--- title: "GET /knowledgebases/{knowledgeBaseId}" method: GET path: "/knowledgebases/{knowledgeBaseId}" --- # GET /knowledgebases/{knowledgeBaseId} `GET /knowledgebases/{knowledgeBaseId}` Gets information about a knowledge base. ## Path parameters - `knowledgeBaseId` string, required ## Response `200` Success - GetKnowledgeBaseResponse - `knowledgeBase` object, required — Contains details about the knowledge base. - `knowledgeBaseId` string, required — The unique identifier of the knowledge base. - `name` string, required — The name of the knowledge base. - `knowledgeBaseArn` string, required — The Amazon Resource Name (ARN) of the knowledge base. - `description` string — The description of the knowledge base. - `roleArn` string, required — The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base. - `knowledgeBaseConfiguration` object, required — Contains details about the embeddings configuration of the knowledge base. - `type` 'VECTOR' | 'KENDRA' | 'SQL' | 'MANAGED', required — The type of data that the data source is converted into for the knowledge base. Choose MANAGED to create a managed knowledge base. - `vectorKnowledgeBaseConfiguration` object — Contains details about the model that's used to convert the data source into vector embeddings. - `embeddingModelArn` string, required — The Amazon Resource Name (ARN) of the model used to create vector embeddings for the knowledge base. - `embeddingModelConfiguration` object — The embeddings model configuration details for the vector model used in Knowledge Base. - `bedrockEmbeddingModelConfiguration` object — The vector configuration details on the Bedrock embeddings model. - `dimensions` integer — The dimensions details for the vector configuration used on the Bedrock embeddings model. - `embeddingDataType` 'FLOAT32' | 'BINARY' — The data type for the vectors when using a model to convert text into vector embeddings. The model must support the specified data type for vector embeddings. Floating-point (float32) is the default data type, and is supported by most models for vector embeddings. See Supported embeddings models for information on the available models and their vector data types. - `audio` object[] — Configuration settings for processing audio content in multimodal knowledge bases. - … - `video` object[] — Configuration settings for processing video content in multimodal knowledge bases. - … - `supplementalDataStorageConfiguration` object — If you include multimodal data from your data source, use this object to specify configurations for the storage location of the images extracted from your documents. These images can be retrieved and returned to the end user. They can also be used in generation when using RetrieveAndGenerate. - `storageLocations` SupplementalDataStorageLocation[], required — A list of objects specifying storage locations for multimedia content (images, audio, and video) extracted from multimodal documents in your data source. - `type` 'S3', required — Specifies the storage service used for this location. - `s3Location` object — Contains information about the Amazon S3 location for the extracted multimedia content. - … - `managedKnowledgeBaseConfiguration` ManagedKnowledgeBaseConfiguration — Configurations for a managed knowledge base. - `embeddingModelType` 'CUSTOM' | 'MANAGED' — Choose CUSTOM to provide your own Bedrock embedding model ARN. Choose MANAGED to use a service-managed embedding model. For more information, see Embedding model options. - `embeddingModelArn` string — The ARN for the embeddings model. - `embeddingModelConfiguration` EmbeddingModelConfiguration — The configuration details for the embeddings model. - `bedrockEmbeddingModelConfiguration` object — The vector configuration details on the Bedrock embeddings model. - `dimensions` integer — The dimensions details for the vector configuration used on the Bedrock embeddings model. - `embeddingDataType` 'FLOAT32' | 'BINARY' — The data type for the vectors when using a model to convert text into vector embeddings. The model must support the specified data type for vector embeddings. Floating-point (float32) is the default data type, and is supported by most models for vector embeddings. See Supported embeddings models for information on the available models and their vector data types. - `audio` object[] — Configuration settings for processing audio content in multimodal knowledge bases. - … - `video` object[] — Configuration settings for processing video content in multimodal knowledge bases. - … - `serverSideEncryptionConfiguration` ServerSideEncryptionConfiguration — Contains the configuration for server-side encryption for your managed knowledge base. - `kmsKeyArn` string — The Amazon Resource Name (ARN) of the KMS key used to encrypt the resource. - `kendraKnowledgeBaseConfiguration` object — Settings for an Amazon Kendra knowledge base. - `kendraIndexArn` string, required — The ARN of the Amazon Kendra index. - `sqlKnowledgeBaseConfiguration` object — Specifies configurations for a knowledge base connected to an SQL database. - `type` 'REDSHIFT', required — The type of SQL database to connect to the knowledge base. - `redshiftConfiguration` object — Specifies configurations for a knowledge base connected to an Amazon Redshift database. - `storageConfigurations` RedshiftQueryEngineStorageConfiguration[], required — Specifies configurations for Amazon Redshift database storage. - `type` 'REDSHIFT' | 'AWS_DATA_CATALOG', required — The data storage service to use. - `awsDataCatalogConfiguration` object — Specifies configurations for storage in Glue Data Catalog. - … - `redshiftConfiguration` object — Specifies configurations for storage in Amazon Redshift. - … - `queryEngineConfiguration` object, required — Specifies configurations for an Amazon Redshift query engine. - `type` 'SERVERLESS' | 'PROVISIONED', required — The type of query engine. - `serverlessConfiguration` object — Specifies configurations for a serverless Amazon Redshift query engine. - … - `provisionedConfiguration` object — Specifies configurations for a provisioned Amazon Redshift query engine. - … - `queryGenerationConfiguration` object — Specifies configurations for generating queries. - `executionTimeoutSeconds` integer — The time after which query generation will time out. - `generationContext` object — Specifies configurations for context to use during query generation. - … - `storageConfiguration` object — Contains details about the storage configuration of the knowledge base. - `type` 'OPENSEARCH_SERVERLESS' | 'PINECONE' | 'REDIS_ENTERPRISE_CLOUD' | 'RDS' | 'MONGO_DB_ATLAS' | 'NEPTUNE_ANALYTICS' | 'OPENSEARCH_MANAGED_CLUSTER' | 'S3_VECTORS', required — The vector store service in which the knowledge base is stored. - `opensearchServerlessConfiguration` object — Contains the storage configuration of the knowledge base in Amazon OpenSearch Service. - `collectionArn` string, required — The Amazon Resource Name (ARN) of the OpenSearch Service vector store. - `vectorIndexName` string, required — The name of the vector store. