diff --git a/docs/features/chat-features/code-execution/python.md b/docs/features/chat-features/code-execution/python.md index c2a2a05c4..dbb0ef818 100644 --- a/docs/features/chat-features/code-execution/python.md +++ b/docs/features/chat-features/code-execution/python.md @@ -58,9 +58,15 @@ When using **Native function calling mode** with a capable model (e.g., GPT-5, C - **Same image handling**: Base64 image URLs in output are replaced with file URLs; model embeds via markdown **Requirements:** -1. `ENABLE_CODE_INTERPRETER` must be enabled globally -2. Model must have `code_interpreter` capability enabled -3. Model must use **Native** function calling mode (set in model's advanced params) +1. Code Interpreter enabled globally at **Admin Panel > Settings > Code Execution** +2. **Builtin Tools** capability ON for the model (in **Admin Panel > Settings > Models > Capabilities**) +3. Model must have `code_interpreter` capability enabled (in **Admin Panel > Settings > Models > Capabilities**) +4. Model must use **Native** function calling mode (set in model's advanced params) +5. **Code Interpreter toggle** must be ON in the chat interface + +:::tip Enabling Code Interpreter by Default +Go to **Admin Panel > Settings > Models**, select a model, and scroll to **Default Features**. Toggle on **Code Interpreter** so it's pre-enabled for new chats with this model. +::: For more details on builtin tools and native mode, see the [Tool Development Guide](/features/plugin/tools/development#built-in-system-tools-nativeagentic-mode). diff --git a/docs/features/image-generation-and-editing/usage.md b/docs/features/image-generation-and-editing/usage.md index aea079cc5..461b61f55 100644 --- a/docs/features/image-generation-and-editing/usage.md +++ b/docs/features/image-generation-and-editing/usage.md @@ -20,13 +20,18 @@ If your model is configured with **Native Function Calling** (see the [**Central ### How it works: - **Requirements**: - **Image Generation** must be enabled globally in **Admin Panel → Settings → Images** - - The model must have the **Image Generation** capability enabled -- **No Chat Toggle Needed**: With Native Mode, the `generate_image` tool is automatically included when the model has the `image_generation` capability. You don't need to manually toggle it on per chat. + - **Builtin Tools** capability must be enabled for the model (in **Admin Panel > Settings > Models > Capabilities**) + - The model must have the **Image Generation** capability enabled (in **Admin Panel > Settings > Models > Capabilities**) + - **Image Generation toggle** must be ON in the chat interface - **Natural Language**: You can simply ask the model: *"Generate an image of a cybernetic forest."* -- **Action**: If **Native Mode** is active and the model has the capability, it will invoke the `generate_image` tool. +- **Action**: If **Native Mode** is active and all conditions are met, it will invoke the `generate_image` tool. - **Display**: The generated image is displayed directly in the chat interface. - **Editing**: This also supports **Image Editing** (inpainting) via the `edit_image` tool (e.g., *"Make the sky in this image red"*). +:::tip Enabling Image Generation by Default +Go to **Admin Panel > Settings > Models**, select a model, and scroll to **Default Features**. Toggle on **Image Generation** so it's pre-enabled for new chats with this model. +::: + This approach allows the model to "reason" about the prompt before generating, or even generate multiple images as part of a complex request. diff --git a/docs/features/plugin/tools/index.mdx b/docs/features/plugin/tools/index.mdx index 89d0caa0d..3ba21f616 100644 --- a/docs/features/plugin/tools/index.mdx +++ b/docs/features/plugin/tools/index.mdx @@ -150,20 +150,20 @@ These models excel at multi-step reasoning, proper JSON formatting, and autonomo | Tool | Purpose | |------|---------| -| **Search & Web** | *Requires `ENABLE_WEB_SEARCH` enabled.* | -| `search_web` | Search the public web for information. Best for current events, external references, or topics not covered in internal documents. | +| **Search & Web** | | +| `search_web` | *Requires `ENABLE_WEB_SEARCH` + model `web_search` capability + chat toggle ON.* – Search the public web for information. Best for current events, external references, or topics not covered in internal documents. | | `fetch_url` | Visits a URL and extracts text content via the Web Loader. | | **Knowledge Base** | *Always available.* | | `list_knowledge_bases` | List the user's accessible knowledge bases with file counts. | -| `query_knowledge_bases` | Search knowledge bases by semantic similarity to query. Finds KBs whose name/description match the meaning of your query. Use this to discover relevant knowledge bases before querying their files. | +| `query_knowledge_bases` | Search knowledge bases by semantic similarity to query. Use this to discover relevant knowledge bases before querying their files. | | `search_knowledge_bases` | Search knowledge bases by name and description. | | `query_knowledge_files` | Search knowledge base files using simple vector search. **Note:** Does not use hybrid search or reranking—for full RAG pipeline with reranking, use File Context instead by attaching files via `#` or assigning knowledge bases. | | `search_knowledge_files` | Search files across accessible knowledge bases by filename. | | `view_knowledge_file` | Get the full content of a file from a knowledge base. | -| **Image Gen** | *Requires image generation enabled (per-tool).