OpenAI

LanceDB registers the OpenAI embeddings function in the registry by default, as openai. Below are the parameters that you can customize when creating the instances:

Parameter	Type	Default Value	Description
`name`	`str`	`"text-embedding-ada-002"`	The name of the model.
`dim`	`int`	Model default	Requested output dimensions for models that support shortening embeddings. Required for model names other than the OpenAI ones listed by `model_names()` (for example a model served behind an OpenAI-compatible `base_url`), where it is the model’s embedding dimension. Use `func.ndims()` when defining the vector field.
`use_azure`	bool	`False`	Set true to use Azure OpenAI SDK

Python 0.41.0 accepts only the model names returned by model_names(); setting dim does not enable an arbitrary model name in that version. Custom OpenAI-compatible model names with an explicit dim require the 0.42.0b8 client. Set your OpenAI API key before running the example:

export OPENAI_API_KEY="your-api-key"

import tempfile
from pathlib import Path

import lancedb
from lancedb.embeddings import get_registry
from lancedb.pydantic import LanceModel, Vector

db_path = Path(tempfile.mkdtemp()) / "openai-embeddings"
db = lancedb.connect(str(db_path))
func = get_registry().get("openai").create(name="text-embedding-ada-002")

class Words(LanceModel):
    text: str = func.SourceField()
    vector: Vector(func.ndims()) = func.VectorField()

table = db.create_table("words", schema=Words, mode="overwrite")
table.add(
    [
        {"text": "hello world"},
        {"text": "goodbye world"},
    ]
)

query = "greetings"
actual = table.search(query).limit(1).to_pydantic(Words)[0]
print(actual.text)

Embedding Registry

Embedding Providers

Rerankers

Data Platforms & Frameworks

AI Platforms & Frameworks