Skip to content

8Opt/ReWOO-with-Graph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ReWOO-with-Graph

Clean code, clear mind, solutions you'll find.

Introduction

This project aims to re-factor the implementation of the original ReWOO's setting into graph-based design. In addtion, the project evaluate the performance of ReWOO based on the bigbench and SOTU dataset.

Why's ReWOO, you might ask? There are several factors that make ReWOO stands out:

  1. Reduce token consumption.
  2. Reduce execution time.
  3. Fine-tuning does not affect the whole system

Features

  • Graph-based implementation of ReWOO.
  • Evaluation with Ragas.

Stack of Tech

  • Lang-'s ecosystem: LangChain and LangGraph.
  • Tavily Search.
  • Groq.
  • Ollama.
  • RAGAs.

Getting started

Set up environment

  1. Create .env file.
  2. Get api key from Tavily, and Groq.

Note: For those who want to use Gemini or Ollama, make sure to get those API keys and install the relevant packages.

Clone the repo and install requirements

    git clone https://github.com/8Opt/ReWOO-with-Graph.git
    cd ReWOO-with-Graph
    pip install -r requirements.txt

Ready to use

All informtion of using the code is well-instructed in the /assets/notebooks.

Notes

About

Building ReWOO using LangGraph

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published