AWS.Tools.BedrockRuntime.XML
|
<?xml version="1.0"?>
<doc> <assembly> <name>AWS.Tools.BedrockRuntime</name> </assembly> <members> <member name="T:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet"> <summary> Sends messages to the specified Amazon Bedrock model. <c>Converse</c> provides a consistent interface that works with all models that support messages. This allows you to write code once and use it with different models. If a model has unique inference parameters, you can also pass those unique parameters to the model. <para> Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response. </para><para> You can submit a prompt by including it in the <c>messages</c> field, specifying the <c>modelId</c> of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case. </para><para> You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the <c>promptVariables</c> field. You can append more messages to the prompt by using the <c>messages</c> field. If you use a prompt from Prompt management, you can't include the following fields in the request: <c>additionalModelRequestFields</c>, <c>inferenceConfig</c>, <c>system</c>, or <c>toolConfig</c>. Instead, these fields must be defined through Prompt management. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management-use.html">Use a prompt from Prompt management</a>. </para><para> For information about the Converse API, see <i>Use the Converse API</i> in the <i>Amazon Bedrock User Guide</i>. To use a guardrail, see <i>Use a guardrail with the Converse API</i> in the <i>Amazon Bedrock User Guide</i>. To use a tool with a model, see <i>Tool use (Function calling)</i> in the <i>Amazon Bedrock User Guide</i></para><para> For example code, see <i>Converse API examples</i> in the <i>Amazon Bedrock User Guide</i>. </para><para> This operation requires permission for the <c>bedrock:InvokeModel</c> action. </para><important><para> To deny all inference access to resources that you specify in the modelId field, you need to deny access to the <c>bedrock:InvokeModel</c> and <c>bedrock:InvokeModelWithResponseStream</c> actions. Doing this also denies access to the resource through the base inference actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html">InvokeModel</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html">InvokeModelWithResponseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>. </para></important><para> For troubleshooting some of the common errors you might encounter when using the <c>Converse</c> API, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.AdditionalModelRequestField"> <summary> <para> <para>Additional inference parameters that the model supports, beyond the base set of inference parameters that <c>Converse</c> and <c>ConverseStream</c> support in the <c>inferenceConfig</c> field. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Model parameters</a>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.AdditionalModelResponseFieldPath"> <summary> <para> <para>Additional model parameters field paths to return in the response. <c>Converse</c> and <c>ConverseStream</c> return the requested fields as a JSON Pointer object in the <c>additionalModelResponseFields</c> field. The following is example JSON for <c>additionalModelResponseFieldPaths</c>.</para><para><c>[ "/stop_sequence" ]</c></para><para>For information about the JSON Pointer syntax, see the <a href="https://datatracker.ietf.org/doc/html/rfc6901">Internet Engineering Task Force (IETF)</a> documentation.</para><para><c>Converse</c> and <c>ConverseStream</c> reject an empty JSON Pointer or incorrectly structured JSON Pointer with a <c>400</c> error code. if the JSON Pointer is valid, but the requested field is not in the model response, it is ignored by <c>Converse</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.ToolChoice_Any"> <summary> <para> <para>The model must request at least one tool (no text is generated).</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.ToolChoice_Auto"> <summary> <para> <para>(Default). The Model automatically decides if a tool should be called or whether to generate text instead. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.GuardrailConfig_GuardrailIdentifier"> <summary> <para> <para>The identifier for the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.GuardrailConfig_GuardrailVersion"> <summary> <para> <para>The version of the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.PerformanceConfig_Latency"> <summary> <para> <para>To use a latency-optimized version of the model, set to <c>optimized</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.InferenceConfig_MaxToken"> <summary> <para> <para>The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.Message"> <summary> <para> <para>The messages that you want to send to the model.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.ModelId"> <summary> <para> <para>Specifies the model or throughput with which to run inference, or the prompt resource to use in inference. The value depends on the resource that you use:</para><ul><li><para>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</para></li><li><para>To include a prompt that was defined in <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html">Prompt management</a>, specify the ARN of the prompt version to use.</para></li></ul><para>The Converse API doesn't support <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported models</a>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.Tool_Name"> <summary> <para> <para>The name of the tool that the model must request. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.PromptVariable"> <summary> <para> <para>Contains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation. This field is ignored if you don't specify a prompt resource in the <c>modelId</c> field.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.InferenceConfig_StopSequence"> <summary> <para> <para>A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.System"> <summary> <para> <para>A prompt that provides instructions or context to the model about the task it should perform, or the persona it should adopt during the conversation.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.InferenceConfig_Temperature"> <summary> <para> <para>The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.</para><para>The default value is the default value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.ToolConfig_Tool"> <summary> <para> <para>An array of tools that you want to pass to a model.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.InferenceConfig_TopP"> <summary> <para> <para>The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for <c>topP</c>, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.</para><para>The default value is the default value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.GuardrailConfig_Trace"> <summary> <para> <para>The trace behavior for the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is '*'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.BedrockRuntime.Model.ConverseResponse). Specifying the name of a property of type Amazon.BedrockRuntime.Model.ConverseResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the ModelId parameter. The -PassThru parameter is deprecated, use -Select '^ModelId' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> <member name="T:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet"> <summary> Sends messages to the specified Amazon Bedrock model and returns the response in a stream. <c>ConverseStream</c> provides a consistent API that works with all Amazon Bedrock models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model. <para> To find out if a model supports streaming, call <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetFoundationModel.html">GetFoundationModel</a> and check the <c>responseStreamingSupported</c> field in the response. </para><note><para> The CLI doesn't support streaming operations in Amazon Bedrock, including <c>ConverseStream</c>. </para></note><para> Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response. </para><para> You can submit a prompt by including it in the <c>messages</c> field, specifying the <c>modelId</c> of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case. </para><para> You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the <c>promptVariables</c> field. You can append more messages to the prompt by using the <c>messages</c> field. If you use a prompt from Prompt management, you can't include the following fields in the request: <c>additionalModelRequestFields</c>, <c>inferenceConfig</c>, <c>system</c>, or <c>toolConfig</c>. Instead, these fields must be defined through Prompt management. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management-use.html">Use a prompt from Prompt management</a>. </para><para> For information about the Converse API, see <i>Use the Converse API</i> in the <i>Amazon Bedrock User Guide</i>. To use a guardrail, see <i>Use a guardrail with the Converse API</i> in the <i>Amazon Bedrock User Guide</i>. To use a tool with a model, see <i>Tool use (Function calling)</i> in the <i>Amazon Bedrock User Guide</i></para><para> For example code, see <i>Conversation streaming example</i> in the <i>Amazon Bedrock User Guide</i>. </para><para> This operation requires permission for the <c>bedrock:InvokeModelWithResponseStream</c> action. </para><important><para> To deny all inference access to resources that you specify in the modelId field, you need to deny access to the <c>bedrock:InvokeModel</c> and <c>bedrock:InvokeModelWithResponseStream</c> actions. Doing this also denies access to the resource through the base inference actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html">InvokeModel</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html">InvokeModelWithResponseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>. </para></important><para> For troubleshooting some of the common errors you might encounter when using the <c>ConverseStream</c> API, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.AdditionalModelRequestField"> <summary> <para> <para>Additional inference parameters that the model supports, beyond the base set of inference parameters that <c>Converse</c> and <c>ConverseStream</c> support in the <c>inferenceConfig</c> field. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Model parameters</a>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.AdditionalModelResponseFieldPath"> <summary> <para> <para>Additional model parameters field paths to return in the response. <c>Converse</c> and <c>ConverseStream</c> return the requested fields as a JSON Pointer object in the <c>additionalModelResponseFields</c> field. The following is example JSON for <c>additionalModelResponseFieldPaths</c>.</para><para><c>[ "/stop_sequence" ]</c></para><para>For information about the JSON Pointer syntax, see the <a href="https://datatracker.ietf.org/doc/html/rfc6901">Internet Engineering Task Force (IETF)</a> documentation.</para><para><c>Converse</c> and <c>ConverseStream</c> reject an empty JSON Pointer or incorrectly structured JSON Pointer with a <c>400</c> error code. if the JSON Pointer is valid, but the requested field is not in the model response, it is ignored by <c>Converse</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.ToolChoice_Any"> <summary> <para> <para>The model must request at least one tool (no text is generated).</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.ToolChoice_Auto"> <summary> <para> <para>(Default). The Model automatically decides if a tool should be called or whether to generate text instead. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.GuardrailConfig_GuardrailIdentifier"> <summary> <para> <para>The identifier for the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.GuardrailConfig_GuardrailVersion"> <summary> <para> <para>The version of the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.PerformanceConfig_Latency"> <summary> <para> <para>To use a latency-optimized version of the model, set to <c>optimized</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.InferenceConfig_MaxToken"> <summary> <para> <para>The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.Message"> <summary> <para> <para>The messages that you want to send to the model.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.ModelId"> <summary> <para> <para>Specifies the model or throughput with which to run inference, or the prompt resource to use in inference. The value depends on the resource that you use:</para><ul><li><para>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</para></li><li><para>To include a prompt that was defined in <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html">Prompt management</a>, specify the ARN of the prompt version to use.</para></li></ul><para>The Converse API doesn't support <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported models</a>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.Tool_Name"> <summary> <para> <para>The name of the tool that the model must request. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.PromptVariable"> <summary> <para> <para>Contains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation. This field is ignored if you don't specify a prompt resource in the <c>modelId</c> field.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.InferenceConfig_StopSequence"> <summary> <para> <para>A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.GuardrailConfig_StreamProcessingMode"> <summary> <para> <para>The processing mode. </para><para>The processing mode. For more information, see <i>Configure streaming response behavior</i> in the <i>Amazon Bedrock User Guide</i>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.System"> <summary> <para> <para>A prompt that provides instructions or context to the model about the task it should perform, or the persona it should adopt during the conversation.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.InferenceConfig_Temperature"> <summary> <para> <para>The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.</para><para>The default value is the default value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.ToolConfig_Tool"> <summary> <para> <para>An array of tools that you want to pass to a model.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.InferenceConfig_TopP"> <summary> <para> <para>The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for <c>topP</c>, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.</para><para>The default value is the default value for the model that you are using. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters for foundation models</a>. </para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.GuardrailConfig_Trace"> <summary> <para> <para>The trace behavior for the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is 'Stream'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.BedrockRuntime.Model.ConverseStreamResponse). Specifying the name of a property of type Amazon.BedrockRuntime.Model.ConverseStreamResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the ModelId parameter. The -PassThru parameter is deprecated, use -Select '^ModelId' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRConverseStreamCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> <member name="T:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet"> <summary> The action to apply a guardrail. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.Content"> <summary> <para> <para>The content details used in the request to apply the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.GuardrailIdentifier"> <summary> <para> <para>The guardrail identifier used in the request to apply the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.GuardrailVersion"> <summary> <para> <para>The guardrail version used in the request to apply the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.Source"> <summary> <para> <para>The source of data used in the request to apply the guardrail.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is '*'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.BedrockRuntime.Model.ApplyGuardrailResponse). Specifying the name of a property of type Amazon.BedrockRuntime.Model.ApplyGuardrailResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the GuardrailIdentifier parameter. The -PassThru parameter is deprecated, use -Select '^GuardrailIdentifier' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRGuardrailCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> <member name="T:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet"> <summary> Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to generate text, images, and embeddings. <para> For example code, see <i>Invoke model code examples</i> in the <i>Amazon Bedrock User Guide</i>. </para><para> This operation requires permission for the <c>bedrock:InvokeModel</c> action. </para><important><para> To deny all inference access to resources that you specify in the modelId field, you need to deny access to the <c>bedrock:InvokeModel</c> and <c>bedrock:InvokeModelWithResponseStream</c> actions. Doing this also denies access to the resource through the Converse API actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html">Converse</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html">ConverseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>. </para></important><para> For troubleshooting some of the common errors you might encounter when using the <c>InvokeModel</c> API, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.Accept"> <summary> <para> <para>The desired MIME type of the inference body in the response. The default value is <c>application/json</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.Body"> <summary> <para> <para>The prompt and inference parameters in the format specified in the <c>contentType</c> in the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters</a>. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/api-methods-run.html">Run inference</a> in the Bedrock User Guide.</para> </para> <para>The cmdlet will automatically convert the supplied parameter of type string, string[], System.IO.FileInfo or System.IO.Stream to byte[] before supplying it to the service.</para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.ContentType"> <summary> <para> <para>The MIME type of the input data in the request. You must specify <c>application/json</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.GuardrailIdentifier"> <summary> <para> <para>The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.</para><para>An error will be thrown in the following situations.</para><ul><li><para>You don't provide a guardrail identifier but you specify the <c>amazon-bedrock-guardrailConfig</c> field in the request body.</para></li><li><para>You enable the guardrail but the <c>contentType</c> isn't <c>application/json</c>.</para></li><li><para>You provide a guardrail identifier, but <c>guardrailVersion</c> isn't specified.</para></li></ul> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.GuardrailVersion"> <summary> <para> <para>The version number for the guardrail. The value can also be <c>DRAFT</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.ModelId"> <summary> <para> <para>The unique identifier of the model to invoke to run inference.</para><para>The <c>modelId</c> to provide depends on the type of model or throughput that you use:</para><ul><li><para>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use an <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported model</a>, specify the ARN of the imported model. You can get the model ARN from a successful call to <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html">CreateModelImportJob</a> or from the Imported models page in the Amazon Bedrock console.</para></li></ul> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.PerformanceConfigLatency"> <summary> <para> <para>Model performance settings for the request.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.Trace"> <summary> <para> <para>Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is '*'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.BedrockRuntime.Model.InvokeModelResponse). Specifying the name of a property of type Amazon.BedrockRuntime.Model.InvokeModelResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the ModelId parameter. The -PassThru parameter is deprecated, use -Select '^ModelId' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> <member name="T:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet"> <summary> Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream. <para> To see if a model supports streaming, call <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetFoundationModel.html">GetFoundationModel</a> and check the <c>responseStreamingSupported</c> field in the response. </para><note><para> The CLI doesn't support streaming operations in Amazon Bedrock, including <c>InvokeModelWithResponseStream</c>. </para></note><para> For example code, see <i>Invoke model with streaming code example</i> in the <i>Amazon Bedrock User Guide</i>. </para><para> This operation requires permissions to perform the <c>bedrock:InvokeModelWithResponseStream</c> action. </para><important><para> To deny all inference access to resources that you specify in the modelId field, you need to deny access to the <c>bedrock:InvokeModel</c> and <c>bedrock:InvokeModelWithResponseStream</c> actions. Doing this also denies access to the resource through the Converse API actions (<a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html">Converse</a> and <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html">ConverseStream</a>). For more information see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html#security_iam_id-based-policy-examples-deny-inference">Deny access for inference on specific models</a>. </para></important><para> For troubleshooting some of the common errors you might encounter when using the <c>InvokeModelWithResponseStream</c> API, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/troubleshooting-api-error-codes.html">Troubleshooting Amazon Bedrock API Error Codes</a> in the Amazon Bedrock User Guide </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.Accept"> <summary> <para> <para>The desired MIME type of the inference body in the response. The default value is <c>application/json</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.Body"> <summary> <para> <para>The prompt and inference parameters in the format specified in the <c>contentType</c> in the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters.html">Inference parameters</a>. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/api-methods-run.html">Run inference</a> in the Bedrock User Guide.</para> </para> <para>The cmdlet will automatically convert the supplied parameter of type string, string[], System.IO.FileInfo or System.IO.Stream to byte[] before supplying it to the service.</para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.ContentType"> <summary> <para> <para>The MIME type of the input data in the request. You must specify <c>application/json</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.GuardrailIdentifier"> <summary> <para> <para>The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.</para><para>An error is thrown in the following situations.</para><ul><li><para>You don't provide a guardrail identifier but you specify the <c>amazon-bedrock-guardrailConfig</c> field in the request body.</para></li><li><para>You enable the guardrail but the <c>contentType</c> isn't <c>application/json</c>.</para></li><li><para>You provide a guardrail identifier, but <c>guardrailVersion</c> isn't specified.</para></li></ul> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.GuardrailVersion"> <summary> <para> <para>The version number for the guardrail. The value can also be <c>DRAFT</c>.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.ModelId"> <summary> <para> <para>The unique identifier of the model to invoke to run inference.</para><para>The <c>modelId</c> to provide depends on the type of model or throughput that you use:</para><ul><li><para>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</para></li><li><para>If you use an <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported model</a>, specify the ARN of the imported model. You can get the model ARN from a successful call to <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html">CreateModelImportJob</a> or from the Imported models page in the Amazon Bedrock console.</para></li></ul> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.PerformanceConfigLatency"> <summary> <para> <para>Model performance settings for the request.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.Trace"> <summary> <para> <para>Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.</para> </para> </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.Select"> <summary> Use the -Select parameter to control the cmdlet output. The default value is '*'. Specifying -Select '*' will result in the cmdlet returning the whole service response (Amazon.BedrockRuntime.Model.InvokeModelWithResponseStreamResponse). Specifying the name of a property of type Amazon.BedrockRuntime.Model.InvokeModelWithResponseStreamResponse will result in that property being returned. Specifying -Select '^ParameterName' will result in the cmdlet returning the selected cmdlet parameter value. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.PassThru"> <summary> Changes the cmdlet behavior to return the value passed to the ModelId parameter. The -PassThru parameter is deprecated, use -Select '^ModelId' instead. This parameter will be removed in a future version. </summary> </member> <member name="P:Amazon.PowerShell.Cmdlets.BDRR.InvokeBDRRModelWithResponseStreamCmdlet.Force"> <summary> This parameter overrides confirmation prompts to force the cmdlet to continue its operation. This parameter should always be used with caution. </summary> </member> </members> </doc> |