This product is not supported for your selected
Datadog site. (
).
이 페이지는 아직 영어로 제공되지 않습니다. 번역 작업 중입니다.
현재 번역 프로젝트에 대한 질문이나 피드백이 있으신 경우
언제든지 연락주시기 바랍니다.aws_bedrock_evaluation_job
account_id
Type: STRING
application_type
Type: STRING
Provider name: applicationType
Description: Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
creation_time
Type: TIMESTAMP
Provider name: creationTime
Description: The time the evaluation job was created.
customer_encryption_key_id
Type: STRING
Provider name: customerEncryptionKeyId
Description: The Amazon Resource Name (ARN) of the customer managed encryption key specified when the evaluation job was created.
evaluation_config
Type: STRUCT
Provider name: evaluationConfig
Description: Contains the configuration details of either an automated or human-based evaluation job.
automated
Type: STRUCT
Provider name: automated
Description: Contains the configuration details of an automated evaluation job that computes metrics.
custom_metric_config
Type: STRUCT
Provider name: customMetricConfig
Description: Defines the configuration of custom metrics to be used in an evaluation job.
custom_metrics
Type: UNORDERED_LIST_STRUCT
Provider name: customMetrics
Description: Defines a list of custom metrics to be used in an Amazon Bedrock evaluation job.
custom_metric_definition
Type: STRUCT
Provider name: customMetricDefinition
Description: The definition of a custom metric for use in an Amazon Bedrock evaluation job.
instructions
Type: STRING
Provider name: instructions
Description: The prompt for a custom metric that instructs the evaluator model how to rate the model or RAG source under evaluation.
name
Type: STRING
Provider name: name
Description: The name for a custom metric. Names must be unique in your Amazon Web Services region.
rating_scale
Type: UNORDERED_LIST_STRUCT
Provider name: ratingScale
Description: Defines the rating scale to be used for a custom metric. We recommend that you always define a ratings scale when creating a custom metric. If you don’t define a scale, Amazon Bedrock won’t be able to visually display the results of the evaluation in the console or calculate average values of numerical scores. For more information on specifying a rating scale, see Specifying an output schema (rating scale).
definition
Type: STRING
Provider name: definition
Description: Defines the definition for one rating in a custom metric rating scale.
value
Type: STRUCT
Provider name: value
Description: Defines the value for one rating in a custom metric rating scale.
float_value
Type: FLOAT
Provider name: floatValue
Description: A floating point number representing the value for a rating in a custom metric rating scale.
string_value
Type: STRING
Provider name: stringValue
Description: A string representing the value for a rating in a custom metric rating scale.
evaluator_model_config
Type: STRUCT
Provider name: evaluatorModelConfig
Description: Configuration of the evaluator model you want to use to evaluate custom metrics in an Amazon Bedrock evaluation job.
bedrock_evaluator_models
Type: UNORDERED_LIST_STRUCT
Provider name: bedrockEvaluatorModels
Description: Defines the model you want to evaluate custom metrics in an Amazon Bedrock evaluation job.
dataset_metric_configs
Type: UNORDERED_LIST_STRUCT
Provider name: datasetMetricConfigs
Description: Configuration details of the prompt datasets and metrics you want to use for your evaluation job.
dataset
Type: STRUCT
Provider name: dataset
Description: Specifies the prompt dataset.
dataset_location
Type: STRUCT
Provider name: datasetLocation
Description: For custom prompt datasets, you must specify the location in Amazon S3 where the prompt dataset is saved.
s3_uri
Type: STRING
Provider name: s3Uri
Description: The S3 URI of the S3 bucket specified in the job.
name
Type: STRING
Provider name: name
Description: Used to specify supported built-in prompt datasets. Valid values are Builtin.Bold, Builtin.BoolQ, Builtin.NaturalQuestions, Builtin.Gigaword, Builtin.RealToxicityPrompts, Builtin.TriviaQA, Builtin.T-Rex, Builtin.WomensEcommerceClothingReviews and Builtin.Wikitext2.
