llm_based_agent

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

llm_based_agent

★ 12 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# llm_based_agent

Python implementations of some of the fundamental LLM based Agent method from scratch, like CoT, ReAct, etc.

The purpose of this project is to understand the core methods of agent development using Python, without relying on frameworks like Langchain.

## Table of Contents

Currently, we are only these four methods:

| Method | Link | 
|:-------|:-------------:|
| CoT  | [code](lec1_cot.ipynb)    |
| Self-Refine  | [code](lec2_self_refine.ipynb)    | 
| Plan and Execute  | [code](lec3_plan_and_execute.ipynb)    | 
| tools  | [code1](lec4_tool1.ipynb) ,[code2](lec4_tool2.ipynb), [code3](lec4_tool3.ipynb)   | 
| P&E with tool | [code1](lec5_plan_and_execute_with_tool_execute.ipynb), [code2](lec5_plan_and_execute_with_tool_plan.ipynb)    | 
| React  | [code](lec6_react.ipynb)    |

## Use

Currently, we're only using DeepSeek as the LLM, so you first needs your own API key. If you have an OpenAI key, you can
also follow [llm_based_agent_from_scratch](https://github.com/MessyLab/llm_based_agent_from_scratch)

llm_based_agent

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README