* | +| **Image Gen** | *Requires image generation enabled + model `image_generation` capability + chat toggle ON (per-tool).* | | `generate_image` | Generates a new image based on a prompt. Requires `ENABLE_IMAGE_GENERATION`. | -| `edit_image` | Edits existing images based on a prompt and image URLs. Requires `ENABLE_IMAGE_EDIT`. | -| **Memory** | *Requires Memory feature enabled.* | +| `edit_image` | Edits an existing image based on a prompt and URL. Requires `ENABLE_IMAGE_EDIT`. | +| **Memory** | *Requires Memory feature enabled globally and for the user.* | | `search_memories` | Searches the user's personal memory/personalization bank. | | `add_memory` | Stores a new fact in the user's personalization memory. | | `replace_memory_content` | Updates an existing memory record by its unique ID. | @@ -174,7 +174,7 @@ These models excel at multi-step reasoning, proper JSON formatting, and autonomo | `replace_note_content` | Update an existing note's content or title. | | **Chat History** | *Always available.* | | `search_chats` | Simple text search across chat titles and message content. Returns matching chat IDs and snippets. | -| `view_chat` | Reads and returns the full message history of a specific chat by ID. | +| `view_chat` | Retrieve the full message history of a specific previous chat. | | **Channels** | *Requires `ENABLE_CHANNELS` enabled.* | | `search_channels` | Find public or accessible channels by name/description. | | `search_channel_messages` | Search for specific messages inside accessible channels. | @@ -218,6 +218,19 @@ These models excel at multi-step reasoning, proper JSON formatting, and autonomo Open WebUI automatically detects and stores your timezone when you log in. This allows time-related tools and features to provide accurate local times without any manual configuration. Your timezone is determined from your browser settings. ::: +:::tip Four-Layer Tool Control +Feature-specific tools (Web Search, Image Generation, Code Interpreter) require **all four conditions** to be met: + +1. **Feature enabled globally** (e.g., **Admin Panel > Settings > Web Search / Code Execution / Images**) +2. **Builtin Tools** capability ON for the model +3. **Feature-specific capability** ON for the model (e.g., `web_search`) +4. **Chat toggle** enabled for the feature + +**Enabling Features by Default:** +- **Admins:** Go to **Admin Panel > Settings > Models**, select a model, and scroll to **Default Features**. Toggle on the desired features so they're pre-enabled for new chats. +- **Users:** Go to **Settings > Interface** and set **Web Search** to **Always**. +::: + :::tip Knowledge Base Tools vs RAG Pipeline The native `query_knowledge_files` tool uses **simple vector search** with a default of 5 results. It does **not** use: - Hybrid search (BM25 + vector) diff --git a/docs/features/web-search/agentic-search.mdx b/docs/features/web-search/agentic-search.mdx index 5f9f39cbd..74b7ba471 100644 --- a/docs/features/web-search/agentic-search.mdx +++ b/docs/features/web-search/agentic-search.mdx @@ -35,12 +35,18 @@ To unlock these features, your model must support native tool calling and have s * In the same model settings, under **Advanced Parameters**, set **Function Calling** to `Native`. 4. **Use a Quality Model**: Ensure you're using a frontier model with strong reasoning capabilities for best results. -:::tip Model Capability vs. Chat Toggle -In **Native Mode**, the `search_web` and `fetch_url` tools are automatically included based on the model's `web_search` capability setting. The chat toggle is not required. - -In **Default Mode** (non-native), the chat toggle still controls whether web search is performed via RAG-style injection. - -**Important**: If you disable the `web_search` capability on a model but use Native Mode, the tools won't be available even if you manually toggle Web Search on in the chat. +:::tip Four-Layer Tool Control +In **Native Mode**, the `search_web` tool requires **all four conditions** to be met: +1. **Feature enabled globally**: Web Search enabled at **Admin Panel > Settings > Web Search** +2. **Builtin Tools** capability ON for the model (in **Admin Panel > Settings > Models > Capabilities**) +3. **Model capability**: `web_search` capability ON (in **Admin Panel > Settings > Models > Capabilities**) +4. **Chat toggle**: Web Search toggle ON in the chat interface + +This gives both admins and users fine-grained control. Inlet filters can also programmatically control tool availability by modifying `body["features"]`—see the [Filter Development Guide](/features/plugin/functions/filter) for details. + +**Enabling Web Search by Default:** +- **Admins:** Go to **Admin Panel > Settings > Models**, select a model, and scroll to **Default Features**. Toggle on **Web Search** so it's pre-enabled for all new chats with this model. +- **Users:** Go to **Settings > Interface** and set **Web Search** to **Always**. ::: ## How Native Tools Handle Data (Agentic Mode)