Fetching metadata from the HF Docker repository...
-
feat: deploy Tiers 2 & 3 — CRAG, faithfulness, streaming, Prometheus, eval-driven retrieval Running
BrejBala +1: Claude Sonnet 4.6 Tier 2 additions:
- Corrective RAG (CRAG) corrective retrieval loop with max_iters guard
- Two-layer faithfulness check (verify_citations + LLM judge, flag-default-OFF)
- Honest streaming via llm.astream (/chat/stream endpoint)
- Per-request cost/token accounting (actual API usage_metadata)
- Prometheus metrics endpoint (/metrics/prometheus)
- Cosine floor gate (RAG_MIN_CHUNK_SCORE=0.20, data-derived safety bound)
- Reranking implemented, A/B tested, disabled (nDCG@3 -0.057, +435ms)
- History-aware query contextualization (flag-default-OFF)
- Pinned, hash-locked requirements.txt (uv pip compile, 85 packages)
Tier 3 additions:
- Corpus reproducibility manifest (eval/corpus_manifest.py)
- Indirect-injection delimiting in RAG prompt
- End-to-end integration tests (CI-safe, zero network)
- Recruiter-facing DESIGN.md + architecture diagram
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
-
final changes with API key
-
Deploy backend Docker app