RAGBOT
Real-time Chat Interface with React and RAG from scratch
Listed in categories:
TechGitHubArtificial Intelligence


Description
RAGBot is a fullstack application that combines a React frontend with a FastAPI backend to create a powerful real-time chat interface. The system leverages a custom-built Retrieval-Augmented Generation (RAG) pipeline for efficient document retrieval and query answering.
How to use RAGBOT?
To get started, clone the repository, create a virtual environment, and install the backend and frontend dependencies. Start the backend FastAPI server and the frontend React development server to begin using the application.
Core features of RAGBOT:
1️⃣
File Upload: Allows users to upload documents easily to the backend.
2️⃣
Document Chunking: Automatically splits documents into smaller manageable chunks for more efficient processing and analysis.
3️⃣
Embedding Generation: Uses transformer models to compute high-quality embeddings for each document chunk.
4️⃣
Similarity Search: Enables querying of document chunks and returns the most relevant ones based on cosine similarity with the input query.
5️⃣
Database Integration: Uses SQLite and SQLAlchemy for storing file metadata, chunk data, and processing status.
Why could be used RAGBOT?
# | Use case | Status | |
---|---|---|---|
# 1 | Users can interact with the LLM by typing queries in the chat interface. | ✅ | |
# 2 | Users can upload documents which will be processed and stored for future retrieval. | ✅ | |
# 3 | The system allows for efficient search through a collection of documents. | ✅ |
Who developed RAGBOT?
The project is developed by Anass MAJJI, a data scientist who has created this application to facilitate real-time document retrieval and query answering using advanced AI techniques.