deepseek-ai/deepseek-recipe

English | 中文 deepseek-recipe is a collection of Rust libraries and Python bindings that uniformly convert API requests in different formats into the Conversation format, render conversations into prompts for DeepSeek models, encode conversations into token IDs with an attached tokenizer, and convert model output into responses in the corresponding format. Use these components to connect an inference backend to API services that support multiple formats. The caller must provide model inference, tool execution, and HTTP transport. Getting started · Streaming response · Use with tokenizer · License Responses requests, Streaming response, and complete responses. Supports text, images, thinking mode, client tool calls, and Chat Completions prefix continuation. encoding of conversations into token IDs with an attached tokenizer. topp, and output token limits. After the caller encodes the prompt, ConversationRequest::resolvemaxtokens checks the prompt and maxtokens against the context limit and supplies the maxtokens default when the request sets none: 8192…