Skip to content

Latest commit

 

History

History
17 lines (10 loc) · 518 Bytes

README.md

File metadata and controls

17 lines (10 loc) · 518 Bytes

PDF Chat

This project is a simple implementation of a PDF Chatter that uses:

  1. PyPDF: To read and parse PDF Files
  2. AstraDB: To store the text chunks and convert them into vector embeddings using OpenAI Embeddings
  3. Streamlit: To represent the UI
  4. Langchain: To configure the llms and parse the text from the pdf

Prerequisites

pip install -r requirements.txt

Be sure to initialize your own AstraDB, OPENAI_API_KEY and generate all the required environment variables.

Thank You for checking out!