- [https://openai.com/index/new-embedding-models-and-api-updates/](https://openai.com/index/new-embedding-models-and-api-updates/)
- [https://arxiv.org/abs/2205.13147](https://arxiv.org/abs/2205.13147)
- [https://platform.openai.com/docs/guides/embeddings/embedding-models#use-cases](https://platform.openai.com/docs/guides/embeddings/embedding-models#use-cases)
- [https://platform.openai.com/docs/api-reference/embeddings/object](https://platform.openai.com/docs/api-reference/embeddings/object)

```python
tbl_document_fts = Table(
    "tbl_document_fts",
    metadata,
    Column(
        "chunk_id",
        BigInteger,
        ForeignKey("tbl_document_chunks.id", ondelete="CASCADE"),
        primary_key=True,
    ),
    Column("search_vector", TSVECTOR, nullable=False),
    Column("indexed_at", DateTime, server_default=func.now(), index=True),
    Index("idx_chunk_fts_gin", "search", postgresql_using="gin"),
)
```

Shortening the embedding dimensions while retaining accuracy