edge-impulse-api 1.22.2 → 1.32.24444

package/build/library/sdk/api/allowsReadOnlyApi.d.ts

@@ -10,11 +10,13 @@
  * Do not edit the class manually.
  */
 /// <reference types="node" />
-import { AnomalyModelMetadataResponse } from '../model/anomalyModelMetadataResponse';
+import { AnomalyGmmMetadata } from '../model/anomalyGmmMetadata';
+import { AnomalyModelMetadata } from '../model/anomalyModelMetadata';
 import { AnomalyTrainedFeaturesResponse } from '../model/anomalyTrainedFeaturesResponse';
 import { ClassifyJobResponse } from '../model/classifyJobResponse';
 import { ClassifyJobResponsePage } from '../model/classifyJobResponsePage';
 import { ClassifySampleResponse } from '../model/classifySampleResponse';
+import { StartJobResponse } from '../model/startJobResponse';
 import { CountSamplesResponse } from '../model/countSamplesResponse';
 import { DSPMetadataResponse } from '../model/dSPMetadataResponse';
 import { DataExplorerPredictionsResponse } from '../model/dataExplorerPredictionsResponse';
@@ -24,6 +26,8 @@ import { DspRunResponseWithSample } from '../model/dspRunResponseWithSample';
 import { DspSampleFeaturesResponse } from '../model/dspSampleFeaturesResponse';
 import { DspTrainedFeaturesResponse } from '../model/dspTrainedFeaturesResponse';
 import { GetDataExplorerFeaturesResponse } from '../model/getDataExplorerFeaturesResponse';
+import { GetDiversityDataResponse } from '../model/getDiversityDataResponse';
+import { GetLabelNoiseDataResponse } from '../model/getLabelNoiseDataResponse';
 import { GetNotesResponse } from '../model/getNotesResponse';
 import { GetPerformanceCalibrationGroundTruthResponse } from '../model/getPerformanceCalibrationGroundTruthResponse';
 import { GetPerformanceCalibrationParameterSetsResponse } from '../model/getPerformanceCalibrationParameterSetsResponse';
@@ -34,6 +38,7 @@ import { GetSampleResponse } from '../model/getSampleResponse';
 import { HasDataExplorerFeaturesResponse } from '../model/hasDataExplorerFeaturesResponse';
 import { KerasModelMetadata } from '../model/kerasModelMetadata';
 import { KerasModelTypeEnum } from '../model/kerasModelTypeEnum';
+import { KerasModelVariantEnum } from '../model/kerasModelVariantEnum';
 import { ListSamplesResponse } from '../model/listSamplesResponse';
 import { ProjectDeploymentTargetsResponse } from '../model/projectDeploymentTargetsResponse';
 import { ProjectInfoSummaryResponse } from '../model/projectInfoSummaryResponse';
@@ -50,6 +55,16 @@ declare type anomalyTrainedFeaturesQueryParams = {
     featureAx1: number;
     featureAx2: number;
 };
+declare type classifySampleQueryParams = {
+    includeDebugInfo?: boolean;
+};
+declare type classifySampleByLearnBlockV2QueryParams = {
+    variant?: KerasModelVariantEnum;
+};
+declare type classifySampleV2QueryParams = {
+    includeDebugInfo?: boolean;
+    variant?: KerasModelVariantEnum;
+};
 declare type countSamplesQueryParams = {
     category: 'training' | 'testing' | 'anomaly';
     labels?: string;
@@ -81,6 +96,9 @@ declare type getClassifyJobResultPageQueryParams = {
     limit?: number;
     offset?: number;
 };
+declare type getDspMetadataQueryParams = {
+    excludeIncludedSamples?: boolean;
+};
 declare type getDspRawSampleQueryParams = {
     limitPayloadValues?: number;
 };
@@ -174,18 +192,19 @@ export declare class AllowsReadOnlyApi {
         };
     }): Promise<AnomalyTrainedFeaturesResponse>;
     /**
-     * Classify a complete file against the current impulse. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.
-     * @summary Classify sample
+     * This API is deprecated, use classifySampleV2 instead (`/v1/api/{projectId}/classify/v2/{sampleId}`). Classify a complete file against the current impulse. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.
+     * @summary Classify sample (deprecated)
      * @param projectId Project ID
      * @param sampleId Sample ID
+     * @param includeDebugInfo Whether to return the debug information from FOMO classification.
      */
-    classifySample(projectId: number, sampleId: number, options?: {
+    classifySample(projectId: number, sampleId: number, queryParams: classifySampleQueryParams, options?: {
         headers: {
             [name: string]: string;
         };
     }): Promise<ClassifySampleResponse>;
     /**
-     * Classify a complete file against the specified learn block. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.
+     * This API is deprecated, use classifySampleByLearnBlockV2 (`/v1/api/{projectId}/classify/anomaly-gmm/v2/{blockId}/{sampleId}`) instead. Classify a complete file against the specified learn block. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.