metric_names
Type: UNORDERED_LIST_STRING
Provider name: metricNames
Description: The names of the metrics you want to use for your evaluation job. For knowledge base evaluation jobs that evaluate retrieval only, valid values are “Builtin.ContextRelevance”, “Builtin.ContextCoverage”. For knowledge base evaluation jobs that evaluate retrieval with response generation, valid values are “Builtin.Correctness”, “Builtin.Completeness”, “Builtin.Helpfulness”, “Builtin.LogicalCoherence”, “Builtin.Faithfulness”, “Builtin.Harmfulness”, “Builtin.Stereotyping”, “Builtin.Refusal”. For automated model evaluation jobs, valid values are “Builtin.Accuracy”, “Builtin.Robustness”, and “Builtin.Toxicity”. In model evaluation jobs that use a LLM as judge you can specify “Builtin.Correctness”, “Builtin.Completeness”, “Builtin.Faithfulness”, “Builtin.Helpfulness”, “Builtin.Coherence”, “Builtin.Relevance”, “Builtin.FollowingInstructions”, “Builtin.ProfessionalStyleAndTone”, You can also specify the following responsible AI related metrics only for model evaluation job that use a LLM as judge “Builtin.Harmfulness”, “Builtin.Stereotyping”, and “Builtin.Refusal”. For human-based model evaluation jobs, the list of strings must match the name parameter specified in HumanEvaluationCustomMetric.
task_type
Type: STRING
Provider name: taskType
Description: The the type of task you want to evaluate for your evaluation job. This applies only to model evaluation jobs and is ignored for knowledge base evaluation jobs.
evaluator_model_config
Type: STRUCT
Provider name: evaluatorModelConfig
Description: Contains the evaluator model configuration details. EvaluatorModelConfig is required for evaluation jobs that use a knowledge base or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
bedrock_evaluator_models
Type: UNORDERED_LIST_STRUCT
Provider name: bedrockEvaluatorModels
Description: The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
model_identifier
Type: STRING
Provider name: modelIdentifier
Description: The Amazon Resource Name (ARN) of the evaluator model used used in knowledge base evaluation job or in model evaluation job that use a model as judge.
human
Type: STRUCT
Provider name: human
Description: Contains the configuration details of an evaluation job that uses human workers.
custom_metrics
Type: UNORDERED_LIST_STRUCT
Provider name: customMetrics
Description: A HumanEvaluationCustomMetric object. It contains the names the metrics, how the metrics are to be evaluated, an optional description.
description
Type: STRING
Provider name: description
Description: An optional description of the metric. Use this parameter to provide more details about the metric.
name
Type: STRING
Provider name: name
Description: The name of the metric. Your human evaluators will see this name in the evaluation UI.
rating_method
Type: STRING
Provider name: ratingMethod
Description: Choose how you want your human workers to evaluation your model. Valid values for rating methods are ThumbsUpDown, IndividualLikertScale,ComparisonLikertScale, ComparisonChoice, and ComparisonRank
dataset_metric_configs
Type: UNORDERED_LIST_STRUCT
Provider name: datasetMetricConfigs
Description: Use to specify the metrics, task, and prompt dataset to be used in your model evaluation job.
dataset
Type: STRUCT
Provider name: dataset
Description: Specifies the prompt dataset.
dataset_location
Type: STRUCT
Provider name: datasetLocation
Description: For custom prompt datasets, you must specify the location in Amazon S3 where the prompt dataset is saved.
s3_uri
Type: STRING
Provider name: s3Uri
Description: The S3 URI of the S3 bucket specified in the job.
name
Type: STRING
Provider name: name
Description: Used to specify supported built-in prompt datasets. Valid values are Builtin.Bold, Builtin.BoolQ, Builtin.NaturalQuestions, Builtin.Gigaword, Builtin.RealToxicityPrompts, Builtin.TriviaQA, Builtin.T-Rex, Builtin.WomensEcommerceClothingReviews and Builtin.Wikitext2.
metric_names
Type: UNORDERED_LIST_STRING
Provider name: metricNames
Description: The names of the metrics you want to use for your evaluation job. For knowledge base evaluation jobs that evaluate retrieval only, valid values are “Builtin.ContextRelevance”, “Builtin.ContextCoverage”. For knowledge base evaluation jobs that evaluate retrieval with response generation, valid values are “Builtin.Correctness”, “Builtin.Completeness”, “Builtin.Helpfulness”, “Builtin.LogicalCoherence”, “Builtin.Faithfulness”, “Builtin.Harmfulness”, “Builtin.Stereotyping”, “Builtin.Refusal”. For automated model evaluation jobs, valid values are “Builtin.Accuracy”, “Builtin.Robustness”, and “Builtin.Toxicity”. In model evaluation jobs that use a LLM as judge you can specify “Builtin.Correctness”, “Builtin.Completeness”, “Builtin.Faithfulness”, “Builtin.Helpfulness”, “Builtin.Coherence”, “Builtin.Relevance”, “Builtin.FollowingInstructions”, “Builtin.ProfessionalStyleAndTone”, You can also specify the following responsible AI related metrics only for model evaluation job that use a LLM as judge “Builtin.Harmfulness”, “Builtin.Stereotyping”, and “Builtin.Refusal”. For human-based model evaluation jobs, the list of strings must match the name parameter specified in HumanEvaluationCustomMetric.
