urme-b/NexusRAG - 3 Help Wanted Issues

Open Issues Need Help

Decide public-API vs. remove for test-only retrieval helpers 3 months ago

good first issue

Local, self-correcting RAG for scientific papers: hybrid retrieval, sentence-level faithfulness checks, and a reproducible benchmark.

Python

#bm25#cross-encoder#fastapi#information-retrieval#lancedb#llm#nlp#ollama#python#rag#reranking#retrieval-augmented-generation#scientific-papers#semantic-search#sentence-transformers

Wire the ECE metric into a calibration report (or remove it) 3 months ago

good first issue

urme-b/NexusRAG

Local, self-correcting RAG for scientific papers: hybrid retrieval, sentence-level faithfulness checks, and a reproducible benchmark.

Python

#bm25#cross-encoder#fastapi#information-retrieval#lancedb#llm#nlp#ollama#python#rag#reranking#retrieval-augmented-generation#scientific-papers#semantic-search#sentence-transformers

Pin HuggingFace model revisions for reproducible benchmarks 3 months ago

good first issue reproducibility

urme-b/NexusRAG

Local, self-correcting RAG for scientific papers: hybrid retrieval, sentence-level faithfulness checks, and a reproducible benchmark.

Python

#bm25#cross-encoder#fastapi#information-retrieval#lancedb#llm#nlp#ollama#python#rag#reranking#retrieval-augmented-generation#scientific-papers#semantic-search#sentence-transformers