      * @summary Classify sample by learn block
      * @param projectId Project ID
      * @param sampleId Sample ID
@@ -196,6 +215,32 @@ export declare class AllowsReadOnlyApi {
             [name: string]: string;
         };
     }): Promise<ClassifySampleResponse>;
+    /**
+     * Classify a complete file against the specified learn block. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted. Depending on the size of your file, whether your sample is resampled, and whether the result is cached you\'ll get either the result or a job back. If you receive a job, then wait for the completion of the job, and then call this function again to receive the results. The unoptimized (float32) model is used by default, and classification with an optimized (int8) model can be slower.
+     * @summary Classify sample by learn block
+     * @param projectId Project ID
+     * @param sampleId Sample ID
+     * @param blockId Block ID
+     * @param variant Keras model variant
+     */
+    classifySampleByLearnBlockV2(projectId: number, sampleId: number, blockId: number, queryParams: classifySampleByLearnBlockV2QueryParams, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<ClassifySampleResponse | StartJobResponse>;
+    /**
+     * Classify a complete file against the current impulse. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted. Depending on the size of your file, whether your sample is resampled, and whether the result is cached you\'ll get either the result or a job back. If you receive a job, then wait for the completion of the job, and then call this function again to receive the results. The unoptimized (float32) model is used by default, and classification with an optimized (int8) model can be slower.
+     * @summary Classify sample
+     * @param projectId Project ID
+     * @param sampleId Sample ID
+     * @param includeDebugInfo Whether to return the debug information from FOMO classification.
+     * @param variant Keras model variant
+     */
+    classifySampleV2(projectId: number, sampleId: number, queryParams: classifySampleV2QueryParams, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<ClassifySampleResponse | StartJobResponse>;
     /**
      * Count all raw data by category.
      * @summary Count samples
@@ -302,7 +347,7 @@ export declare class AllowsReadOnlyApi {
         headers: {
             [name: string]: string;
         };
-    }): Promise<AnomalyModelMetadataResponse>;
+    }): Promise<AnomalyModelMetadata>;
     /**
      * Get classify job result, containing the result for the complete testing dataset.
      * @summary Classify job result
@@ -346,13 +391,24 @@ export declare class AllowsReadOnlyApi {
             [name: string]: string;
         };
     }): Promise<DataExplorerPredictionsResponse>;
+    /**
+     * Obtain metrics that describe the similarity and diversity of a dataset. To calculate these metrics, use the `calculateDataQualityMetrics` endpoint.
+     * @summary Get diversity metrics data
+     * @param projectId Project ID
+     */
+    getDiversityData(projectId: number, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<GetDiversityDataResponse>;
     /**
      * Retrieve the metadata from a generated DSP block.
      * @summary Get metadata
      * @param projectId Project ID
      * @param dspId DSP Block ID, use the impulse functions to retrieve the ID
+     * @param excludeIncludedSamples Whether to exclude \&#39;includedSamples\&#39; in the response (as these can slow down requests significantly).
      */
-    getDspMetadata(projectId: number, dspId: number, options?: {
+    getDspMetadata(projectId: number, dspId: number, queryParams: getDspMetadataQueryParams, options?: {
         headers: {
             [name: string]: string;
         };
@@ -384,6 +440,17 @@ export declare class AllowsReadOnlyApi {
             [name: string]: string;
         };
     }): Promise<GetSampleResponse>;
+    /**
+     * Get raw model metadata of the Gaussian mixture model (GMM) for a trained anomaly block. Use the impulse blocks to find the learnId.
+     * @summary Anomaly GMM metadata
+     * @param projectId Project ID
+     * @param learnId Learn Block ID, use the impulse functions to retrieve the ID
+     */
+    getGmmMetadata(projectId: number, learnId: number, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<AnomalyGmmMetadata>;
     /**
      * t-SNE2 output of the raw dataset using embeddings from this Keras block
      * @summary Get data explorer features
@@ -406,6 +473,16 @@ export declare class AllowsReadOnlyApi {
             [name: string]: string;
         };
     }): Promise<KerasModelMetadata>;
+    /**
+     * Obtain metrics that describe potential label noise issues in the dataset. To calculate these metrics, use the `calculateDataQualityMetrics` endpoint.
+     * @summary Get label noise data
+     * @param projectId Project ID
+     */
+    getLabelNoiseData(projectId: number, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<GetLabelNoiseDataResponse>;
     /**
      * Get all notes in project.
      * @summary Get notes
@@ -570,6 +647,26 @@ export declare class AllowsReadOnlyApi {
             [name: string]: string;
         };
     }): Promise<HasDataExplorerFeaturesResponse>;
+    /**
+     * Determine if data diversity metrics have been calculated. To calculate these metrics, use the `calculateDataQualityMetrics` endpoint.
+     * @summary Check if data diversity metrics exist
+     * @param projectId Project ID
+     */
+    hasDiversityData(projectId: number, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<HasDataExplorerFeaturesResponse>;
+    /**
+     * Determine if label noise metrics have been calculated. To calculate these metrics, use the `calculateDataQualityMetrics` endpoint.
+     * @summary Check if label noise metrics exist
+     * @param projectId Project ID
+     */
+    hasLabelNoiseData(projectId: number, options?: {
+        headers: {
+            [name: string]: string;
+        };
+    }): Promise<HasDataExplorerFeaturesResponse>;
     /**
      * List all deployment targets
      * @summary Deployment targets