task_type
Type: STRING
Provider name: taskType
Description: The the type of task you want to evaluate for your evaluation job. This applies only to model evaluation jobs and is ignored for knowledge base evaluation jobs.
human_workflow_config
Type: STRUCT
Provider name: humanWorkflowConfig
Description: The parameters of the human workflow.
flow_definition_arn
Type: STRING
Provider name: flowDefinitionArn
Description: The Amazon Resource Number (ARN) for the flow definition
instructions
Type: STRING
Provider name: instructions
Description: Instructions for the flow definition
failure_messages
Type: UNORDERED_LIST_STRING
Provider name: failureMessages
Description: A list of strings that specify why the evaluation job failed to create.
inference_config
Type: STRUCT
Provider name: inferenceConfig
Description: Contains the configuration details of the inference model used for the evaluation job.
models
Type: UNORDERED_LIST_STRUCT
Provider name: models
Description: Specifies the inference models.
bedrock_model
Type: STRUCT
Provider name: bedrockModel
Description: Defines the Amazon Bedrock model or inference profile and inference parameters you want used.
inference_params
Type: STRING
Provider name: inferenceParams
Description: Each Amazon Bedrock support different inference parameters that change how the model behaves during inference.
model_identifier
Type: STRING
Provider name: modelIdentifier
Description: The ARN of the Amazon Bedrock model or inference profile specified.
performance_config
Type: STRUCT
Provider name: performanceConfig
Description: Specifies performance settings for the model or inference profile.
latency
Type: STRING
Provider name: latency
Description: Specifies whether to use the latency-optimized or standard version of a model or inference profile.
precomputed_inference_source
Type: STRUCT
Provider name: precomputedInferenceSource
Description: Defines the model used to generate inference response data for a model evaluation job where you provide your own inference response data.
inference_source_identifier
Type: STRING
Provider name: inferenceSourceIdentifier
Description: A label that identifies a model used in a model evaluation job where you provide your own inference response data.
rag_configs
Type: UNORDERED_LIST_STRUCT
Provider name: ragConfigs
Description: Contains the configuration details of the inference for a knowledge base evaluation job, including either the retrieval only configuration or the retrieval with response generation configuration.
knowledge_base_config
Type: STRUCT
Provider name: knowledgeBaseConfig
Description: Contains configuration details for knowledge base retrieval and response generation.
retrieve_and_generate_config
Type: STRUCT
Provider name: retrieveAndGenerateConfig
Description: Contains configuration details for retrieving information from a knowledge base and generating responses.
external_sources_configuration
Type: STRUCT
Provider name: externalSourcesConfiguration
Description: The configuration for the external source wrapper object in the retrieveAndGenerate function.
generation_configuration
Type: STRUCT
Provider name: generationConfiguration
Description: Contains configurations details for response generation based on retrieved text chunks.
additional_model_request_fields
Type: STRING
Provider name: additionalModelRequestFields
Description: Additional model parameters and their corresponding values not included in the text inference configuration for an external source. Takes in custom model parameters specific to the language model being used.
guardrail_configuration
Type: STRUCT
Provider name: guardrailConfiguration
Description: Configuration details for the guardrail.
guardrail_id
Type: STRING
Provider name: guardrailId
Description: The unique identifier for the guardrail.
guardrail_version
Type: STRING
Provider name: guardrailVersion
Description: The version of the guardrail.
kb_inference_config
Type: STRUCT
Provider name: kbInferenceConfig
Description: Configuration details for inference when using RetrieveAndGenerate to generate responses while using an external source.
text_inference_config
Type: STRUCT
Provider name: textInferenceConfig
Description: Contains configuration details for text generation using a language model via the RetrieveAndGenerate function.
