Skip to content

A simple chatbot for PDFs that lets you upload one or more PDF files and ask natural language questions. The system retrieves relevant chunks from the documents using HuggingFace embeddings + FAISS and generates answers with Google Gemini.

Notifications You must be signed in to change notification settings

Vyshhh/MultiPDF_chatbot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Chat with PDF (Gemini + HuggingFace + Streamlit)

A simple chatbot for PDFs that lets you upload one or more PDF files and ask natural language questions. The system retrieves relevant chunks from the documents using HuggingFace embeddings + FAISS and generates answers with Google Gemini.


Features

  • Upload multiple PDF files.
  • Split PDFs into chunks using LangChain’s RecursiveCharacterTextSplitter.
  • Generate embeddings with HuggingFace (all-MiniLM-L6-v2).
  • Store and query chunks using FAISS vector database.
  • Answer questions using Gemini Flash with LangChain QA chain.
  • Interactive frontend built with Streamlit.

🛠️ Tech Stack

  • Python3
  • Streamlit – Web interface
  • LangChain – Text splitting, QA chain
  • HuggingFace Embeddings – Semantic search
  • FAISS – Vector database
  • Google Gemini API – LLM for answering questions
  • PyPDF2 – Extract text from PDFs

About

A simple chatbot for PDFs that lets you upload one or more PDF files and ask natural language questions. The system retrieves relevant chunks from the documents using HuggingFace embeddings + FAISS and generates answers with Google Gemini.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages