rag-api and Multi-Tenant-Retrieval-Augmented-Generation-RAG-System

Maintenance 6/25
Adoption 8/25
Maturity 7/25
Community 12/25
Maintenance 2/25
Adoption 4/25
Maturity 7/25
Community 14/25
Stars: 48
Forks: 6
Downloads:
Commits (30d): 0
Language: Python
License:
Stars: 5
Forks: 3
Downloads:
Commits (30d): 0
Language: Python
License:
No License No Package No Dependents
No License Stale 6m No Package No Dependents

About rag-api

BukeLy/rag-api

Multi-tenant RAG API powered by LightRAG/RAG-Anything. Auto-selects best parser (DeepSeek-OCR/MinerU/Docling) via complexity scoring

This is an enterprise-grade service for anyone needing to get quick, accurate answers from a wide variety of documents. You input unstructured files like PDFs, Word documents, images, or even spreadsheets, and it intelligently processes them, including extracting text, tables, and formulas. The system then provides precise answers to your questions, drawing insights from the document content, which is especially useful for businesses handling large volumes of diverse information.

document-intelligence enterprise-search knowledge-management business-process-automation data-extraction

About Multi-Tenant-Retrieval-Augmented-Generation-RAG-System

mominalix/Multi-Tenant-Retrieval-Augmented-Generation-RAG-System

A production-grade Multi-Tenant Retrieval-Augmented Generation (RAG) System built with FastAPI, Qdrant, and Streamlit. This system provides secure, isolated RAG capabilities for multiple organizations with advanced document processing, vector search, and LLM integration.

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