RAG-Based AI System
Python
LangChain / LangGraph
Pinecone
HuggingFace Embeddings
Project Overview
This project implements a Retrieval-Augmented Generation (RAG) pipeline for AI systems. It integrates LangGraph workflows, vector databases (Pinecone), and HuggingFace embeddings for document retrieval and question answering.
Key Features
- Async RAG pipeline for fast document retrieval and generation.
- Integrated vector search with Pinecone for semantic similarity.
- Designed modular workflows using LangGraph for multi-agent control flow.