Ayush Chaurasia
ae0d2f2599
fix: Pydantic 1.x compat for weak_lru caching in embeddings API ( #643 )
...
Colab has pydantic 1.x by default and pydantic 1.x BaseModel objects
don't support weakref creation by default that we use to cache embedding
models
https://github.com/lancedb/lancedb/blob/main/python/lancedb/embeddings/utils.py#L206
. It needs to be added to slot.
2023-11-10 15:02:38 +05:30
Ayush Chaurasia
1e8678f11a
Multi-task instructor model with quantization support & weak_lru cache for embedding function models ( #612 )
...
resolves #608
2023-11-09 12:34:18 +05:30
Ayush Chaurasia
1589499f89
Exponential standoff retry support for handling rate limited embedding functions ( #614 )
...
Users ingesting data using rate limited apis don't need to manually make
the process sleep for counter rate limits
resolves #579
2023-11-02 19:20:10 +05:30
Ayush Chaurasia
0293bbe142
[Python]Embeddings API refactor ( #580 )
...
Sets things up for this -> https://github.com/lancedb/lancedb/issues/579
- Just separates out the registry/ingestion code from the function
implementation code
- adds a `get_registry` util
- package name "open-clip" -> "open-clip-torch"
2023-10-17 22:32:19 -07:00
