paper-qa and Local_Pdf_Chat_RAG

These are competitors in the PDF-RAG space, with A offering a production-ready, citation-aware system for scientific documents while B provides a lightweight, educational implementation emphasizing hybrid retrieval (FAISS + BM25) suitable for learning purposes.

paper-qa
70
Verified
Local_Pdf_Chat_RAG
58
Established
Maintenance 13/25
Adoption 12/25
Maturity 25/25
Community 20/25
Maintenance 16/25
Adoption 10/25
Maturity 8/25
Community 24/25
Stars: 8,264
Forks: 838
Downloads:
Commits (30d): 3
Language: Python
License: Apache-2.0
Stars: 842
Forks: 159
Downloads:
Commits (30d): 1
Language: Python
License:
No risk flags
No License No Package No Dependents

About paper-qa

Future-House/paper-qa

High accuracy RAG for answering questions from scientific documents with citations

This tool helps researchers, scientists, and academics quickly find precise answers within a collection of scientific documents, such as PDFs or text files. You feed it your papers, and it provides accurate answers to your questions, complete with in-text citations to the original sources. This is ideal for anyone needing to extract specific information from a large volume of research literature.

scientific-research literature-review academic-writing information-extraction research-synthesis

About Local_Pdf_Chat_RAG

weiwill88/Local_Pdf_Chat_RAG

🧠 纯原生 Python 实现的 RAG 框架 | FAISS + BM25 混合检索 | 支持 Ollama / SiliconFlow | 适合新手入门学习

This project helps anyone who needs to quickly get answers from their documents without sharing sensitive information with external AI services. You can upload various document types like PDFs, Word files, or spreadsheets, ask questions in a user-friendly interface, and receive concise answers based only on the content you provided. This is ideal for researchers, analysts, or anyone managing confidential documents.

document-intelligence private-data-analysis information-retrieval knowledge-management

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