|
174 | 174 | {"shape":"ServiceQuotaExceededException"},
|
175 | 175 | {"shape":"ThrottlingException"}
|
176 | 176 | ],
|
177 |
| - "documentation":"<p>Creates a job to invoke a model on multiple prompts (batch inference). Format your data according to <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference-prerq.html#batch-inference-data\">Format your inference data</a> and upload it to an Amazon S3 bucket. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference-create.html\">Create a batch inference job</a>.</p> <p>The response returns a <code>jobArn</code> that you can use to stop or get details about the job. You can check the status of the job by sending a <a href=\"https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetModelCustomizationJob.html\">GetModelCustomizationJob</a> request.</p>", |
| 177 | + "documentation":"<p>Creates a batch inference job to invoke a model on multiple prompts. Format your data according to <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference-data\">Format your inference data</a> and upload it to an Amazon S3 bucket. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference.html\">Process multiple prompts with batch inference</a>.</p> <p>The response returns a <code>jobArn</code> that you can use to stop or get details about the job.</p>", |
178 | 178 | "idempotent":true
|
179 | 179 | },
|
180 | 180 | "CreateProvisionedModelThroughput":{
|
|
385 | 385 | ],
|
386 | 386 | "documentation":"<p>Gets properties associated with a customized model you imported. </p>"
|
387 | 387 | },
|
| 388 | + "GetInferenceProfile":{ |
| 389 | + "name":"GetInferenceProfile", |
| 390 | + "http":{ |
| 391 | + "method":"GET", |
| 392 | + "requestUri":"/inference-profiles/{inferenceProfileIdentifier}", |
| 393 | + "responseCode":200 |
| 394 | + }, |
| 395 | + "input":{"shape":"GetInferenceProfileRequest"}, |
| 396 | + "output":{"shape":"GetInferenceProfileResponse"}, |
| 397 | + "errors":[ |
| 398 | + {"shape":"ResourceNotFoundException"}, |
| 399 | + {"shape":"AccessDeniedException"}, |
| 400 | + {"shape":"ValidationException"}, |
| 401 | + {"shape":"InternalServerException"}, |
| 402 | + {"shape":"ThrottlingException"} |
| 403 | + ], |
| 404 | + "documentation":"<p>Gets information about an inference profile. For more information, see the Amazon Bedrock User Guide.</p>" |
| 405 | + }, |
388 | 406 | "GetModelCopyJob":{
|
389 | 407 | "name":"GetModelCopyJob",
|
390 | 408 | "http":{
|
|
577 | 595 | ],
|
578 | 596 | "documentation":"<p>Returns a list of models you've imported. You can filter the results to return based on one or more criteria. For more information, see <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html\">Import a customized model</a> in the <a href=\"https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-service.html\">Amazon Bedrock User Guide</a>.</p>"
|
579 | 597 | },
|
| 598 | + "ListInferenceProfiles":{ |
| 599 | + "name":"ListInferenceProfiles", |
| 600 | + "http":{ |
| 601 | + "method":"GET", |
| 602 | + "requestUri":"/inference-profiles", |
| 603 | + "responseCode":200 |
| 604 | + }, |
| 605 | + "input":{"shape":"ListInferenceProfilesRequest"}, |
| 606 | + "output":{"shape":"ListInferenceProfilesResponse"}, |
| 607 | + "errors":[ |
| 608 | + {"shape":"AccessDeniedException"}, |
| 609 | + {"shape":"ValidationException"}, |
| 610 | + {"shape":"InternalServerException"}, |
| 611 | + {"shape":"ThrottlingException"} |
| 612 | + ], |
| 613 | + "documentation":"<p>Returns a list of inference profiles that you can use.</p>" |
| 614 | + }, |
580 | 615 | "ListModelCopyJobs":{
|
581 | 616 | "name":"ListModelCopyJobs",
|
582 | 617 | "http":{
|
|
2398 | 2433 | }
|
2399 | 2434 | }
|
2400 | 2435 | },
|
| 2436 | + "GetInferenceProfileRequest":{ |
| 2437 | + "type":"structure", |
| 2438 | + "required":["inferenceProfileIdentifier"], |
| 2439 | + "members":{ |
| 2440 | + "inferenceProfileIdentifier":{ |
| 2441 | + "shape":"InferenceProfileIdentifier", |
| 2442 | + "documentation":"<p>The unique identifier of the inference profile.</p>", |
| 2443 | + "location":"uri", |
| 2444 | + "locationName":"inferenceProfileIdentifier" |
