RAG-PDF QA Method -
Date
January 2025
Service
Employer
Project Overview
This project aimed to build an interface so that user could provide a PDF and ask specific questions to the LLM based on the pdf content. The LLM also indicated the paragraphs and texts that led to the answer that it provided. This reduced the chances of hallucinations by the model.
https://github.com/ritam3/RAG-PDF-HuggingFace-Groq/tree/main
Key Highlights
Parsing of PDF Document: Supports parsing and preprocessing PDF documents for QA.
HuggingFace Embeddings: Used HuggingFace models to generate embeddings for document text.
Groq API Integration: Used Groq API for embedding retrieval and similarity search.
Session Management: Maintains session state so redundant calculations of embeddings can be avoided; hence, it will be more efficient.
Interactive QA: It allows users to ask queries after uploading documents. It retrieves relevant information from the processed PDFs.