max_tokens
Type: INT32
Provider name: maxTokens
Description: 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 arbitrary values, for actual values consult the limits defined by your specific model.
stop_sequences
Type: UNORDERED_LIST_STRING
Provider name: stopSequences
Description: 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 arbitrary values, for actual values consult the limits defined by your specific model.
temperature
Type: FLOAT
Provider name: temperature
Description: 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.
top_p
Type: FLOAT
Provider name: topP
Description: 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.
prompt_template
Type: STRUCT
Provider name: promptTemplate
Description: Contains the template for the prompt for the external source wrapper object.
text_prompt_template
Type: STRING
Provider name: textPromptTemplate
Description: 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 Knowledge base prompt template and Use XML tags with Anthropic Claude models.
model_arn
Type: STRING
Provider name: modelArn
Description: The Amazon Resource Name (ARN) of the foundation model or inference profile used to generate responses.
sources
Type: UNORDERED_LIST_STRUCT
Provider name: sources
Description: The document for the external source wrapper object in the retrieveAndGenerate function.
byte_content
Type: STRUCT
Provider name: byteContent
Description: The identifier, content type, and data of the external source wrapper object.
content_type
Type: STRING
Provider name: contentType
Description: The MIME type of the document contained in the wrapper object.
identifier
Type: STRING
Provider name: identifier
Description: The file name of the document contained in the wrapper object.
s3_location
Type: STRUCT
Provider name: s3Location
Description: The S3 location of the external source wrapper object.
uri
Type: STRING
Provider name: uri
Description: The S3 URI location for the wrapper object of the document.
source_type
Type: STRING
Provider name: sourceType
Description: The source type of the external source wrapper object.
knowledge_base_configuration
Type: STRUCT
Provider name: knowledgeBaseConfiguration
Description: Contains configuration details for the knowledge base retrieval and response generation.
generation_configuration
Type: STRUCT
Provider name: generationConfiguration
Description: Contains configurations details for response generation based on retrieved text chunks.
additional_model_request_fields
Type: STRING
Provider name: additionalModelRequestFields
Description: Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows you to provide custom model parameters specific to the language model being used.
guardrail_configuration
Type: STRUCT
Provider name: guardrailConfiguration
Description: Contains configuration details for the guardrail.
guardrail_id
Type: STRING
Provider name: guardrailId
Description: The unique identifier for the guardrail.
guardrail_version
Type: STRING
Provider name: guardrailVersion
Description: The version of the guardrail.
kb_inference_config
Type: STRUCT
Provider name: kbInferenceConfig
Description: Contains configuration details for inference for knowledge base retrieval and response generation.
text_inference_config
Type: STRUCT
Provider name: textInferenceConfig
Description: Contains configuration details for text generation using a language model via the RetrieveAndGenerate function.
max_tokens
Type: INT32
Provider name: maxTokens
Description: 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 arbitrary values, for actual values consult the limits defined by your specific model.
stop_sequences
Type: UNORDERED_LIST_STRING
Provider name: stopSequences
Description: 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 arbitrary values, for actual values consult the limits defined by your specific model.
temperature
Type: FLOAT
Provider name: temperature
Description: 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.
top_p
Type: FLOAT
Provider name: topP
Description: 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.
prompt_template
Type: STRUCT
Provider name: promptTemplate
Description: Contains the template for the prompt that’s sent to the model for response generation.
text_prompt_template
Type: STRING
Provider name: textPromptTemplate
Description: 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 Knowledge base prompt template and Use XML tags with Anthropic Claude models.
knowledge_base_id
Type: STRING
Provider name: knowledgeBaseId
Description: The unique identifier of the knowledge base.
model_arn
Type: STRING
Provider name: modelArn
Description: The Amazon Resource Name (ARN) of the foundation model or inference profile used to generate responses.
orchestration_configuration
Type: STRUCT
Provider name: orchestrationConfiguration
Description: Contains configuration details for the model to process the prompt prior to retrieval and response generation.
query_transformation_configuration
Type: STRUCT
Provider name: queryTransformationConfiguration
Description: Contains configuration details for transforming the prompt.
type
Type: STRING
Provider name: type
Description: The type of transformation to apply to the prompt.
retrieval_configuration
Type: STRUCT
Provider name: retrievalConfiguration
Description: Contains configuration details for retrieving text chunks.
