langchain.embeddings.vertexai.VertexAIEmbeddings¶

class langchain.embeddings.vertexai.VertexAIEmbeddings(*, client: '_LanguageModel' = None, model_name: str = 'textembedding-gecko', temperature: float = 0.0, max_output_tokens: int = 128, top_p: float = 0.95, top_k: int = 40, stop: Optional[List[str]] = None, project: Optional[str] = None, location: str = 'us-central1', credentials: Any = None, request_parallelism: int = 5, max_retries: int = 6)[source]¶

Bases: _VertexAICommon, Embeddings

Google Cloud VertexAI embedding models.

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 credentials: Any = None¶

The default custom credentials (google.auth.credentials.Credentials) to use

param location: str = 'us-central1'¶

The default location to use when making API calls.

param max_output_tokens: int = 128¶

Token limit determines the maximum amount of text output from one prompt.

param max_retries: int = 6¶

The maximum number of retries to make when generating.

param model_name: str = 'textembedding-gecko'¶

Model name to use.

param project: Optional[str] = None¶

The default GCP project to use when making Vertex API calls.

param request_parallelism: int = 5¶

The amount of parallelism allowed for requests issued to VertexAI models.

param stop: Optional[List[str]] = None¶

Optional list of stop words to use when generating.

param temperature: float = 0.0¶

Sampling temperature, it controls the degree of randomness in token selection.

param top_k: int = 40¶

How the model selects tokens for output, the next token is selected from

param top_p: float = 0.95¶

Tokens are selected from most probable to least until the sum of their

embed_documents(texts: List[str], batch_size: int = 5) → List[List[float]][source]¶

Embed a list of strings. Vertex AI currently sets a max batch size of 5 strings.

Parameters

  • texts – List[str] The list of strings to embed.

  • batch_size – [int] The batch size of embeddings to send to the model

Returns

List of embeddings, one for each text.

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

Embed a text.

Parameters

text – The text to embed.

Returns

Embedding for the text.

validator validate_environment  »  all fields[source]¶

Validates that the python package exists in environment.

property is_codey_model: bool¶
task_executor: ClassVar[Optional[Executor]] = None¶

Examples using VertexAIEmbeddings¶