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `vectorField` string, required — The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `opensearchManagedClusterConfiguration` object — Contains details about the storage configuration of the knowledge base in OpenSearch Managed Cluster. For more information, see Create a vector index in Amazon OpenSearch Service. - `domainEndpoint` string, required — The endpoint URL the OpenSearch domain. - `domainArn` string, required — The Amazon Resource Name (ARN) of the OpenSearch domain. - `vectorIndexName` string, password, required — The name of the vector store. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `vectorField` string, required — The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `pineconeConfiguration` object — Contains the storage configuration of the knowledge base in Pinecone. - `connectionString` string, required — The endpoint URL for your index management page. - `credentialsSecretArn` string, required — The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that is linked to your Pinecone API key. - `namespace` string — The namespace to be used to write new data to your database. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `redisEnterpriseCloudConfiguration` object — Contains the storage configuration of the knowledge base in Redis Enterprise Cloud. - `endpoint` string, required — The endpoint URL of the Redis Enterprise Cloud database. - `vectorIndexName` string, required — The name of the vector index. - `credentialsSecretArn` string, required — The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that is linked to your Redis Enterprise Cloud database. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `vectorField` string, required — The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `rdsConfiguration` object — Contains details about the storage configuration of the knowledge base in Amazon RDS. For more information, see Create a vector index in Amazon RDS. - `resourceArn` string, required — The Amazon Resource Name (ARN) of the vector store. - `credentialsSecretArn` string, required — The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that is linked to your Amazon RDS database. - `databaseName` string, required — The name of your Amazon RDS database. - `tableName` string, required — The name of the table in the database. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `primaryKeyField` string, required — The name of the field in which Amazon Bedrock stores the ID for each entry. - `vectorField` string, required — The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `customMetadataField` string — Provide a name for the universal metadata field where Amazon Bedrock will store any custom metadata from your data source. - `mongoDbAtlasConfiguration` object — Contains the storage configuration of the knowledge base in MongoDB Atlas. - `endpoint` string, required — The endpoint URL of your MongoDB Atlas cluster for your knowledge base. - `databaseName` string, required — The database name in your MongoDB Atlas cluster for your knowledge base. - `collectionName` string, required — The collection name of the knowledge base in MongoDB Atlas. - `vectorIndexName` string, required — The name of the MongoDB Atlas vector search index. - `credentialsSecretArn` string, required — The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that contains user credentials for your MongoDB Atlas cluster. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `vectorField` string, required — The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `endpointServiceName` string — The name of the VPC endpoint service in your account that is connected to your MongoDB Atlas cluster. - `textIndexName` string — The name of the text search index in the MongoDB collection. This is required for using the hybrid search feature. - `neptuneAnalyticsConfiguration` object — Contains details about the Neptune Analytics configuration of the knowledge base in Amazon Neptune. For more information, see Create a vector index in Amazon Neptune Analytics.. - `graphArn` string, password, required — The Amazon Resource Name (ARN) of the Neptune Analytics vector store. - `fieldMapping` object, required — Contains the names of the fields to which to map information about the vector store. - `textField` string, required — The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose. - `metadataField` string, required — The name of the field in which Amazon Bedrock stores metadata about the vector store. - `s3VectorsConfiguration` object — The configuration settings for storing knowledge base data using S3 vectors. This includes vector index information and S3 bucket details for vector storage. - `vectorBucketArn` string, password — The Amazon Resource Name (ARN) of the S3 bucket where vector embeddings are stored. This bucket contains the vector data used by the knowledge base. - `indexArn` string, password — The Amazon Resource Name (ARN) of the vector index used for the knowledge base. This ARN identifies the specific vector index resource within Amazon Bedrock. - `indexName` string, password — The name of the vector index used for the knowledge base. This name identifies the vector index within the Amazon Bedrock service. - `status` 'CREATING' | 'ACTIVE' | 'DELETING' | 'UPDATING' | 'FAILED' | 'DELETE_UNSUCCESSFUL' | 'UPDATE_UNSUCCESSFUL', required —

The status of the knowledge base. The following statuses are possible:

- `createdAt` string, date-time, required — The time the knowledge base was created. - `updatedAt` string, date-time, required — The time the knowledge base was last updated. - `failureReasons` FailureReason[] — A list of reasons that the API operation on the knowledge base failed. ## Other responses - `480` — ThrottlingException - `481` — AccessDeniedException - `482` — ValidationException - `483` — InternalServerException - `484` — ResourceNotFoundException --- [API](https://skmtc.net/aws/apis/bedrock-agent.md) · [All operations](https://skmtc.net/aws/apis/bedrock-agent/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aws/bedrock-agent/versions/a3b2356f17da/schema)