AsyncOpenAITextEmbedEmbeddingClient

class langchain_community.embeddings.textembed.AsyncOpenAITextEmbedEmbeddingClient(host: str = 'http://localhost:8000/v1', api_key: str | None = None, aiosession: ClientSession | None = None)

A client to handle synchronous and asynchronous requests to the TextEmbed API.

Parameters:

• host (str)

• api_key (str | None)

• aiosession (ClientSession | None)

host

The base URL for the TextEmbed API.

Type:

str

api_key

The API key for authenticating with the TextEmbed API.

Type:

str

aiosession

The aiohttp session for async requests.

Type:

Optional[aiohttp.ClientSession]

_batch_size

Maximum batch size for a single request.

Type:

int

Methods

__init__([host, api_key, aiosession])
aembed(model, texts)	Embeds a list of texts asynchronously.
embed(model, texts)	Embeds a list of texts synchronously.

__init__(host: str = 'http://localhost:8000/v1', api_key: str | None = None, aiosession: ClientSession | None = None) → None

Parameters:

• host (str)

• api_key (str | None)

• aiosession (ClientSession | None)

Return type:

None

async aembed(model: str, texts: List[str]) → List[List[float]]

Embeds a list of texts asynchronously.

Parameters:

• model (str) – The model to use for embedding.

• texts (List[str]) – List of texts to embed.

Returns:

List of embeddings for the texts.

Return type:

List[List[float]]

embed(model: str, texts: List[str]) → List[List[float]]

Embeds a list of texts synchronously.

Parameters:

• model (str) – The model to use for embedding.

• texts (List[str]) – List of texts to embed.

Returns:

List of embeddings for the texts.

Return type:

List[List[float]]