VertexAIEmbeddings

class langchain_google_vertexai.embeddings.VertexAIEmbeddings

Bases: _VertexAICommon, Embeddings

Google Cloud VertexAI embedding models.

Initialize the sentence_transformer.

param additional_headers: Dict[str, str] | None = None

A key-value dictionary representing additional headers for the model call

param api_endpoint: str | None = None (alias 'base_url')

Desired API endpoint, e.g., us-central1-aiplatform.googleapis.com

param api_transport: str | None = None

The desired API transport method, can be either ‘grpc’ or ‘rest’. Uses the default parameter in vertexai.init if defined.

param client_cert_source: Callable[[], Tuple[bytes, bytes]] | None = None

A callback which returns client certificate bytes and private key bytes both

param credentials: Any = None

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

param full_model_name: str | None = None

The full name of the model’s endpoint.

param location: str = 'us-central1'

The default location to use when making API calls.

param max_output_tokens: int | None = None (alias 'max_tokens')

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 = None (alias 'model')

Underlying model name.

param n: int = 1

How many completions to generate for each prompt.

param project: str | None = 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 safety_settings: 'SafetySettingsType' | None = None

The default safety settings to use for all generations.

For example:

from langchain_google_vertexai import HarmBlockThreshold, HarmCategory

safety_settings = {

HarmCategory.HARM_CATEGORY_UNSPECIFIED: HarmBlockThreshold.BLOCK_NONE, HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE, HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_ONLY_HIGH, HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE, HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_NONE,

}

param stop: List[str] | None = None (alias 'stop_sequences')

Optional list of stop words to use when generating.

param streaming: bool = False

Whether to stream the results or not.

param temperature: float | None = None

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

param top_k: int | None = None

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

param top_p: float | None = None

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

param tuned_model_name: str | None = None

The name of a tuned model. If tuned_model_name is passed model_name will be used to determine the model family

async aembed_documents(texts: List[str]) → List[List[float]]

Asynchronous Embed search docs.

Parameters:

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

Returns:

List of embeddings.

Return type:

List[List[float]]

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

Asynchronous Embed query text.

Parameters:

text (str) – Text to embed.

Returns:

Embedding.

Return type:

List[float]

embed(texts: List[str], batch_size: int = 0, embeddings_task_type: Literal['RETRIEVAL_QUERY', 'RETRIEVAL_DOCUMENT', 'SEMANTIC_SIMILARITY', 'CLASSIFICATION', 'CLUSTERING', 'QUESTION_ANSWERING', 'FACT_VERIFICATION'] | None = None, dimensions: int | None = None) → List[List[float]]

Embed a list of strings.

Parameters:

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

• batch_size (int) – [int] The batch size of embeddings to send to the model. If zero, then the largest batch size will be detected dynamically at the first request, starting from 250, down to 5.

• embeddings_task_type (Literal['RETRIEVAL_QUERY', 'RETRIEVAL_DOCUMENT', 'SEMANTIC_SIMILARITY', 'CLASSIFICATION', 'CLUSTERING', 'QUESTION_ANSWERING', 'FACT_VERIFICATION'] | None) –

  [str] optional embeddings task type, one of the following

  RETRIEVAL_QUERY - Text is a query

  in a search/retrieval setting.

  RETRIEVAL_DOCUMENT - Text is a document

  in a search/retrieval setting.

  SEMANTIC_SIMILARITY - Embeddings will be used

  for Semantic Textual Similarity (STS).

  CLASSIFICATION - Embeddings will be used for classification. CLUSTERING - Embeddings will be used for clustering. The following are only supported on preview models: QUESTION_ANSWERING FACT_VERIFICATION

• dimensions (int | None) – [int] optional. Output embeddings dimensions. Only supported on preview models.

Returns:

List of embeddings, one for each text.

Return type:

List[List[float]]

embed_documents(texts: List[str], batch_size: int = 0) → List[List[float]]

Embed a list of documents.

Parameters:

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

• batch_size (int) – [int] The batch size of embeddings to send to the model. If zero, then the largest batch size will be detected dynamically at the first request, starting from 250, down to 5.

Returns:

List of embeddings, one for each text.

Return type:

List[List[float]]

embed_image(image_path: str, contextual_text: str | None = None, dimensions: int | None = None) → List[float]

Embed an image.

Parameters:

• image_path (str) – Path to image (local, Google Cloud Storage or web) to generate

• for. (embeddings) –

• contextual_text (str | None) – Text to generate embeddings for.

• dimensions (int | None) –

Returns:

Embedding for the image.

Return type:

List[float]

embed_query(text: str) → List[float]

Embed a text.

Parameters:

text (str) – The text to embed.

Returns:

Embedding for the text.

Return type:

List[float]

get_num_tokens(text: str) → int

Get the number of tokens present in the text.

Useful for checking if an input will fit in a model’s context window.

Parameters:

text (str) – The string input to tokenize.

Returns:

The integer number of tokens in the text.

Return type:

int

property async_prediction_client: PredictionServiceAsyncClient

Returns PredictionServiceClient.

property model_type: str

property model_version: GoogleEmbeddingModelVersion

property prediction_client: PredictionServiceClient

Returns PredictionServiceClient.

task_executor: ClassVar[Executor | None] = FieldInfo(exclude=True, extra={})