RAGFlex

RAGFlex is a flexible Retrieval Augmented Generation (RAG) framework that allows you to configure pipeline with hydra configuration files with FastAPI as the backend and flutter as the frontend.

Features

• Configure RAG pipeline with hydra configuration files
• Use FastAPI as the backend
• Use flutter as the frontend

Quick look

Getting started

Setup with conda

# Create a new conda environment
conda env create -f environment.yml

# Activate the environment
conda activate ragflex

Start the backend

cd python

# If you are using the default openai api configuration
OPENAI_API_KEY=$OPENAI_API_KEY python fastapi_main.py

Start the frontend

cd flutter

# Run as a web server
flutter run -d web-server --web-hostname=0.0.0.0