https://github.com/joshmusira/rag_application

A state-of-the-art Retrieval-Augmented Generation (RAG) application using OpenAI, Qdrant vector store, embeddings, FastAPI, React for the UI, NewsAPI, Word Cloud, and Langchain. This project enables dynamic reading and QA on news articles, focusing on various people of interest, with real-time, personalized news insights.
https://github.com/joshmusira/rag_application

embeddings-word2vec fastapi langchain-python openai qdrant-vector-database reactjs wordcloud

Last synced: 4 days ago
JSON representation

A state-of-the-art Retrieval-Augmented Generation (RAG) application using OpenAI, Qdrant vector store, embeddings, FastAPI, React for the UI, NewsAPI, Word Cloud, and Langchain. This project enables dynamic reading and QA on news articles, focusing on various people of interest, with real-time, personalized news insights.

• Host: GitHub
• URL: https://github.com/joshmusira/rag_application
• Owner: JoshMusira
• Created: 2024-06-20T17:30:44.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-07-19T11:57:47.000Z (6 months ago)
• Last Synced: 2024-11-15T14:08:11.574Z (2 months ago)
• Topics: embeddings-word2vec, fastapi, langchain-python, openai, qdrant-vector-database, reactjs, wordcloud
• Language: Python
• Homepage:
• Size: 34.2 MB
• Stars: 1
• Watchers: 3
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# RAG Fullstack Application

This repository contains the full-stack implementation for the RAG (Retrieve, Answer, Generate) application. It provides a web interface and backend API to interact with a language model, perform keyword extraction, and generate word clouds based on retrieved information.

## Features

- **Frontend**: Built with React to provide an interactive web interface.

- **Backend**: Developed using FastAPI to handle API requests.

- **Vector Store**: Utilizes Qdrant for vector storage and retrieval.

- **Language Model**: Powered by OpenAI's GPT-3.5-turbo for generating answers.

- **Keyword Extraction**: Uses TF-IDF vectorization to extract keywords from text responses.

- **Word Cloud Generation**: Creates visual representations of word frequency using extracted keywords.

## Requirements

- Python 3.12

- Node.js and npm

- Qdrant

- OpenAI API Key (set as environment variable `OPENAI_API_KEY`)

### Contribute

1. Clone the repository:

   ```bash

   git clone https://github.com//RAG-Fullstack-Backend.git

   cd RAG-Fullstack-Backend