| 2445 | + } |
| 2446 | + } |
| 2447 | + }, |
| 2448 | + "GetInferenceProfileResponse":{ |
| 2449 | + "type":"structure", |
| 2450 | + "required":[ |
| 2451 | + "inferenceProfileName", |
| 2452 | + "models", |
| 2453 | + "inferenceProfileArn", |
| 2454 | + "inferenceProfileId", |
| 2455 | + "status", |
| 2456 | + "type" |
| 2457 | + ], |
| 2458 | + "members":{ |
| 2459 | + "inferenceProfileName":{ |
| 2460 | + "shape":"InferenceProfileName", |
| 2461 | + "documentation":"<p>The name of the inference profile.</p>" |
| 2462 | + }, |
| 2463 | + "models":{ |
| 2464 | + "shape":"InferenceProfileModels", |
| 2465 | + "documentation":"<p>A list of information about each model in the inference profile.</p>" |
| 2466 | + }, |
| 2467 | + "description":{ |
| 2468 | + "shape":"InferenceProfileDescription", |
| 2469 | + "documentation":"<p>The description of the inference profile.</p>" |
| 2470 | + }, |
| 2471 | + "createdAt":{ |
| 2472 | + "shape":"Timestamp", |
| 2473 | + "documentation":"<p>The time at which the inference profile was created.</p>" |
| 2474 | + }, |
| 2475 | + "updatedAt":{ |
| 2476 | + "shape":"Timestamp", |
| 2477 | + "documentation":"<p>The time at which the inference profile was last updated.</p>" |
| 2478 | + }, |
| 2479 | + "inferenceProfileArn":{ |
| 2480 | + "shape":"InferenceProfileArn", |
| 2481 | + "documentation":"<p>The Amazon Resource Name (ARN) of the inference profile.</p>" |
| 2482 | + }, |
| 2483 | + "inferenceProfileId":{ |
| 2484 | + "shape":"InferenceProfileId", |
| 2485 | + "documentation":"<p>The unique identifier of the inference profile.</p>" |
| 2486 | + }, |
| 2487 | + "status":{ |
| 2488 | + "shape":"InferenceProfileStatus", |
| 2489 | + "documentation":"<p>The status of the inference profile. <code>ACTIVE</code> means that the inference profile is available to use.</p>" |
| 2490 | + }, |
| 2491 | + "type":{ |
| 2492 | + "shape":"InferenceProfileType", |
| 2493 | + "documentation":"<p>The type of the inference profile. <code>SYSTEM_DEFINED</code> means that the inference profile is defined by Amazon Bedrock.</p>" |
| 2494 | + } |
| 2495 | + } |
| 2496 | + }, |
2401 | 2497 | "GetModelCopyJobRequest":{
|
2402 | 2498 | "type":"structure",
|
2403 | 2499 | "required":["jobArn"],
|
|
3701 | 3797 | "type":"list",
|
3702 | 3798 | "member":{"shape":"ImportedModelSummary"}
|
3703 | 3799 | },
|
| 3800 | + "InferenceProfileArn":{ |
| 3801 | + "type":"string", |
| 3802 | + "max":2048, |
| 3803 | + "min":1, |
| 3804 | + "pattern":"arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{0,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+" |
| 3805 | + }, |
| 3806 | + "InferenceProfileDescription":{ |
| 3807 | + "type":"string", |
| 3808 | + "max":500, |
| 3809 | + "min":1, |
| 3810 | + "pattern":".+" |
| 3811 | + }, |
| 3812 | + "InferenceProfileId":{ |
| 3813 | + "type":"string", |
| 3814 | + "max":64, |
| 3815 | + "min":1, |
| 3816 | + "pattern":"[a-zA-Z0-9-:.]+" |
| 3817 | + }, |
| 3818 | + "InferenceProfileIdentifier":{ |
| 3819 | + "type":"string", |
| 3820 | + "max":2048, |
| 3821 | + "min":1, |
| 3822 | + "pattern":"(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{0,20}):(|[0-9]{12}):inference-profile/)?[a-zA-Z0-9-:.]+" |
| 3823 | + }, |
| 3824 | + "InferenceProfileModel":{ |
| 3825 | + "type":"structure", |
| 3826 | + "members":{ |
| 3827 | + "modelArn":{ |
| 3828 | + "shape":"FoundationModelArn", |
| 3829 | + "documentation":"<p>The Amazon Resource Name (ARN) of the model.</p>" |
| 3830 | + } |
| 3831 | + }, |
| 3832 | + "documentation":"<p>Contains information about a model.</p>" |
| 3833 | + }, |
| 3834 | + "InferenceProfileModels":{ |
| 3835 | + "type":"list", |
| 3836 | + "member":{"shape":"InferenceProfileModel"}, |
| 3837 | + "max":5, |
| 3838 | + "min":1 |
| 3839 | + }, |
| 3840 | + "InferenceProfileName":{ |
| 3841 | + "type":"string", |
| 3842 | + "max":64, |
| 3843 | + "min":1, |
| 3844 | + "pattern":"([0-9a-zA-Z][ _-]?)+" |
| 3845 | + }, |
| 3846 | + "InferenceProfileStatus":{ |
| 3847 | + "type":"string", |
| 3848 | + "enum":["ACTIVE"] |
| 3849 | + }, |
| 3850 | + "InferenceProfileSummaries":{ |
| 3851 | + "type":"list", |
