This is a simple Streamlit application that allows you to upload a PDF file and chat with an AI assistant about its content. The application processes the PDF, creates embeddings, stores them in a Qdrant vector store, and uses the OpenAI API to answer questions based on the PDF's content.
- Upload PDF files.
- Process PDF content into searchable chunks.
- Use vector embeddings for semantic search.
- Answer questions about the PDF using an AI model.
- Reference page numbers from the original PDF in the answers.
- Python
- Streamlit
- LangChain
- OpenAI API
- Qdrant Vector Database
-
Run the Streamlit application from the project root directory:
streamlit run app.py
-
Your web browser will open with the application.
-
Upload a PDF file using the file uploader.
-
Once the PDF is processed, a chat interface will appear.
-
Type your questions about the PDF content in the chat input box and press Enter.
-
The AI assistant will provide answers based on the document, citing relevant page numbers.