This project is a Retrieval-Augmented Generation (RAG) based Legal Document Question Answering System built using:
- π¦ LangChain
- π PDF loaders
- β‘ Cohere Embeddings & LLM
- π Chroma vector store
- β Upload legal PDF documents
- β
Chunk and embed text using Cohere's
embed-english-v3.0 - β Store document vectors in a local Chroma DB
- β Ask natural language questions about the PDF
- β Get AI-generated answers with source references
- β Streamlit UI for easy interaction
| Tool | Purpose |
|---|---|
LangChain |
Orchestrate RAG pipeline |
Cohere |
Embeddings + LLM for Q&A |
Chroma |
Vector DB for semantic search |
Streamlit |
Web UI |
dotenv |
Local secret handling |
PyPDF2 |
PDF parsing |
