Spaces:
Sleeping
Sleeping
Commit History
-
feat: switch deployment to Hugging Face Spaces (16GB free tier)
Render free tier OOMs at 512MB with sentence-transformers. HF Spaces provides 16GB RAM free with Docker support. - Dockerfile: user 1000 (HF requirement), port 7860, models pre-downloaded - README: HF Spaces frontmatter, updated demo URL and curl examples - Startup warmup re-enabled (16GB is plenty) - Remove render.yaml Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>cd0c04f -
feat: add cross-encoder reranking with feature flag
CrossEncoderReranker (ms-marco-MiniLM-L-6-v2) reranks RRF-fused candidates to improve retrieval precision. Lazy-loads model on first use. Enabled by default; rag.reranker.enabled: false restores V1. - RerankerConfig extended with model_name and top_k (independent of retrieval.top_k) - Retriever passes all RRF candidates to reranker, preserves original RRF scores on reranked results (critical for refusal gate interaction) - Dockerfile pre-downloads cross-encoder model at build time - 6 new tests including score-preservation regression test (109 total) - DECISIONS.md entry with rationale - Benchmark comparison deferred pending eval sweep with API key Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>65d5480
-
feat: Day 9 — Docker deployment with Dockerfile and docker-compose
- Dockerfile: python:3.11-slim, copies source before pip install, pre-downloads embedding model and runs ingestion at build time - docker-compose.yaml: maps port 8000, passes OPENAI_API_KEY, mounts .cache volume for embedding persistence - .dockerignore: excludes tests, docs, .git, caches from build context Docker daemon not running in this environment — build not verified. Dockerfile follows design spec exactly (copy-before-install pattern). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>04e6c77