Results for rag-eval

Perform various evaluations to input RAG data

Core types, schemas, and domain models for RAG evaluation

RAG evaluation metric scorers: faithfulness, relevance, context precision/recall

Dataset loading, validation, generation, and versioning for RAG evals

Cost tracking, pricing, budgeting, and reporting for RAG evaluations

LLM-as-judge with calibration, consensus voting, and cost tracking

Central evaluation orchestrator that ties metrics, judge, cost, gate, and dataset together

Structured logging, OpenTelemetry tracing, and metrics for RAG evaluations

CLI entry point and commands for the RAG evaluation toolkit

Quality gates and CI/CD regression checks for RAG evaluations

Evaluate RAG pipelines: retrieval precision, faithfulness, answer correctness. Multi-provider judge (Claude/OpenAI). Zero-config CLI.

MCP server exposing RAG evaluation tools (judge, suite, gate)

evaluate statically-analyzable expressions

Simple JavaScript expression evaluator

Evaluate node require() module content directly

Mathematical expression evaluator fork with exports map, prototype pollution and code injection security fixes

A flexible math expression evaluator

require or eval modules

Lightweight RAG evaluation metrics for CI/CD pipelines

Mark scopes for deopt which contain a direct eval call

Get callsites from the V8 stack trace API

JavaScript expression parsing and evaluation.

Alias for eval global.

CLI for installing agent harness + UI + RAG + eval patterns from attrition.sh into .claude/skills/ and AGENTS.md.