AWS cli documentation change
Summary
Updated CLI version reference from 2.31.1 to 2.31.3
Security assessment
Routine version number update without any security-specific context or vulnerability references
Diff
diff --git a/cli/latest/reference/bedrock-agent-runtime/retrieve-and-generate.md b/cli/latest/reference/bedrock-agent-runtime/retrieve-and-generate.md index 36b9e0b6d..6b244f9af 100644 --- a//cli/latest/reference/bedrock-agent-runtime/retrieve-and-generate.md +++ b//cli/latest/reference/bedrock-agent-runtime/retrieve-and-generate.md @@ -15 +15 @@ - * [AWS CLI 2.31.1 Command Reference](../../index.html) » + * [AWS CLI 2.31.3 Command Reference](../../index.html) » @@ -68,0 +69 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc + [--session-id <value>] @@ -72 +72,0 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc - [--session-id <value>] @@ -96,0 +97,12 @@ See also: [AWS API Documentation](https://docs.aws.amazon.com/goto/WebAPI/bedroc +`--session-id` (string) + +> The unique identifier of the session. When you first make a `RetrieveAndGenerate` request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can’t explicitly set the `sessionId` yourself. +> +> Constraints: +> +> * min: `2` +> * max: `100` +> * pattern: `[0-9a-zA-Z._:-]+` +> + + @@ -130 +142 @@ JSON Syntax: -> externalSourcesConfiguration -> (structure) +> type -> (string) [required] @@ -132 +144 @@ JSON Syntax: ->> The configuration for the external source wrapper object in the `retrieveAndGenerate` function. +>> The type of resource that contains your data for retrieving information and generating responses. @@ -134 +146 @@ JSON Syntax: ->> generationConfiguration -> (structure) +>> ### Note @@ -136 +148,16 @@ JSON Syntax: ->>> The prompt used with the external source wrapper object with the `retrieveAndGenerate` function. +>> If you choose to use `EXTERNAL_SOURCES` , then currently only Anthropic Claude 3 Sonnet models for knowledge bases are supported. +>> +>> Possible values: +>> +>> * `KNOWLEDGE_BASE` +>> * `EXTERNAL_SOURCES` +>> + +> +> knowledgeBaseConfiguration -> (structure) +> +>> Contains details about the knowledge base for retrieving information and generating responses. +>> +>> knowledgeBaseId -> (string) [required] +>> +>>> The unique identifier of the knowledge base that is queried. @@ -138 +165,5 @@ JSON Syntax: ->>> additionalModelRequestFields -> (map) +>>> Constraints: +>>> +>>> * min: `0` +>>> * max: `10` +>>> * pattern: `[0-9a-zA-Z]+` @@ -140,9 +170,0 @@ JSON Syntax: ->>>> Additional model parameters and their corresponding values not included in the textInferenceConfig structure for an external source. Takes in custom model parameters specific to the language model being used. ->>>> ->>>> key -> (string) ->>>> ->>>>> Constraints: ->>>>> ->>>>> * min: `1` ->>>>> * max: `100` ->>>>> @@ -150,2 +172,4 @@ JSON Syntax: ->>>> ->>>> value -> (document) +>> +>> modelArn -> (string) [required] +>> +>>> The ARN of the foundation model or [inference profile](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html) used to generate a response. @@ -153 +177 @@ JSON Syntax: ->>> guardrailConfiguration -> (structure) +>>> Constraints: @@ -155 +179,13 @@ JSON Syntax: ->>>> The configuration details for the guardrail. +>>> * min: `1` +>>> * max: `2048` +>>> * pattern: `(arn:aws(-[^:]+)?:(bedrock|sagemaker):[a-z0-9-]{1,20}:([0-9]{12})?:([a-z-]+/)?)?([a-z0-9.-]{1,63}){0,2}(([:][a-z0-9-]{1,63}){0,2})?(/[a-z0-9]{1,12})?` +>>> + +>> +>> retrievalConfiguration -> (structure) +>> +>>> Contains configurations for how to retrieve and return the knowledge base query. +>>> +>>> vectorSearchConfiguration -> (structure) [required] +>>> +>>>> Contains details about how the results from the vector search should be returned. For more information, see [Query configurations](https://docs.aws.amazon.com/bedrock/latest/userguide/kb-test-config.html) . @@ -157 +193 @@ JSON Syntax: ->>>> guardrailId -> (string) [required] +>>>> numberOfResults -> (integer) @@ -159 +195 @@ JSON Syntax: ->>>>> The unique identifier for the guardrail. +>>>>> The number of source chunks to retrieve. @@ -163,3 +199,2 @@ JSON Syntax: ->>>>> * min: `0` ->>>>> * max: `64` ->>>>> * pattern: `^[a-z0-9]+$` +>>>>> * min: `1` +>>>>> * max: `100` @@ -169 +204 @@ JSON Syntax: ->>>> guardrailVersion -> (string) [required] +>>>> overrideSearchType -> (string) @@ -171 +206 @@ JSON Syntax: ->>>>> The version of the guardrail. +>>>>> By default, Amazon Bedrock decides a search strategy for you. If you’re using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a `HYBRID` search using both vector embeddings and raw text, or `SEMANTIC` search using only vector embeddings. For other vector store configurations, only `SEMANTIC` search is available. For more information, see [Test a knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-test.html) . @@ -173 +208 @@ JSON Syntax: ->>>>> Constraints: +>>>>> Possible values: @@ -175,3 +210,2 @@ JSON Syntax: ->>>>> * min: `1` ->>>>> * max: `5` ->>>>> * pattern: `^(([1-9][0-9]{0,7})|(DRAFT))$` +>>>>> * `HYBRID` +>>>>> * `SEMANTIC` @@ -180,4 +213,0 @@ JSON Syntax: ->>> ->>> inferenceConfig -> (structure) ->>> ->>>> Configuration settings for inference when using RetrieveAndGenerate to generate responses while using an external source. @@ -185 +215 @@ JSON Syntax: ->>>> textInferenceConfig -> (structure) +>>>> filter -> (tagged union structure) @@ -187 +217 @@ JSON Syntax: ->>>>> Configuration settings specific to text generation while generating responses using RetrieveAndGenerate. +>>>>> Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see [Query configurations](https://docs.aws.amazon.com/bedrock/latest/userguide/kb-test-config.html) . @@ -189 +219 @@ JSON Syntax: ->>>>> maxTokens -> (integer) +>>>>> ### Note @@ -191 +221,5 @@ JSON Syntax: ->>>>>> 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. +>>>>> This is a Tagged Union structure. Only one of the following top level keys can be set: `equals`, `notEquals`, `greaterThan`, `greaterThanOrEquals`, `lessThan`, `lessThanOrEquals`, `in`, `notIn`, `startsWith`, `listContains`, `stringContains`, `andAll`, `orAll`. +>>>>> +>>>>> equals -> (structure) +>>>>> +>>>>>> 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. @@ -193 +227 @@ JSON Syntax: ->>>>>> Constraints: +>>>>>> The following example would return data sources with an `animal` attribute whose value is `cat` : @@ -195,2 +229,3 @@ JSON Syntax: ->>>>>> * min: `0` ->>>>>> * max: `65536` +>>>>>>> `"equals": { "key": "animal", "value": "cat" }` +>>>>>> +>>>>>> key -> (string) [required] @@ -197,0 +233,7 @@ JSON Syntax: +>>>>>>> The name that the metadata attribute must match. +>>>>>>> +>>>>>>> Constraints: +>>>>>>> +>>>>>>> * min: `1` +>>>>>>> * max: `100` +>>>>>>> @@ -198,0 +241,4 @@ JSON Syntax: +>>>>>> +>>>>>> value -> (document) [required] +>>>>>> +>>>>>>> The value to whcih to compare the value of the metadata attribute. @@ -200 +246 @@ JSON Syntax: ->>>>> stopSequences -> (list) +>>>>> notEquals -> (structure) @@ -202,3 +248 @@ JSON Syntax: ->>>>>> 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. ->>>>>> ->>>>>> Constraints: +>>>>>> Knowledge base data sources are returned when: @@ -206,2 +250,2 @@ JSON Syntax: ->>>>>> * min: `0` ->>>>>> * max: `4` +>>>>>> * It contains a metadata attribute whose name matches the `key` and whose value doesn’t match the `value` in this object. +>>>>>> * The key is not present in the document. @@ -211 +255,3 @@ JSON Syntax: ->>>>>> (string) +>>>>>> The following example would return data sources that don’t contain an `animal` attribute whose value is `cat` . +>>>>>> +>>>>>>> `"notEquals": { "key": "animal", "value": "cat" }` @@ -212,0 +259,4 @@ JSON Syntax: +>>>>>> key -> (string) [required] +>>>>>> +>>>>>>> The name that the metadata attribute must match. +>>>>>>> @@ -216 +266 @@ JSON Syntax: ->>>>>>> * max: `1000` +>>>>>>> * max: `100` @@ -218,0 +269,4 @@ JSON Syntax: +>>>>>> +>>>>>> value -> (document) [required] +>>>>>> +>>>>>>> The value to whcih to compare the value of the metadata attribute. @@ -220 +274 @@ JSON Syntax: ->>>>> temperature -> (float) +>>>>> greaterThan -> (structure) @@ -222 +276 @@ JSON Syntax: ->>>>>> 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. +>>>>>> 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.