| title | Pdfsense |
|---|---|
| emoji | 📜 |
| colorFrom | red |
| colorTo | red |
| sdk | streamlit |
| sdk_version | 1.40.2 |
| app_file | app.py |
| pinned | false |
| license | apache-2.0 |
| short_description | PDF Answering Assistant |
Check out the configuration reference at Hugging Face Spaces Config.
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.
- 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.
- 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.
- 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.
Make sure you have the following prerequisites:
If you want to use this locally on your system:
git clone https://github.com/Akashvarma26/PDFSense.git
pip install -r requirements.txt
Run the Streamlit app locally:
streamlit run app.py