Merge pull request open-webui#9190 from open-webui/dev

0.5.8

Author: tjbck

CHANGELOG.md

@@ -5,6 +5,35 @@ 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).
 
+## [0.5.8] - 2025-02-05
+
+### Added
+
+- **🖥️ Code Interpreter**: Models can now execute code in real time to refine their answers dynamically, running securely within a sandboxed browser environment using Pyodide. Perfect for calculations, data analysis, and AI-assisted coding tasks!
+- **💬 Redesigned Chat Input UI**: Enjoy a sleeker and more intuitive message input with improved feature selection, making it easier than ever to toggle tools, enable search, and interact with AI seamlessly.
+- **🛠️ Native Tool Calling Support (Experimental)**: Supported models can now call tools natively, reducing query latency and improving contextual responses. More enhancements coming soon!
+- **🔗 Exa Search Engine Integration**: A new search provider has been added, allowing users to retrieve up-to-date and relevant information without leaving the chat interface.
+- **🌍 Localized Dates & Times**: Date and time formats now match your system locale, ensuring a more natural, region-specific experience.
+- **📎 User Headers for External Embedding APIs**: API calls to external embedding services now include user-related headers.
+- **🌍 "Always On" Web Search Toggle**: A new option under Settings > Interface allows users to enable Web Search by default—transform Open WebUI into your go-to search engine, ensuring AI-powered results with every query.
+- **🚀 General Performance & Stability**: Significant improvements across the platform for a faster, more reliable experience.
+- **🖼️ UI/UX Enhancements**: Numerous design refinements improving readability, responsiveness, and accessibility.
+- **🌍 Improved Translations**: Chinese, Korean, French, Ukrainian and Serbian translations have been updated with refined terminologies for better clarity.
+
+### Fixed
+
+- **🔄 OAuth Name Field Fallback**: Resolves OAuth login failures by using the email field as a fallback when a name is missing.
+- **🔑 Google Drive Credentials Restriction**: Ensures only authenticated users can access Google Drive credentials for enhanced security.
+- **🌐 DuckDuckGo Search Rate Limit Handling**: Fixes issues where users would encounter 202 errors due to rate limits when using DuckDuckGo for web search.
+- **📁 File Upload Permission Indicator**: Users are now notified when they lack permission to upload files, improving clarity on system restrictions.
+- **🔧 Max Tokens Issue**: Fixes cases where 'max_tokens' were not applied correctly, ensuring proper model behavior.
+- **🔍 Validation for RAG Web Search URLs**: Filters out invalid or unsupported URLs when using web-based retrieval augmentation.
+- **🖋️ Title Generation Bug**: Fixes inconsistencies in title generation, ensuring proper chat organization.
+
+### Removed
+
+- **⚡ Deprecated Non-Web Worker Pyodide Execution**: Moves entirely to browser sandboxing for better performance and security.
+
 ## [0.5.7] - 2025-01-23
 
 ### Added

backend/open_webui/config.py

@@ -927,6 +927,12 @@ def oidc_oauth_register(client):
     == "true"
 )
 
+USER_PERMISSIONS_FEATURES_CODE_INTERPRETER = (
+    os.environ.get("USER_PERMISSIONS_FEATURES_CODE_INTERPRETER", "True").lower()
+    == "true"
+)
+
+
 DEFAULT_USER_PERMISSIONS = {
     "workspace": {
         "models": USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS,
@@ -944,6 +950,7 @@ def oidc_oauth_register(client):
     "features": {
         "web_search": USER_PERMISSIONS_FEATURES_WEB_SEARCH,
         "image_generation": USER_PERMISSIONS_FEATURES_IMAGE_GENERATION,
+        "code_interpreter": USER_PERMISSIONS_FEATURES_CODE_INTERPRETER,
     },
 }
 
@@ -1094,21 +1101,27 @@ class BannerModel(BaseModel):
     os.environ.get("TITLE_GENERATION_PROMPT_TEMPLATE", ""),
 )
 
-DEFAULT_TITLE_GENERATION_PROMPT_TEMPLATE = """Create a concise, 3-5 word title with an emoji as a title for the chat history, in the given language. Suitable Emojis for the summary can be used to enhance understanding but avoid quotation marks or special formatting. RESPOND ONLY WITH THE TITLE TEXT.
-
-Examples of titles:
-📉 Stock Market Trends
-🍪 Perfect Chocolate Chip Recipe
-Evolution of Music Streaming
-Remote Work Productivity Tips
-Artificial Intelligence in Healthcare
-🎮 Video Game Development Insights
-
+DEFAULT_TITLE_GENERATION_PROMPT_TEMPLATE = """### Task:
+Generate a concise, 3-5 word title with an emoji summarizing the chat history.
+### Guidelines:
+- The title should clearly represent the main theme or subject of the conversation.
+- 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.
+### Output:
+JSON format: { "title": "your concise title here" }
+### Examples:
+- { "title": "📉 Stock Market Trends" },
+- { "title": "🍪 Perfect Chocolate Chip Recipe" },
+- { "title": "Evolution of Music Streaming" },
+- { "title": "Remote Work Productivity Tips" },
+- { "title": "Artificial Intelligence in Healthcare" },
+- { "title": "🎮 Video Game Development Insights" }
+### Chat History:
 <chat_history>
 {{MESSAGES:END:2}}
 </chat_history>"""
 
