ollama_pdf_rag and pdf-rag

These are competitors—both implement complete RAG pipelines for PDF interaction with similar core functionality (document ingestion, vector search, chat interface), so users would typically choose one based on maturity (A's higher star count suggests wider adoption) rather than use them together.

ollama_pdf_rag
61
Established
pdf-rag
40
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 7/25
Maturity 16/25
Community 17/25
Stars: 496
Forks: 189
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 38
Forks: 9
Downloads:
Commits (30d): 0
Language: TypeScript
License: AGPL-3.0
No Package No Dependents
Stale 6m No Package No Dependents

About ollama_pdf_rag

tonykipkemboi/ollama_pdf_rag

A full-stack demo showcasing a local RAG (Retrieval Augmented Generation) pipeline to chat with your PDFs.

This tool helps you quickly get answers and insights from your PDF documents by having a natural conversation with them. You upload one or more PDFs, and then you can ask questions in plain language, receiving answers with citations back. Anyone who needs to extract information from documents or conduct research without relying on external AI services would find this useful.

document-analysis private-research information-extraction local-AI knowledge-discovery

About pdf-rag

renton4code/pdf-rag

RAG (Retrieval-Augmented Generation) template with PDF OCR, vector search and chat/documents UI

This tool helps anyone who needs to quickly get answers from large collections of PDF documents. You can upload scanned or digital PDFs, and then ask questions in a chat interface. It identifies relevant information within your documents and provides direct answers with references to the original pages, making it easy to cite sources or verify details. This is ideal for researchers, analysts, or legal professionals working with extensive document libraries.

document-qa research-analysis information-retrieval knowledge-management legal-discovery

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