langchain.OpenAIEmbeddingsDataset

kedro_datasets_experimental.langchain.OpenAIEmbeddingsDataset

OpenAIEmbeddingsDataset(credentials, kwargs=None)

Bases: OpenAIDataset[OpenAIEmbeddings]

OpenAIEmbeddingsDataset loads an OpenAIEmbeddings langchain model.

Example usage for the YAML API

catalog.yml

text_embedding_ada_002:
    type: langchain.OpenAIEmbeddingsDataset
    kwargs:
        model: "text-embedding-ada-002"
    credentials: openai

credentials.yml

openai:
    openai_api_base: <openai-api-base>
    openai_api_key: <openai-api-key>

Example usage for the Python API

from kedro_datasets_experimental.langchain import OpenAIEmbeddingsDataset

embeddings = OpenAIEmbeddingsDataset(
    credentials={
        "openai_api_base": "<openai-api-base>",
        "openai_api_key": "<openai-api-key>",
    },
    kwargs={
        "model": "text-embedding-ada-002",
    },
).load()

# See: https://python.langchain.com/docs/integrations/text_embedding/openai
embeddings.embed_query("Hello world!")

Source code in kedro-datasets/kedro_datasets_experimental/langchain/_openai.py

def __init__(self, credentials: dict[str, str], kwargs: dict[str, Any] = None):
    """Constructor.

    Args:
        credentials: must contain `openai_api_base` and `openai_api_key`.
        kwargs: keyword arguments passed to the underlying constructor.
    """
    self.openai_api_base = credentials["openai_api_base"]
    self.openai_api_key = credentials["openai_api_key"]
    self.kwargs = kwargs or {}

constructor property

constructor