vector_search_configuration
Type: STRUCT
Provider name: vectorSearchConfiguration
Description: Contains configuration details for returning the results from the vector search.
filter
Type: STRUCT
Provider name: filter
Description: Specifies the filters to use on the metadata fields in the knowledge base data sources before returning results.
and_all
Type: UNORDERED_LIST_STRING
Provider name: andAll
Description: Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
equals
Type: STRUCT
Provider name: equals
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object. The following example would return data sources with an animal attribute whose value is ‘cat’: “equals”: { “key”: “animal”, “value”: “cat” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
greater_than
Type: STRUCT
Provider name: greaterThan
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object. The following example would return data sources with an year attribute whose value is greater than ‘1989’: “greaterThan”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
greater_than_or_equals
Type: STRUCT
Provider name: greaterThanOrEquals
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object. The following example would return data sources with an year attribute whose value is greater than or equal to ‘1989’: “greaterThanOrEquals”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
in
Type: STRUCT
Provider name: in
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object. The following example would return data sources with an animal attribute that is either ‘cat’ or ‘dog’: “in”: { “key”: “animal”, “value”: [“cat”, “dog”] }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
less_than
Type: STRUCT
Provider name: lessThan
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object. The following example would return data sources with an year attribute whose value is less than to ‘1989’: “lessThan”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
less_than_or_equals
Type: STRUCT
Provider name: lessThanOrEquals
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object. The following example would return data sources with an year attribute whose value is less than or equal to ‘1989’: “lessThanOrEquals”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
list_contains
Type: STRUCT
Provider name: listContains
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members. The following example would return data sources with an animals attribute that is a list containing a cat member (for example, [“dog”, “cat”]): “listContains”: { “key”: “animals”, “value”: “cat” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
not_equals
Type: STRUCT
Provider name: notEquals
Description: Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn’t match the value in this object are returned. The following example would return data sources that don’t contain an animal attribute whose value is ‘cat’: “notEquals”: { “key”: “animal”, “value”: “cat” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
not_in
Type: STRUCT
Provider name: notIn
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn’t in the list specified in the value in this object. The following example would return data sources whose animal attribute is neither ‘cat’ nor ‘dog’: “notIn”: { “key”: “animal”, “value”: [“cat”, “dog”] }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
or_all
Type: UNORDERED_LIST_STRING
Provider name: orAll
Description: Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
starts_with
Type: STRUCT
Provider name: startsWith
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores. The following example would return data sources with an animal attribute starts with ‘ca’ (for example, ‘cat’ or ‘camel’). “startsWith”: { “key”: “animal”, “value”: “ca” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
string_contains
Type: STRUCT
Provider name: stringContains
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following: A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example, ‘cat’): “stringContains”: { “key”: “animal”, “value”: “at” } A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example, [“dog”, “cat”]): “stringContains”: { “key”: “animals”, “value”: “at” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
number_of_results
Type: INT32
Provider name: numberOfResults
Description: The number of text chunks to retrieve; the number of results to return.
override_search_type
Type: STRING
Provider name: overrideSearchType
Description: 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.
type
Type: STRING
Provider name: type
Description: The type of resource that contains your data for retrieving information and generating responses. If you choose to use EXTERNAL_SOURCES, then currently only Claude 3 Sonnet models for knowledge bases are supported.
retrieve_config
Type: STRUCT
Provider name: retrieveConfig
Description: Contains configuration details for retrieving information from a knowledge base.
knowledge_base_id
Type: STRING
Provider name: knowledgeBaseId
Description: The unique identifier of the knowledge base.
knowledge_base_retrieval_configuration
Type: STRUCT
Provider name: knowledgeBaseRetrievalConfiguration
Description: Contains configuration details for knowledge base retrieval.
vector_search_configuration
Type: STRUCT
Provider name: vectorSearchConfiguration
Description: Contains configuration details for returning the results from the vector search.
filter
Type: STRUCT
Provider name: filter
Description: Specifies the filters to use on the metadata fields in the knowledge base data sources before returning results.
