feat: chunked bge embeddings + lancedb sutta index

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
marcuspaico
2026-08-14 17:18:42 -07:00
parent 221b1f5097
commit 691d2d94f5
3 changed files with 64 additions and 0 deletions

10
scripts/build_index.py Normal file
View File

@@ -0,0 +1,10 @@
#!/usr/bin/env python
"""Build the sutta embeddings index."""
from pathlib import Path
from buddhagpt.index import build_index
if __name__ == "__main__":
jsonl = Path("corpus/suttas.jsonl")
db_path = Path("data/lancedb")
n = build_index(jsonl, db_path)
print(f"Built index with {n} chunks at {db_path}")