Commit History

  1. HowItWorks: fix step 02 title 'Dual Pipeline' -> '3-Pipeline Activation'

    dc29f08
  2. Home page: fix 8 stale/wrong facts⁠

    6d09a0b
  3. Benchmark: add LLM-as-a-Judge + BERTScore (hackathon 30% accuracy criterion)⁠

    5d58764
  4. Branding: replace Claude with TigerGraph logo and remove Claude references⁠

    c51e9c9
  5. Explorer live query: better error, science chips, fallback answer⁠

    64c3622
  6. Explorer: 4 science scenarios, BFS hop filter, live query section⁠

    b40d0b7
  7. Fix UI: 3-pipeline playground, science examples, correct docs/architecture⁠

    f26d060
  8. Fix README: remove HF frontmatter, correct dataset/eval/quickstart/latency⁠

    d52b559
  9. Improve latency: parallel LLM calls, embedding cache, client reuse⁠

    90b36cb
  10. Add HuggingFace repo card YAML metadata to README

    04362d1
  11. Add corpus.jsonl dataset via git-lfs (478 Wikipedia science docs, 2.5M tokens)

    44da0e3

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

    577adc4
  2. Add dataset preparation script — downloads Wikipedia/arxiv/BBC, verifies 2M+ tokens, ingests into TigerGraph

    Verified signature
    3ee4528
  3. Address feedback: add benchmark results table, ablation study, demo GIF section, 2M+ dataset plan

    Verified signature
    60b14ca

  1. Fix #10: Rewrite README — 3-pipeline system, TG GraphRAG integration, LLM-Judge + BERTScore, NoveltyEngine wiring

    Verified signature
    c6818ea
  2. Fix #8: Update web API compare route — 3-pipeline (LLM-Only + Basic RAG + GraphRAG) with side-by-side metrics

    Verified signature
    9333670
  3. Fix #7: Update dashboard.py — 3-column layout (LLM-Only / Basic RAG / GraphRAG), fix _get_demo_passages() query matching, add LLM-Judge + BERTScore display

    Verified signature
    ac2d14c
  4. Fix #9: Update benchmark runner for 3-pipeline comparison + LLM-as-a-Judge + BERTScore evaluation

    Verified signature
    ddfbb09
  5. Update __init__.py with new exports (TGGraphRAGClient, TripleComparisonResult, LLM judge, BERTScore, etc.)

    Verified signature
    df00339
  6. Fix #5: Install advanced GSQL queries (PPR, paths, activation) in setup_tigergraph.py

    Verified signature
    2941bc4
  7. Fix #3: Add LLM-as-a-Judge (PASS/FAIL) + BERTScore evaluation — the two hackathon-required accuracy metrics

    Verified signature
    f486777
  8. Fix #2+#4+#6: Add LLM-Only pipeline, wire NoveltyEngine, integrate TG GraphRAG client, 3-pipeline comparison

    Verified signature
    079d32f
  9. Fix #1: Add TigerGraph GraphRAG integration layer wrapping official repo REST APIs

    Verified signature
    3101051
  10. Deep research update: comprehensive README with 12 cited papers, evaluation methodology, architecture deep-dives, and hackathon-aligned benchmarking strategy

    Verified signature
    79a8e0b

  1. 🎨 Ultra premium UI: 6 separate pages with animations, bento grid, premium design

    Verified signature
    005833b
  2. 🎨 Add home page sections: Hero, Stats, Features, HowItWorks, Bento, Testimonials, CTA

    Verified signature
    5fcdc45
  3. 🎨 Stats bar component

    Verified signature
    00b163c
  4. 🎨 Premium navbar with page routing and mobile menu

    Verified signature
    023a6ec
  5. 🎨 Updated footer with page links

    Verified signature
    f4447b9
  6. 🎨 New multi-section home page

    Verified signature
    4adfc03
  7. 🎨 Update layout with new title

    Verified signature
    e56ae2e
  8. 🎨 Ultra premium UI: enhanced design system with animations, gradients, bento grid

    Verified signature
    3325bbe

  1. Massive README: 14 novelties from 10 papers, full architecture, paper citations, test counts"

    Verified signature
    36c721f
  2. Add unit tests for all 6 novelty techniques"

    Verified signature
    e51378c
  3. Add advanced GSQL queries: PPR scoring, shortest paths, spreading activation, community detection"

    Verified signature
    fe766f7
  4. Add GraphRAG novelties engine: PPR scoring, token budget, path pruning, spreading activation, hybrid router, incremental updates

    Verified signature
    4dd67cd
  5. Add .npmrc for peer dep compat

    Verified signature
    ff2ca1b
  6. Fix TS strict mode: remove unused imports, fix Tooltip formatter types in CostAnalysis"

    Verified signature
    7229c6f
  7. Fix build: add openai dep, add overrides for recharts/react19 peer deps, add .npmrc

    Verified signature
    697efb9
  8. Final README update with Docker deployment, test instructions, live benchmark, provider selector docs

    Verified signature
    10b2275
  9. Update Benchmark tab with live 'Run Benchmark Now' that calls API and populates real data"

    Verified signature
    c8e45c7
  10. Wire UniversalLLM into layers __init__ + add benchmark API endpoint for live runs

    Verified signature
    91ff0de
  11. Add benchmark API route for live benchmark runs from dashboard

    Verified signature
    fe0369c
  12. Add comprehensive unit tests for core functions

    Verified signature
    11bcc35
  13. Add Dockerfile for one-command deployment

    Verified signature
    47d8a83
  14. Add provider selector to LiveCompare + fix UI to support all 12 providers

    Verified signature
    d865094
  15. Massive README update with 12 LLM providers, OpenClaw integration, Ollama support, full architecture docs

    Verified signature
    c0294cf
  16. Update .env.example with all 12 LLM providers + Ollama + TigerGraph

    Verified signature
    9a33b09
  17. Add Python universal LLM layer with LiteLLM supporting 12 providers + Ollama

    Verified signature
    2cd4ca5
  18. Add multi-provider compare API route + providers listing endpoint

    Verified signature
    ddb116f