LocalAIEmbeddings#

class langchain_community.embeddings.localai.LocalAIEmbeddings[source]#

Bases: BaseModel, Embeddings

LocalAI embedding models.

Since LocalAI and OpenAI have 1:1 compatibility between APIs, this class uses the openai Python package’s openai.Embedding as its client. Thus, you should have the openai python package installed, and defeat the environment variable OPENAI_API_KEY by setting to a random string. You also need to specify OPENAI_API_BASE to point to your LocalAI service endpoint.

Example

from langchain_community.embeddings import LocalAIEmbeddings
openai = LocalAIEmbeddings(
    openai_api_key="random-string",
    openai_api_base="http://localhost:8080"
)

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param allowed_special: Literal['all'] | Set[str] = {}#

param chunk_size: int = 1000#: Maximum number of texts to embed in each batch

param deployment: str = 'text-embedding-ada-002'#

param disallowed_special: Literal['all'] | Set[str] | Sequence[str] = 'all'#

param embedding_ctx_length: int = 8191#: The maximum number of tokens to embed at once.

param headers: Any = None#

param max_retries: int = 6#: Maximum number of retries to make when generating.

param model: str = 'text-embedding-ada-002'#

param model_kwargs: Dict[str, Any] [Optional]#: Holds any model parameters valid for create call not explicitly specified.

param openai_api_base: str | None = None#

param openai_api_key: str | None = None#

param openai_api_version: str | None = None#

param openai_organization: str | None = None#

param openai_proxy: str | None = None#

param request_timeout: float | Tuple[float, float] | None = None#: Timeout in seconds for the LocalAI request.

param show_progress_bar: bool = False#: Whether to show a progress bar when embedding.

async aembed_documents(texts: List[str], chunk_size: int | None = 0) → List[List[float]][source]#

Call out to LocalAI’s embedding endpoint async for embedding search docs.

Parameters:

texts (List[str]) – The list of texts to embed.
chunk_size (int | None) – The chunk size of embeddings. If None, will use the chunk size specified by the class.

Returns:

List of embeddings, one for each text.

Return type:

List[List[float]]

async aembed_query(text: str) → List[float][source]#

Call out to LocalAI’s embedding endpoint async for embedding query text.

Parameters:: text (str) – The text to embed.
Returns:: Embedding for the text.
Return type:: List[float]

embed_documents(texts: List[str], chunk_size: int | None = 0) → List[List[float]][source]#

Call out to LocalAI’s embedding endpoint for embedding search docs.

Parameters:

texts (List[str]) – The list of texts to embed.
chunk_size (int | None) – The chunk size of embeddings. If None, will use the chunk size specified by the class.

Returns:

List of embeddings, one for each text.

Return type:

List[List[float]]

embed_query(text: str) → List[float][source]#

Call out to LocalAI’s embedding endpoint for embedding query text.

Parameters:: text (str) – The text to embed.
Returns:: Embedding for the text.
Return type:: List[float]

Examples using LocalAIEmbeddings

LocalAI