emtcmca/transparent-confidence

Docs recipe: wiring RAGAS output through the evaluator bridge in a live pipeline about 2 hours ago

documentation good first issue

2

Zero-dependency, fully auditable TypeScript library that scores a RAG answer inline at query time. No LLM calls. No offline pipeline. Uses signals already in your retrieval stack. Output: a typed 0–100 scorecard with per-dimension breakdowns.

TypeScript

#evaluator#inline#rag#rag-pipeline#semantic-analysis

Python port: identical algorithm, same test scenarios, same output shape about 2 hours ago

enhancement help wanted

emtcmca/transparent-confidence

2

Zero-dependency, fully auditable TypeScript library that scores a RAG answer inline at query time. No LLM calls. No offline pipeline. Uses signals already in your retrieval stack. Output: a typed 0–100 scorecard with per-dimension breakdowns.

TypeScript

#evaluator#inline#rag#rag-pipeline#semantic-analysis

Domain preset configs: presets.legalDocs, presets.customerSupport about 2 hours ago

enhancement good first issue

emtcmca/transparent-confidence

2

Zero-dependency, fully auditable TypeScript library that scores a RAG answer inline at query time. No LLM calls. No offline pipeline. Uses signals already in your retrieval stack. Output: a typed 0–100 scorecard with per-dimension breakdowns.

TypeScript

#evaluator#inline#rag#rag-pipeline#semantic-analysis

Score explanation renderer: format DimensionScore.explanation into Markdown/HTML about 2 hours ago

enhancement good first issue

emtcmca/transparent-confidence

2

Zero-dependency, fully auditable TypeScript library that scores a RAG answer inline at query time. No LLM calls. No offline pipeline. Uses signals already in your retrieval stack. Output: a typed 0–100 scorecard with per-dimension breakdowns.

TypeScript

#evaluator#inline#rag#rag-pipeline#semantic-analysis

Open Issues Need Help