String resourceName
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
String contentType
The MIME type of the document contained in the wrapper object.
ByteBuffer data
The byte value of the file to upload, encoded as a Base-64 string.
String identifier
The file name of the document contained in the wrapper object.
GeneratedResponsePart generatedResponsePart
Contains the generated response and metadata
List<E> retrievedReferences
Contains metadata about the sources cited for the generated response.
String resourceName
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
ByteContentDoc byteContent
The identifier, contentType, and data of the external source wrapper object.
S3ObjectDoc s3Location
The S3 location of the external source wrapper object.
String sourceType
The source type of the external source wrapper object.
GuardrailConfiguration guardrailConfiguration
The configuration details for the guardrail.
InferenceConfig inferenceConfig
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using an external source.
PromptTemplate promptTemplate
Contain the textPromptTemplate string for the external source wrapper object.
ExternalSourcesGenerationConfiguration generationConfiguration
The prompt used with the external source wrapper object with the retrieveAndGenerate function.
String modelArn
The modelArn used with the external source wrapper object in the retrieveAndGenerate function.
List<E> sources
The document used with the external source wrapper object in the retrieveAndGenerate function.
TextResponsePart textResponsePart
Contains metadata about a textual part of the generated response that is accompanied by a citation.
GuardrailConfiguration guardrailConfiguration
The configuration details for the guardrail.
InferenceConfig inferenceConfig
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
PromptTemplate promptTemplate
Contains the template for the prompt that's sent to the model for response generation.
TextInferenceConfig textInferenceConfig
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
String text
The text of the query made to the knowledge base.
KnowledgeBaseVectorSearchConfiguration vectorSearchConfiguration
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
RetrievalResultContent content
Contains a chunk of text from a data source in the knowledge base.
RetrievalResultLocation location
Contains information about the location of the data source.
Double score
The level of relevance of the result to the query.
GenerationConfiguration generationConfiguration
Contains configurations for response generation based on the knowwledge base query results.
String knowledgeBaseId
The unique identifier of the knowledge base that is queried and the foundation model used for generation.
String modelArn
The ARN of the foundation model used to generate a response.
KnowledgeBaseRetrievalConfiguration retrievalConfiguration
Contains configurations for how to retrieve and return the knowledge base query.
RetrievalFilter filter
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
Integer numberOfResults
The number of source chunks to retrieve.
String overrideSearchType
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless
vector store that contains a filterable text field, you can specify whether to query the knowledge base with a
HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only
vector embeddings. For other vector store configurations, only SEMANTIC search is available. For
more information, see Test a knowledge base.
String textPromptTemplate
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
String text
The cited text from the data source.
RetrievalResultS3Location s3Location
Contains the S3 location of the data source.
String type
The type of the location of the data source.
String uri
The S3 URI of the data source.
ExternalSourcesRetrieveAndGenerateConfiguration externalSourcesConfiguration
The configuration used with the external source wrapper object in the retrieveAndGenerate function.
KnowledgeBaseRetrieveAndGenerateConfiguration knowledgeBaseConfiguration
Contains details about the resource being queried.
String type
The type of resource that is queried by the request.
String text
The query made to the knowledge base.
String text
The response generated from querying the knowledge base.
RetrieveAndGenerateInput input
Contains the query to be made to the knowledge base.
RetrieveAndGenerateConfiguration retrieveAndGenerateConfiguration
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
RetrieveAndGenerateSessionConfiguration sessionConfiguration
Contains details about the session with the knowledge base.
String sessionId
The unique identifier of the session. Reuse the same value to continue the same session with the knowledge base.
List<E> citations
A list of segments of the generated response that are based on sources in the knowledge base, alongside information about the sources.
String guardrailAction
Specifies if there is a guardrail intervention in the response.
RetrieveAndGenerateOutput output
Contains the response generated from querying the knowledge base.
String sessionId
The unique identifier of the session. Reuse the same value to continue the same session with the knowledge base.
String kmsKeyArn
The ARN of the KMS key encrypting the session.
RetrievalResultContent content
Contains the cited text from the data source.
RetrievalResultLocation location
Contains information about the location of the data source.
String knowledgeBaseId
The unique identifier of the knowledge base to query.
String nextToken
If there are more results than can fit in the response, the response returns a nextToken. Use this
token in the nextToken field of another request to retrieve the next batch of results.
KnowledgeBaseRetrievalConfiguration retrievalConfiguration
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
KnowledgeBaseQuery retrievalQuery
Contains the query to send the knowledge base.
String nextToken
If there are more results than can fit in the response, the response returns a nextToken. Use this
token in the nextToken field of another request to retrieve the next batch of results.
List<E> retrievalResults
A list of results from querying the knowledge base.
String uri
The file location of the S3 wrapper object.
Integer maxTokens
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
List<E> stopSequences
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
Float temperature
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
Float topP
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
Copyright © 2024. All rights reserved.