This repository contains two main components:
- pdfrag.py - A PDF processing and question-answering app built using Streamlit and Google's Gemini model.
- Websearch_agent.py - A web search agent that performs searches and answers questions based on web search results.
- PDF text extraction using
PyPDF2
. - Chunking of text and creating a FAISS vector store for similarity searches.
- Integration with Google's Gemini model for QA functionality.
- Web search and QA using
transformers
.
Before running the application, ensure that the following Python dependencies are installed. You can install them using pip
:
pip install -r requirements.txt
streamlit run pdfrag.py