Implementing my own LLM API

[westlongtime]

how to bulid AgentKit without using api? I want to load my local LLM

[Holmeswww]

LLM_API_FUNCTION can be any LLM API function that takes msg:list and shrink_idx:int, and outputs llm_result:str and usage:dict. Where msg is a prompt (OpenAI format by default), and shrink_idx:int is an index at which the LLM should reduce the length of the prompt in case of overflow.

You can write your custom LLM function by extending or following the format of https://github.com/Holmeswww/AgentKit/blob/main/src/agentkit/llm_api/base.py