-
 TAGS_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
     "TAGS_GENERATION_PROMPT_TEMPLATE",
     "task.tags.prompt_template",
@@ -1277,7 +1290,28 @@ class BannerModel(BaseModel):
 )
 
 
-DEFAULT_TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = """Available Tools: {{TOOLS}}\nReturn an empty string if no tools match the query. If a function tool matches, construct and return a JSON object in the format {\"name\": \"functionName\", \"parameters\": {\"requiredFunctionParamKey\": \"requiredFunctionParamValue\"}} using the appropriate tool and its parameters. Only return the object and limit the response to the JSON object without additional text."""
+DEFAULT_TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = """Available Tools: {{TOOLS}}
+
+Your task is to choose and return the correct tool(s) from the list of available tools based on the query. Follow these guidelines:
+
+- Return only the JSON object, without any additional text or explanation.
+
+- If no tools match the query, return an empty array: 
+   {
+     "tool_calls": []
+   }
+
+- If one or more tools match the query, construct a JSON response containing a "tool_calls" array with objects that include:
+   - "name": The tool's name.
+   - "parameters": A dictionary of required parameters and their corresponding values.
+
+The format for the JSON response is strictly:
+{
+  "tool_calls": [
+    {"name": "toolName1", "parameters": {"key1": "value1"}},
+    {"name": "toolName2", "parameters": {"key2": "value2"}}
+  ]
+}"""
 
 
 DEFAULT_EMOJI_GENERATION_PROMPT_TEMPLATE = """Your task is to reflect the speaker's likely facial expression through a fitting emoji. Interpret emotions from the message and reflect their facial expression using fitting, diverse emojis (e.g., 😊, 😢, 😡, 😱).
@@ -1290,6 +1324,24 @@ class BannerModel(BaseModel):
 
 Responses from models: {{responses}}"""
 
+
+DEFAULT_CODE_INTERPRETER_PROMPT = """
+#### Tools Available
+
+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.
+   - 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.  
+   - If a link is provided for an image, audio, or any file, include it in the response exactly as given to ensure the user has access to the original resource.  
+   - All responses should be communicated in the chat's primary language, ensuring seamless understanding. If the chat is multilingual, default to English for clarity.
+   - **If a link to an image, audio, or any file is provided in markdown format, explicitly display it as part of the response to ensure the user can access it easily, do NOT change the link.**
+
+Ensure that the tools are effectively utilized to achieve the highest-quality analysis for the user."""
+
+
 ####################################
 # Vector Database
 ####################################
@@ -1319,6 +1371,7 @@ class BannerModel(BaseModel):
 
 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)
 
 # Qdrant
 QDRANT_URI = os.environ.get("QDRANT_URI", None)
@@ -1699,6 +1752,11 @@ class BannerModel(BaseModel):
     os.environ.get("BING_SEARCH_V7_SUBSCRIPTION_KEY", ""),
 )
 
+EXA_API_KEY = PersistentConfig(
+    "EXA_API_KEY",
+    "rag.web.search.exa_api_key",
+    os.getenv("EXA_API_KEY", ""),
+)
 
 RAG_WEB_SEARCH_RESULT_COUNT = PersistentConfig(
     "RAG_WEB_SEARCH_RESULT_COUNT",

backend/open_webui/constants.py

@@ -57,7 +57,7 @@ def __str__(self) -> str:
     )
 
     FILE_NOT_SENT = "FILE_NOT_SENT"
-    FILE_NOT_SUPPORTED = "Oops! It seems like the file format you're trying to upload is not supported. Please upload a file with a supported format (e.g., JPG, PNG, PDF, TXT) and try again."
+    FILE_NOT_SUPPORTED = "Oops! It seems like the file format you're trying to upload is not supported. Please upload a file with a supported format and try again."
 
