document-qa-rag-system and Agentic_RAG

Agentic_RAG
29
Experimental
Maintenance 2/25
Adoption 5/25
Maturity 15/25
Community 11/25
Maintenance 0/25
Adoption 5/25
Maturity 8/25
Community 16/25
Stars: 12
Forks: 2
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
Stars: 10
Forks: 6
Downloads:
Commits (30d): 0
Language: Python
License:
Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About document-qa-rag-system

ZohaibCodez/document-qa-rag-system

A simple Retrieval-Augmented Generation (RAG) project built with LangChain and Streamlit. Upload documents (PDF/TXT) and interact with them using natural language questions powered by embeddings and vector search.

This tool helps you quickly get answers from your documents by turning any PDF or plain text file into an interactive Q&A experience. You upload your document, and then you can ask questions about its content in everyday language, getting direct answers back. It's ideal for professionals, researchers, or students who need to extract specific information or summarize key points from reports, articles, or books without manually sifting through pages.

information-retrieval document-analysis research-assistant knowledge-management study-aid

About Agentic_RAG

rajveersinghcse/Agentic_RAG

✌️ A dynamic Retrieval-Augmented Generation (RAG) system with support for PDF indexing, website crawling, and semantic Q&A powered by OpenAI, Qdrant, and Streamlit.

This tool helps you quickly get answers from large documents and websites without manually sifting through information. You provide PDF files or website URLs, and it intelligently retrieves answers to your questions, even performing an online search if the information isn't found in your sources. Anyone needing to extract specific information from a collection of documents or web pages, like researchers, analysts, or content strategists, would find this useful.

information-retrieval document-analysis content-research knowledge-management web-scraping-qa

Scores updated daily from GitHub, PyPI, and npm data. How scores work