Commit History

  1. Benchmark: add LLM-as-a-Judge + BERTScore (hackathon 30% accuracy criterion)⁠

    5d58764
  2. Improve latency: parallel LLM calls, embedding cache, client reuse⁠

    90b36cb

  1. Add .gitignore, dataset metadata, retrieval layer, and latest web/graphrag updates

    577adc4

  1. Fix #8: Update web API compare route — 3-pipeline (LLM-Only + Basic RAG + GraphRAG) with side-by-side metrics

    Verified signature
    9333670

  1. Add benchmark API route for live benchmark runs from dashboard

    Verified signature
    fe0369c
  2. Add multi-provider compare API route + providers listing endpoint

    Verified signature
    ddb116f
  3. Add providers listing API endpoint

    Verified signature
    71f60e2
  4. Add Claude-powered compare API route with dual-pipeline orchestration

    Verified signature
    19df402