     NOT_FOUND = "We could not find what you're looking for :/"
     USER_NOT_FOUND = "We could not find what you're looking for :/"

backend/open_webui/env.py

@@ -356,14 +356,22 @@ def parse_section(section):
     ),  # DEPRECATED: remove at next major version
 )
 
-WEBUI_SESSION_COOKIE_SAME_SITE = os.environ.get(
-    "WEBUI_SESSION_COOKIE_SAME_SITE",
-    os.environ.get("WEBUI_SESSION_COOKIE_SAME_SITE", "lax"),
+WEBUI_SESSION_COOKIE_SAME_SITE = os.environ.get("WEBUI_SESSION_COOKIE_SAME_SITE", "lax")
+
+WEBUI_SESSION_COOKIE_SECURE = (
+    os.environ.get("WEBUI_SESSION_COOKIE_SECURE", "false").lower() == "true"
+)
+
+WEBUI_AUTH_COOKIE_SAME_SITE = os.environ.get(
+    "WEBUI_AUTH_COOKIE_SAME_SITE", WEBUI_SESSION_COOKIE_SAME_SITE
 )
 
-WEBUI_SESSION_COOKIE_SECURE = os.environ.get(
-    "WEBUI_SESSION_COOKIE_SECURE",
-    os.environ.get("WEBUI_SESSION_COOKIE_SECURE", "false").lower() == "true",
+WEBUI_AUTH_COOKIE_SECURE = (
+    os.environ.get(
+        "WEBUI_AUTH_COOKIE_SECURE",
+        os.environ.get("WEBUI_SESSION_COOKIE_SECURE", "false"),
+    ).lower()
+    == "true"
 )
 
 if WEBUI_AUTH and WEBUI_SECRET_KEY == "":

backend/open_webui/main.py

@@ -177,6 +177,7 @@
     BING_SEARCH_V7_ENDPOINT,
     BING_SEARCH_V7_SUBSCRIPTION_KEY,
     BRAVE_SEARCH_API_KEY,
+    EXA_API_KEY,
     KAGI_SEARCH_API_KEY,
     MOJEEK_SEARCH_API_KEY,
     GOOGLE_PSE_API_KEY,
@@ -523,6 +524,7 @@ async def lifespan(app: FastAPI):
 app.state.config.JINA_API_KEY = JINA_API_KEY
 app.state.config.BING_SEARCH_V7_ENDPOINT = BING_SEARCH_V7_ENDPOINT
 app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY = BING_SEARCH_V7_SUBSCRIPTION_KEY
+app.state.config.EXA_API_KEY = EXA_API_KEY
 
 app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = RAG_WEB_SEARCH_RESULT_COUNT
 app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = RAG_WEB_SEARCH_CONCURRENT_REQUESTS
@@ -859,6 +861,7 @@ async def chat_completion(
         if model_id not in request.app.state.MODELS:
             raise Exception("Model not found")
         model = request.app.state.MODELS[model_id]
+        model_info = Models.get_model_by_id(model_id)
 
         # Check if user has access to the model
         if not BYPASS_MODEL_ACCESS_CONTROL and user.role == "user":
@@ -875,12 +878,25 @@ async def chat_completion(
             "tool_ids": form_data.get("tool_ids", None),
             "files": form_data.get("files", None),
             "features": form_data.get("features", None),
+            "variables": form_data.get("variables", None),
+            "model": model_info,
+            **(
+                {"function_calling": "native"}
+                if form_data.get("params", {}).get("function_calling") == "native"
+                or (
+                    model_info
+                    and model_info.params.model_dump().get("function_calling")
+                    == "native"
+                )
+                else {}
+            ),
         }
         form_data["metadata"] = metadata
 
-        form_data, events = await process_chat_payload(
+        form_data, metadata, events = await process_chat_payload(
             request, form_data, metadata, user, model
         )
+
     except Exception as e:
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
@@ -889,6 +905,7 @@ async def chat_completion(
 
     try:
         response = await chat_completion_handler(request, form_data, user)
+
         return await process_chat_response(
             request, response, form_data, user, events, metadata, tasks
         )
@@ -1007,10 +1024,6 @@ async def get_app_config(request: Request):
                 else {}
             ),
         },
-        "google_drive": {
-            "client_id": GOOGLE_DRIVE_CLIENT_ID.value,
-            "api_key": GOOGLE_DRIVE_API_KEY.value,
-        },
         **(
             {
                 "default_models": app.state.config.DEFAULT_MODELS,
@@ -1030,6 +1043,10 @@ async def get_app_config(request: Request):
                     "max_count": app.state.config.FILE_MAX_COUNT,
                 },
                 "permissions": {**app.state.config.USER_PERMISSIONS},
+                "google_drive": {
+                    "client_id": GOOGLE_DRIVE_CLIENT_ID.value,
+                    "api_key": GOOGLE_DRIVE_API_KEY.value,
+                },
             }
             if user is not None
             else {}
@@ -1063,7 +1080,7 @@ async def get_app_version():
 
 
 @app.get("/api/version/updates")
-async def get_app_latest_release_version():
+async def get_app_latest_release_version(user=Depends(get_verified_user)):
     if OFFLINE_MODE:
         log.debug(
             f"Offline mode is enabled, returning current version as latest version"