📄️ Function Calling
Checking if a model supports function calling
📄️ Web Search
Use web search with litellm
📄️ 網頁搜尋攔截
Enable transparent server-side web search execution for any LLM provider. LiteLLM automatically intercepts web search tool calls and executes them using your configured search provider (Perplexity, Tavily, etc.).
📄️ Web Fetch
The web fetch tool allows LLMs to retrieve full content from specified web pages and PDF documents. This enables AI models to access real-time information from the internet and incorporate web content into their responses.
📄️ Computer Use
Computer use allows models to interact with computer interfaces by taking screenshots and performing actions like clicking, typing, and scrolling. This enables AI models to autonomously operate desktop environments.
📄️ Code Interpreter
Use OpenAI's Code Interpreter tool to execute Python code in a secure, sandboxed environment.
📄️ 程式碼解譯器沙箱攔截
Run model-generated code inside an isolated sandbox and get its output back. The API is provider-agnostic; e2b and opensandbox are supported backends, talked to directly over HTTPS with no extra SDK dependency.
📄️ Advisor Tool
Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation.
📄️ Message Sanitization for Tool Calling for anthropic models
Automatically fix common message formatting issues when using tool calling with modify_params=True