title	emoji	colorFrom	colorTo	sdk	sdk_version	app_file	pinned	license	short_description
Pdfsense	📜	red	red	streamlit	1.40.2	app.py	false	apache-2.0	PDF Answering Assistant

Check out the configuration reference at Hugging Face Spaces Config.

📜 PDFSense : PDF Question Answering Assistant with Chat History

PDFSense is an LLM-powered Streamlit application that enables users to upload PDFs and ask questions based on the document's content. It uses a Retrieval-Augmented Generation (RAG) approach to provide accurate, context-aware answers by incorporating previous chat history of the current session.

App in Hugging Face Space

🚀 Features

• Upload and analyze PDF documents.
• Ask questions about the uploaded PDF in natural language.
• Retrieve answers using LangChain, FAISS indexing, and Hugging Face embeddings.
• Maintain conversation context for coherent responses.

📚 How It Works

• Upload PDF: Drag and drop your PDF file into the uploader.
• Ask Questions: Type a question about the PDF's content.
• Contextual Answers: PDFSense retrieves answers using FAISS and LLMs while maintaining chat history for context.

🛠️ Technologies Used

• Streamlit: Interactive web application framework.
• LangChain: Framework for creating LLM-based applications.
• FAISS: Vector search for efficient retrieval.
• Hugging Face: Pretrained embeddings for document processing.
• Groq: LLM used for generating responses.
• PyPDFLoader: Document loader for processing PDFs.

🧩 Prerequisites

Make sure you have the following prerequisites:

• Python 3.8 and above
• Hugging Face account
• Hugging Face Access Token
• Groq API key

📦 Installation

If you want to use this locally on your system:

git clone https://github.com/Akashvarma26/PDFSense.git

pip install -r requirements.txt

▶️ Usage

Run the Streamlit app locally:

streamlit run app.py

🙋‍♂️ Acknowledgments

• LangChain
• Hugging Face
• FAISS
• Groq
• streamlit