|
|
88db8987b0
|
feat(infra): add hybrid arxiv search with pgvector HNSW + pg_trgm
- embed_arxiv.py: batch embedding of 700k arxiv abstracts using
static-retrieval-mrl-en-v1 (1024-dim model)
- hybrid_search.sql: RRF merger of trigram + vector search, 22ms query time
- jaccard_hybrid.py: 48 cornfield concepts matched to arxiv papers
Results: 480 hybrid citations loaded (vector-only matches for abstract concepts)
Build: 3314 jobs, 0 errors (lake build Compiler)
|
2026-06-22 01:11:17 -05:00 |
|
