="name" class="text-sm font-medium text-left mb-1 block"
+												>{$i18n.t('Name')}</label
+											>
 											<input
 												bind:value={name}
 												type="text"
+												id="name"
 												class="my-0.5 w-full text-sm outline-hidden bg-transparent"
 												autocomplete="name"
 												placeholder={$i18n.t('Enter Your Full Name')}
@@ -262,23 +260,29 @@
 
 									{#if mode === 'ldap'}
 										<div class="mb-2">
-											<div class=" text-sm font-medium text-left mb-1">{$i18n.t('Username')}</div>
+											<label for="username" class="text-sm font-medium text-left mb-1 block"
+												>{$i18n.t('Username')}</label
+											>
 											<input
 												bind:value={ldapUsername}
 												type="text"
 												class="my-0.5 w-full text-sm outline-hidden bg-transparent"
 												autocomplete="username"
 												name="username"
+												id="username"
 												placeholder={$i18n.t('Enter Your Username')}
 												required
 											/>
 										</div>
 									{:else}
 										<div class="mb-2">
-											<div class=" text-sm font-medium text-left mb-1">{$i18n.t('Email')}</div>
+											<label for="email" class="text-sm font-medium text-left mb-1 block"
+												>{$i18n.t('Email')}</label
+											>
 											<input
 												bind:value={email}
 												type="email"
+												id="email"
 												class="my-0.5 w-full text-sm outline-hidden bg-transparent"
 												autocomplete="email"
 												name="email"
@@ -289,11 +293,13 @@
 									{/if}
 
 									<div>
-										<div class=" text-sm font-medium text-left mb-1">{$i18n.t('Password')}</div>
+										<label for="password" class="text-sm font-medium text-left mb-1 block"
-
+											>{$i18n.t('Password')}</label
+										>
 										<input
 											bind:value={password}
 											type="password"
+											id="password"
 											class="my-0.5 w-full text-sm outline-hidden bg-transparent"
 											placeholder={$i18n.t('Enter Your Password')}
 											autocomplete="current-password"

src/tailwind.css

@@ -24,7 +24,7 @@
 	html,
 	pre {
 		font-family: -apple-system, BlinkMacSystemFont, 'Inter', ui-sans-serif, system-ui, 'Segoe UI',
-			Roboto, Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Helvetica Neue', Arial,
+			Roboto, Ubuntu, Cantarell, 'Vazirmatn', 'Noto Sans', sans-serif, 'Helvetica Neue', Arial,
 			'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
 	}