feat: chunked bge embeddings + lancedb sutta index
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
10
scripts/build_index.py
Normal file
10
scripts/build_index.py
Normal 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}")
|
||||
Reference in New Issue
Block a user