This project integrates LangChain v0.2.6, HuggingFace Serverless Inference API, and Meta-Llama-3-8B-Instruct. It provides a chat-like web interface to interact with a language model and maintain conversation history using the Runnable interface, the upgraded version of LLMChain. LLMChain has been deprecated since 0.1.17.

A production-ready RAG (Retrieval Augmented Generation) system built with FastAPI, LangChain, LangServe, LangSmith, Hugging Face, and Qdrant for document processing and intelligent querying.

This project combines the power of vector databases, large language models, and chat history management to create an interactive PDF chatbot

Click below to checkout the website

PDF Q&A ChatBot is a simple Streamlit web app that lets you upload a PDF and ask questions about its content using Google's Gemini AI. It extracts the text, builds a vector store, and answers your queries intelligently based on the document.