`VertexAIEmbeddings`¶

Reference docs

This page contains reference documentation for VertexAIEmbeddings. See the docs for conceptual guides, tutorials, and examples on using VertexAIEmbeddings.

VertexAIEmbeddings `deprecated` ¶

Bases: BaseModel, Embeddings

Deprecated

Use GoogleGenerativeAIEmbeddings instead.

Google Cloud VertexAI embedding models.

METHOD	DESCRIPTION
`aembed_documents`	Asynchronous Embed search docs.
`aembed_query`	Asynchronous Embed query text.
`validate_environment`	Validates that the python package exists in environment.
`embed`	Embed a list of strings.
`embed_documents`	Embed a list of documents.
`embed_query`	Embed a text.

project `class-attribute` `instance-attribute` ¶

project: str | None = None

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

location `class-attribute` `instance-attribute` ¶

location: str = Field(default='us-central1')

The default location to use when making API calls.

model_name `class-attribute` `instance-attribute` ¶

model_name: str | None = Field(default=None, alias='model')

Underlying model name.

credentials `class-attribute` `instance-attribute` ¶

credentials: Any = Field(default=None, exclude=True)

The default custom credentials to use when making API calls.

(google.auth.credentials.Credentials)

If not provided, credentials will be ascertained from the environment.

max_retries `class-attribute` `instance-attribute` ¶

max_retries: int = 6

The maximum number of retries to make when generating.

dimensions `class-attribute` `instance-attribute` ¶

dimensions: int | None = None

Default output dimensionality for embeddings. If not specified, uses the model's default. Can be overridden per request in embed() method.

aembed_documents `async` ¶

aembed_documents(texts: list[str]) -> list[list[float]]

Asynchronous Embed search docs.

PARAMETER	DESCRIPTION
`texts`	List of text to embed. TYPE: `list[str]`

RETURNS	DESCRIPTION
`list[list[float]]`	List of embeddings.

aembed_query `async` ¶

aembed_query(text: str) -> list[float]

Asynchronous Embed query text.

PARAMETER	DESCRIPTION
`text`	Text to embed. TYPE: `str`

RETURNS	DESCRIPTION
`list[float]`	Embedding.

validate_environment ¶

validate_environment() -> Self

Validates that the python package exists in environment.

embed ¶

embed(
    texts: list[str],
    embeddings_task_type: EmbeddingTaskTypes | None = None,
    dimensions: int | None = None,
    title: str | None = None,
) -> list[list[float]]

Embed a list of strings.

PARAMETER	DESCRIPTION
`texts`	The list of strings to embed. TYPE: `list[str]`
`embeddings_task_type`	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. `CODE_RETRIEVAL_QUERY` - Embeddings will be used for code retrieval for Java and Python. The following are only supported on preview models: `QUESTION_ANSWERING`, `FACT_VERIFICATION`. TYPE: `EmbeddingTaskTypes \| None` DEFAULT: `None`
`dimensions`	Output embeddings dimensions. Only supported on preview models. If not provided, uses the default dimensions specified in the constructor. TYPE: `int \| None` DEFAULT: `None`
`title`	Title for the text. Only applicable when `TaskType` is `RETRIEVAL_DOCUMENT`. TYPE: `str \| None` DEFAULT: `None`

RETURNS	DESCRIPTION
`list[list[float]]`	List of embeddings, one for each text.

embed_documents ¶

embed_documents(
    texts: list[str], *, embeddings_task_type: EmbeddingTaskTypes = "RETRIEVAL_DOCUMENT"
) -> list[list[float]]

Embed a list of documents.

PARAMETER	DESCRIPTION
`texts`	The list of texts to embed. TYPE: `list[str]`
`embeddings_task_type`	The task type for embeddings. TYPE: `EmbeddingTaskTypes` DEFAULT: `'RETRIEVAL_DOCUMENT'`

RETURNS	DESCRIPTION
`list[list[float]]`	List of embeddings, one for each text.

embed_query ¶

embed_query(
    text: str, *, embeddings_task_type: EmbeddingTaskTypes = "RETRIEVAL_QUERY"
) -> list[float]

Embed a text.

PARAMETER	DESCRIPTION
`text`	The text to embed. TYPE: `str`
`embeddings_task_type`	The task type for embeddings. TYPE: `EmbeddingTaskTypes` DEFAULT: `'RETRIEVAL_QUERY'`

RETURNS	DESCRIPTION
`list[float]`	Embedding for the text.

VertexAIEmbeddings¶