osllmai/inDox

The Indox Ecosystem offers integrated AI tools for data workflows. Our four components (IndoxArcg, IndoxMiner, IndoxJudge, and IndoxGen) enhance AI applications with advanced retrieval, extraction, evaluation, and generation capabilities, supporting multiple document formats and LLM providers.

47
/ 100
Emerging

IndoxArcg implements semantic caching and multi-query retrieval with pluggable similarity algorithms (TF-IDF, BM25, Jaccard), while IndoxMiner provides schema-based extraction with OCR for high-resolution PDFs and async processing. IndoxJudge includes RAG-specific evaluation metrics alongside safety/bias assessment, and IndoxGen offers both LLM-powered and GAN-based (TensorFlow/PyTorch) synthetic data generation. The ecosystem supports OpenAI, Google, Mistral, HuggingFace, and Ollama with intelligent fallback mechanisms for retrieval failures and hallucination detection.

Available on PyPI.

Maintenance 10 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 8 / 25

How are scores calculated?

Stars

19

Forks

2

Language

Jupyter Notebook

License

AGPL-3.0

Last pushed

Feb 05, 2026

Monthly downloads

131

Commits (30d)

0

Dependencies

17

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/osllmai/inDox"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.