and_all
Type: UNORDERED_LIST_STRING
Provider name: andAll
Description: Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
equals
Type: STRUCT
Provider name: equals
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object. The following example would return data sources with an animal attribute whose value is ‘cat’: “equals”: { “key”: “animal”, “value”: “cat” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
greater_than
Type: STRUCT
Provider name: greaterThan
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object. The following example would return data sources with an year attribute whose value is greater than ‘1989’: “greaterThan”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
greater_than_or_equals
Type: STRUCT
Provider name: greaterThanOrEquals
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object. The following example would return data sources with an year attribute whose value is greater than or equal to ‘1989’: “greaterThanOrEquals”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
in
Type: STRUCT
Provider name: in
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object. The following example would return data sources with an animal attribute that is either ‘cat’ or ‘dog’: “in”: { “key”: “animal”, “value”: [“cat”, “dog”] }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
less_than
Type: STRUCT
Provider name: lessThan
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object. The following example would return data sources with an year attribute whose value is less than to ‘1989’: “lessThan”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
less_than_or_equals
Type: STRUCT
Provider name: lessThanOrEquals
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object. The following example would return data sources with an year attribute whose value is less than or equal to ‘1989’: “lessThanOrEquals”: { “key”: “year”, “value”: 1989 }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
list_contains
Type: STRUCT
Provider name: listContains
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members. The following example would return data sources with an animals attribute that is a list containing a cat member (for example, [“dog”, “cat”]): “listContains”: { “key”: “animals”, “value”: “cat” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
not_equals
Type: STRUCT
Provider name: notEquals
Description: Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn’t match the value in this object are returned. The following example would return data sources that don’t contain an animal attribute whose value is ‘cat’: “notEquals”: { “key”: “animal”, “value”: “cat” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
not_in
Type: STRUCT
Provider name: notIn
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn’t in the list specified in the value in this object. The following example would return data sources whose animal attribute is neither ‘cat’ nor ‘dog’: “notIn”: { “key”: “animal”, “value”: [“cat”, “dog”] }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
or_all
Type: UNORDERED_LIST_STRING
Provider name: orAll
Description: Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
starts_with
Type: STRUCT
Provider name: startsWith
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores. The following example would return data sources with an animal attribute starts with ‘ca’ (for example, ‘cat’ or ‘camel’). “startsWith”: { “key”: “animal”, “value”: “ca” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
string_contains
Type: STRUCT
Provider name: stringContains
Description: Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following: A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example, ‘cat’): “stringContains”: { “key”: “animal”, “value”: “at” } A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example, [“dog”, “cat”]): “stringContains”: { “key”: “animals”, “value”: “at” }
key
Type: STRING
Provider name: key
Description: The name of metadata attribute/field, which must match the name in your data source/document metadata.
value
Type: STRUCT
Provider name: value
Description: The value of the metadata attribute/field.
number_of_results
Type: INT32
Provider name: numberOfResults
Description: The number of text chunks to retrieve; the number of results to return.
override_search_type
Type: STRING
Provider name: overrideSearchType
Description: 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.
precomputed_rag_source_config
Type: STRUCT
Provider name: precomputedRagSourceConfig
Description: Contains configuration details about the RAG source used to generate inference response data for a Knowledge Base evaluation job.
retrieve_and_generate_source_config
Type: STRUCT
Provider name: retrieveAndGenerateSourceConfig
Description: A summary of a RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.
rag_source_identifier
Type: STRING
Provider name: ragSourceIdentifier
Description: A label that identifies the RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.
retrieve_source_config
Type: STRUCT
Provider name: retrieveSourceConfig
Description: A summary of a RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.
rag_source_identifier
Type: STRING
Provider name: ragSourceIdentifier
Description: A label that identifies the RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.
job_arn
Type: STRING
Provider name: jobArn
Description: The Amazon Resource Name (ARN) of the evaluation job.
job_description
Type: STRING
Provider name: jobDescription
Description: The description of the evaluation job.
job_name
Type: STRING
Provider name: jobName
Description: The name for the evaluation job.
job_type
Type: STRING
Provider name: jobType
Description: Specifies whether the evaluation job is automated or human-based.
last_modified_time
Type: TIMESTAMP
Provider name: lastModifiedTime
Description: The time the evaluation job was last modified.
output_data_config
Type: STRUCT
Provider name: outputDataConfig
Description: Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.
s3_uri
Type: STRING
Provider name: s3Uri
Description: The Amazon S3 URI where the results of the evaluation job are saved.
role_arn
Type: STRING
Provider name: roleArn
Description: The Amazon Resource Name (ARN) of the IAM service role used in the evaluation job.
status
Type: STRING
Provider name: status
Description: The current status of the evaluation job.
Type: UNORDERED_LIST_STRING