| 3852 | + "member":{"shape":"InferenceProfileSummary"} |
| 3853 | + }, |
| 3854 | + "InferenceProfileSummary":{ |
| 3855 | + "type":"structure", |
| 3856 | + "required":[ |
| 3857 | + "inferenceProfileName", |
| 3858 | + "models", |
| 3859 | + "inferenceProfileArn", |
| 3860 | + "inferenceProfileId", |
| 3861 | + "status", |
| 3862 | + "type" |
| 3863 | + ], |
| 3864 | + "members":{ |
| 3865 | + "inferenceProfileName":{ |
| 3866 | + "shape":"InferenceProfileName", |
| 3867 | + "documentation":"<p>The name of the inference profile.</p>" |
| 3868 | + }, |
| 3869 | + "models":{ |
| 3870 | + "shape":"InferenceProfileModels", |
| 3871 | + "documentation":"<p>A list of information about each model in the inference profile.</p>" |
| 3872 | + }, |
| 3873 | + "description":{ |
| 3874 | + "shape":"InferenceProfileDescription", |
| 3875 | + "documentation":"<p>The description of the inference profile.</p>" |
| 3876 | + }, |
| 3877 | + "createdAt":{ |
| 3878 | + "shape":"Timestamp", |
| 3879 | + "documentation":"<p>The time at which the inference profile was created.</p>" |
| 3880 | + }, |
| 3881 | + "updatedAt":{ |
| 3882 | + "shape":"Timestamp", |
| 3883 | + "documentation":"<p>The time at which the inference profile was last updated.</p>" |
| 3884 | + }, |
| 3885 | + "inferenceProfileArn":{ |
| 3886 | + "shape":"InferenceProfileArn", |
| 3887 | + "documentation":"<p>The Amazon Resource Name (ARN) of the inference profile.</p>" |
| 3888 | + }, |
| 3889 | + "inferenceProfileId":{ |
| 3890 | + "shape":"InferenceProfileId", |
| 3891 | + "documentation":"<p>The unique identifier of the inference profile.</p>" |
| 3892 | + }, |
| 3893 | + "status":{ |
| 3894 | + "shape":"InferenceProfileStatus", |
| 3895 | + "documentation":"<p>The status of the inference profile. <code>ACTIVE</code> means that the inference profile is available to use.</p>" |
| 3896 | + }, |
| 3897 | + "type":{ |
| 3898 | + "shape":"InferenceProfileType", |
| 3899 | + "documentation":"<p>The type of the inference profile. <code>SYSTEM_DEFINED</code> means that the inference profile is defined by Amazon Bedrock.</p>" |
| 3900 | + } |
| 3901 | + }, |
| 3902 | + "documentation":"<p>Contains information about an inference profile.</p>" |
| 3903 | + }, |
| 3904 | + "InferenceProfileType":{ |
| 3905 | + "type":"string", |
| 3906 | + "enum":["SYSTEM_DEFINED"] |
| 3907 | + }, |
3704 | 3908 | "InferenceType":{
|
3705 | 3909 | "type":"string",
|
3706 | 3910 | "enum":[
|
|
4024 | 4228 | }
|
4025 | 4229 | }
|
4026 | 4230 | },
|
| 4231 | + "ListInferenceProfilesRequest":{ |
| 4232 | + "type":"structure", |
| 4233 | + "members":{ |
| 4234 | + "maxResults":{ |
| 4235 | + "shape":"MaxResults", |
| 4236 | + "documentation":"<p>The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the <code>nextToken</code> field when making another request to return the next batch of results.</p>", |
| 4237 | + "location":"querystring", |
| 4238 | + "locationName":"maxResults" |
| 4239 | + }, |
| 4240 | + "nextToken":{ |
| 4241 | + "shape":"PaginationToken", |
| 4242 | + "documentation":"<p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, enter the token returned in the <code>nextToken</code> field in the response in this field to return the next batch of results.</p>", |
| 4243 | + "location":"querystring", |
| 4244 | + "locationName":"nextToken" |
| 4245 | + } |
| 4246 | + } |
| 4247 | + }, |
| 4248 | + "ListInferenceProfilesResponse":{ |
| 4249 | + "type":"structure", |
| 4250 | + "members":{ |
| 4251 | + "inferenceProfileSummaries":{ |
| 4252 | + "shape":"InferenceProfileSummaries", |
| 4253 | + "documentation":"<p>A list of information about each inference profile that you can use.</p>" |
| 4254 | + }, |
| 4255 | + "nextToken":{ |
| 4256 | + "shape":"PaginationToken", |
| 4257 | + "documentation":"<p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, use this token when making another request in the <code>nextToken</code> field to return the next batch of results.</p>" |
| 4258 | + } |
| 4259 | + } |
| 4260 | + }, |
4027 | 4261 | "ListModelCopyJobsRequest":{
|
4028 | 4262 | "type":"structure",
|
4029 | 4263 | "members":{
|
|
0 commit comments