Skip to content

utkarsh240/Pdf_analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

8 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ“„ PDF Q&A with LangChain, OpenAI, and Qdrant

A Streamlit app that lets you upload a PDF and ask natural language questions about its content. It uses LangChain, OpenAI, and Qdrant to provide accurate answers based solely on the uploaded document.


πŸš€ Features

  • Upload and parse PDFs
  • Split PDF text into smart chunks
  • Embed and store content using Qdrant
  • Ask context-aware questions powered by GPT-4
  • Answers grounded in the uploaded PDF only

🧰 Tech Stack

  • Streamlit – Interactive Web UI
  • LangChain – Text splitting, Vector store handling, QA chain
  • OpenAI – Embeddings + LLM (GPT-4)
  • Qdrant – High-performance vector database
  • PyMuPDF (fitz) – PDF parsing and text extraction

πŸ“¦ Installation

Install the dependencies using pip:

pip install -r requirements.txt

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages