Table of Contents

Namespace GenerativeAI.Types.RagEngine

Vertex AI RAG Engine: VertexRagManager, RAG corpora and files, import and upload configuration, retrieval settings and the RAG Engine configuration (Serverless or Spanner mode).

Classes

ApiAuth

The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead.

ApiAuthApiKeyConfig

The API secret.

BigQueryDestination

The BigQuery location for the output content.

BigQuerySource

The BigQuery location for the input content.

CorpusStatus

RagCorpus status.

DirectUploadSource

The input content is encapsulated and uploaded in the request.

FileManagementClient

A client for interacting with the RAG Engine API for file management.

FileStatus

RagFile status.

GcsSource

The Google Cloud Storage location for the input content.

GoogleDriveSource

The Google Drive location for the input content.

GoogleDriveSourceResourceId

The type and ID of the Google Drive resource.

GoogleRpcStatus

The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.

ImportRagFilesConfig

Config for importing RagFiles.

ImportRagFilesRequest

Request message for VertexRagDataService.ImportRagFiles.

JiraSource

The Jira source for the ImportRagFilesRequest.

JiraSourceJiraQueries

JiraQueries contains the Jira queries and corresponding authentication.

ListRagCorporaResponse

Response message for VertexRagDataService.ListRagCorpora.

ListRagFilesResponse

Response message for VertexRagDataService.ListRagFiles.

RagContexts

Relevant contexts for one query.

RagContextsContext

A context of the query.

RagCorpus

A RagCorpus is a RagFile container and a project can have multiple RagCorpora.

RagCorpusClient

A client for interacting with the Vertex AI RAG Engine API.

RagEmbeddingModelConfig

Config for the embedding model to use for RAG.

RagEmbeddingModelConfigHybridSearchConfig

Config for hybrid search.

RagEmbeddingModelConfigSparseEmbeddingConfig

Configuration for sparse emebdding generation.

RagEmbeddingModelConfigSparseEmbeddingConfigBm25

Message for BM25 parameters.

RagEmbeddingModelConfigVertexPredictionEndpoint

Config representing a model hosted on Vertex Prediction Endpoint.

RagEngineConfig

Project-level configuration of the Vertex AI RAG Engine for one location, including the mode of the RAG-managed database (Serverless or Spanner).

RagFile

A RagFile contains user data for chunking, embedding and indexing.

RagFileChunkingConfig

Specifies the size and overlap of chunks for RagFiles.

RagFileChunkingConfigFixedLengthChunking

Specifies the fixed length chunking config.

RagFileParsingConfig

Specifies the parsing config for RagFiles.

RagFileParsingConfigAdvancedParser

Specifies the advanced parsing for RagFiles.

RagFileParsingConfigLayoutParser

Document AI Layout Parser config.

RagFileParsingConfigLlmParser

Specifies the advanced parsing for RagFiles.

RagFileTransformationConfig

Specifies the transformation config for RagFiles.

RagManagedDbBasic

The Basic tier of the RAG-managed database.

RagManagedDbConfig

The configuration of the RAG-managed database. Set exactly one of Serverless or Spanner; the top-level tier fields are deprecated.

RagManagedDbScaled

The Scaled tier of the RAG-managed database.

RagManagedDbServerless

Serverless mode of the RAG-managed database.

RagManagedDbSpanner

Spanner mode of the RAG-managed database. Set at most one tier.

RagManagedDbUnprovisioned

The Unprovisioned tier: disables the RAG Engine and deletes its data.

RagQuery

A query to retrieve relevant contexts.

RagQueryRanking

Configurations for hybrid search results ranking.

RagRetrievalConfig

Specifies the context retrieval config.

RagRetrievalConfigFilter

Config for filters.

RagRetrievalConfigHybridSearch

Config for Hybrid Search.

RagRetrievalConfigRanking

Config for ranking and reranking.

RagRetrievalConfigRankingLlmRanker

Config for LlmRanker.

RagRetrievalConfigRankingRankService

Config for Rank Service.

RagVectorDbConfig

Config for the Vector DB to use for RAG.

RagVectorDbConfigPinecone

The config for the Pinecone.

RagVectorDbConfigRagManagedDb

The config for the default RAG-managed Vector DB.

RagVectorDbConfigVertexFeatureStore

The config for the Vertex Feature Store.

RagVectorDbConfigVertexVectorSearch

The config for the Vertex Vector Search.

RagVectorDbConfigWeaviate

The config for the Weaviate.

SharePointSource

An individual SharePointSource.

SharePointSources

The SharePointSources to pass to ImportRagFiles.

SlackSource

The Slack source for the ImportRagFilesRequest.

SlackSourceSlackChannels

SlackChannels contains the Slack channels and corresponding access token.

SlackSourceSlackChannelsSlackChannel

SlackChannel contains the Slack channel ID and the time range to import.

UploadRagFileConfig

Config for uploading RagFile.

UploadRagFileRequest

Request message for VertexRagDataService.UploadRagFile.

UploadRagFileResponse

Response message for VertexRagDataService.UploadRagFile.

VertexAISearch

Retrieve from Vertex AI Search datastore or engine for grounding. Datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder

VertexAISearchDataStoreSpec

Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec

VertexAiSearchConfig

Config for the Vertex AI Search.

VertexRagManager

VertexRagManager provides management and interaction capabilities for RAG (Retrieval-Augmented Generation) resources. It is designed to facilitate operations involving file management and RAG corpus resources. This class serves as a specialized client built upon the BaseClient, leveraging shared functionality like authorization handling and HTTP communication. The manager provides direct access to:

  • File management operations via FileManagementClient.
  • RAG corpus operations via RagCorpusClient.
VertexRagStore

Retrieve from Vertex RAG Store for grounding.

VertexRagStoreRagResource

The definition of the Rag resource.

Enums

CorpusStatusState

Defines the possible states of a corpus within the system.

FileStatusState

Represents the state of a file in the RAG engine.

GoogleDriveSourceResourceIdResourceType

Specifies the type of Google Drive resource.

RagFileType

Specifies the type of file in the RAG engine.