NyaySetu LLM RAG

A legal document question-answering system built with RAG (Retrieval-Augmented Generation) using LangChain, FAISS, and Llama3.

Features

pip install -r requirements.txt

python extract_pdf_to_json.py

python build_vectorstore.py

uvicorn app:app --reload

Name		Name	Last commit message	Last commit date
Latest commit History 26 Commits
.vscode		.vscode
__pycache__		__pycache__
faiss_index		faiss_index
nyaysetu_faiss_index		nyaysetu_faiss_index
pdfs		pdfs
.dockerignore		.dockerignore
.env.local		.env.local
.gitignore		.gitignore
README.md		README.md
__init__.py		__init__.py
app.py		app.py
build_vectorstore.py		build_vectorstore.py
docker		docker
extract_pdf_to_json.py		extract_pdf_to_json.py
local_rag_llama3.py		local_rag_llama3.py
main.py		main.py
nyaysetu-llm-rag.code-workspace		nyaysetu-llm-rag.code-workspace
nyaysetu_pdf_texts.json		nyaysetu_pdf_texts.json
pyproject.toml		pyproject.toml
query_vectorstore.py		query_vectorstore.py
replit.md		replit.md
requirements.txt		requirements.txt
runtime.txt		runtime.txt
script.py		script.py