https://github.com/harmeshgv/rag-experiments
Showcasing diverse RAG techniques for enhanced natural language processing tasks.
https://github.com/harmeshgv/rag-experiments
gorq retrival-augmented-generation
Last synced: 11 months ago
JSON representation
Showcasing diverse RAG techniques for enhanced natural language processing tasks.
- Host: GitHub
- URL: https://github.com/harmeshgv/rag-experiments
- Owner: harmeshgv
- License: mit
- Created: 2025-02-07T18:53:07.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-18T11:05:05.000Z (over 1 year ago)
- Last Synced: 2025-03-18T11:38:16.518Z (over 1 year ago)
- Topics: gorq, retrival-augmented-generation
- Language: Python
- Homepage:
- Size: 2.93 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Stat IQ - PDF Q&A System
## Overview
Stat IQ is a simple Retrieval-Augmented Generation (RAG) system that enables users to upload a PDF document and ask questions related to its content. The system extracts text from the uploaded PDF and leverages the Groq API to generate responses based on the document's content.
## Features
- Upload a PDF file for text extraction.
- Ask questions related to the document.
- AI-powered responses using a conversational history.
- Handles API errors and rate limits efficiently.
## How It Works
1. User uploads a PDF file.
2. The system extracts text from the document.
3. User asks a question related to the PDF content.
4. The Groq API processes the query with the extracted text as context and returns a response.
5. The response is displayed to the user.
## Future Enhancements
This repository will be updated with more advanced RAG techniques, including:
- Chunk-based retrieval for better context handling.
- Vector embeddings for semantic search.
- Hybrid search using dense and sparse retrieval methods.
- Multi-document querying with ranking algorithms.
Stay tuned for more updates on advanced RAG implementations!