vertex_ai library
GCP Vertex AI ML platform API client (PaLM, Matching Engine, etc.).
Classes
- VertexAIAlgorithmConfig
- The configuration with regard to the algorithms used for efficient search.
- VertexAIAutomaticResources
- A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
- VertexAIAutoscalingMetricSpec
- The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
- VertexAIBruteForceAlgorithmConfig
- Configuration options for using brute force search, which simply implements the standard linear search in the database for each query.
- VertexAICountTokensResponse
- Response for a Vertex AI count tokens request.
- VertexAIDedicatedResources
- A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration.
- VertexAIDeployedIndex
- A deployment of an Index.
- VertexAIDeployedIndexAuthConfig
- Used to set up the auth on the DeployedIndex's private endpoint.
- VertexAIDeployedIndexAuthConfigAuthProvider
- Configuration for an authentication provider, including support for [JSON Web Token (JWT)](https://tools.ietf.org/html/draft-ietf-oauth-json-web-token-32).
- VertexAIDeployedIndexRef
- Points to a VertexAIDeployedIndex.
- VertexAIFindNeighborsRequestQuery
- A query to find a number of the nearest neighbors (most similar vectors) of a vector.
- VertexAIFindNeighborsResponse
- The response message for MatchService.FindNeighbors.
- VertexAIFindNeighborsResponseNearestNeighbors
- Nearest neighbors for one query.
- VertexAIFindNeighborsResponseNeighbor
- A neighbor of the query vector.
- VertexAIGenAIClient
- A client for interacting with Vertex AI's Generative AI foundational models.
- VertexAIIndex
- A Vertex AI Index.
- VertexAIIndexDatapoint
- A datapoint of Index.
- VertexAIIndexDatapointCrowdingTag
- Crowding tag is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute.
- VertexAIIndexDatapointRestriction
- Restriction of a datapoint which describe its attributes(tokens) from each of several attribute categories(namespaces).
- VertexAIIndexEndpoint
- Indexes are deployed into it.
- VertexAIIndexEndpointsApi
- Vertex AI Index Endpoints API.
- VertexAIIndexEndpointsOperationsApi
- Vertex AI Index Endpoints Operations API.
- VertexAIIndexesApi
- Vertex AI Indexes API.
- VertexAIIndexesOperationsApi
- Vertex AI Indexes Operations API.
- VertexAIIndexMetadata
- A Vertex AI Nearest Neighbor Search Index Metadata.
- VertexAIIndexPrivateEndpoints
- IndexPrivateEndpoints proto is used to provide paths for users to send requests via private endpoints (e.g. private service access, private service connect).
- VertexAIIndexRequestMetadata
- Metadata required to create or update a Vertex AI Index.
- VertexAIIndexStats
- The statistics of a Vertex AI Index.
- VertexAIMachineSpec
- Specification of a single machine.
- VertexAIMatchingEngineClient
- A client for interacting with Vertex AI's Matching Engine vector database.
- VertexAINearestNeighborSearchConfig
- The configuration of the Matching Engine Index.
- VertexAIOperation
- A long-running operation that is the result of a network API call.
- VertexAIOperationError
- The error result of the operation in case of failure.
- VertexAIPredictionCitation
- Citation for a Vertex AI Text Model Prediction.
- VertexAIPredictionSafetyAttributes
- Content processed through the Vertex AI PaLM API is assessed against a list of safety attributes, which include "harmful categories" and topics that may be considered sensitive. https://cloud.google.com/vertex-ai/docs/generative-ai/learn/responsible-ai#safety_attribute_confidence_scoring
- VertexAIPrivateServiceConnectConfig
- Represents configuration for private service connect.
- VertexAITextChatModelApi
- A client for interacting with Vertex AI Model Garden Text Chat Models.
- VertexAITextChatModelExample
- Example of what the model should generate.
- VertexAITextChatModelMessage
- A message includes an author and the content of the message.
- VertexAITextChatModelPrediction
- Prediction from a Vertex AI Chat Model.
- VertexAITextChatModelRequest
- Request for a Vertex AI Text Chat Model.
- VertexAITextChatModelRequestParams
- Parameters for a Vertex AI Text Chat model request.
- VertexAITextChatModelResponse
- Response for a Vertex AI Text Chat Model.
- VertexAITextChatModelResponseMetadata
- Metadata for a Vertex AI Text Chat Model Response.
- VertexAITextChatModelResponseMetadataToken
- Token metadata for a Vertex AI Text Chat Model Response.
- VertexAITextEmbeddingsModelApi
- A client for interacting with Vertex AI Model Garden text embeddings models.
- VertexAITextEmbeddingsModelContent
- The content to embed.
- VertexAITextEmbeddingsModelPrediction
- Prediction from a Vertex AI Text Embeddings Model.
- VertexAITextEmbeddingsModelRequest
- Request for a Vertex AI Text Embeddings Model.
- VertexAITextEmbeddingsModelResponse
- Response for a Vertex AI Text Embeddings Model.
- VertexAITextEmbeddingsModelResponseMetadata
- Metadata for a Vertex AI Text Embeddings Model Response.
- VertexAITextEmbeddingsModelResponseStatistics
- Statistics for a Vertex AI Text Embeddings Model Response.
- VertexAITextModelApi
- A client for interacting with Vertex AI Generative AI text models.
- VertexAITextModelPrediction
- Prediction from a Vertex AI Text Model.
- VertexAITextModelRequest
- Request for a Vertex AI Text Model.
- VertexAITextModelRequestParams
- Parameters for a Vertex AI Text model request.
- VertexAITextModelResponse
- Response for a Vertex AI Text Model.
- VertexAITextModelResponseMetadata
- Metadata for a Vertex AI Text Model Response.
- VertexAITextModelResponseMetadataToken
- Token metadata for a Vertex AI Text Model Response.
- VertexAITreeAhAlgorithmConfig
- Tree-AH efficient search algorithm.
Enums
- VertexAIDistanceMeasureType
- The distance measure used in nearest neighbor search.
- VertexAIFeatureNormType
- Type of normalization to be carried out on each vector.
- VertexAIIndexUpdateMethod
- The update method to use with this Index.
- VertexAIPredictionSafetyAttributesCategory
- Category of the safety attribute. https://cloud.google.com/vertex-ai/docs/generative-ai/learn/responsible-ai#safety_attribute_descriptions
- VertexAIShardSize
- Index data is split into equal parts to be processed. These are called "shards". When you create an index you must specify the shard size. Once you create the index, you can determine what machine type to use when you deploy your index.
- VertexAITextEmbeddingsModelTaskType
- Type of task where the embeddings will be used. It helps the model produce better quality embeddings.