The project utilizes Python and several libraries to achieve the following:
- PDF Processing: Extract text from PDF documents.
- Text Chunking: Split extracted text into manageable chunks for processing.
- Embeddings and Vectorization: Utilize Google Generative AI Embeddings and FAISS for text vectorization and similarity search.
- Question Answering: Use a conversational model (Gemini-Pro) for answering questions based on the processed PDF content.
- PyPDF2
- langchain
- langchain_google_genai
- FAISS
- dotenv