AI / RAG

PaperLM

RAG-based PDF Chatbot built with LangChain and Pinecone.

Project Media

Photos / Videos go here

Tech Stack

LangChainPostgreSQLPineconeAWS S3Next.js

Links

The Challenge

PaperLM is a document ingestion and retrieval system that allows users to chat with their PDF documents. It features a robust backend using RAG pipeline, AWS S3 for secure document storage, and PostgreSQL for metadata management. It leverages Pinecone for vector-based semantic retrieval and OpenAI embeddings to provide accurate and context-aware responses.

Key Features

  • Feature one description would go here.
  • Another important capability of the system.
  • Technical highlight or optimization.

Outcome

The project resulted in a significant improvement in performance/usability. It demonstrates advanced capabilities in the chosen technology stack.