@huggingface/tasks 0.11.12 → 0.11.13

package/src/tasks/keypoint-detection/data.ts

@@ -0,0 +1,46 @@
+import type { TaskDataCustom } from "..";
+
+const taskData: TaskDataCustom = {
+	datasets: [
+		{
+			description: "A dataset of hand keypoints of over 500k examples.",
+			id: "Vincent-luo/hagrid-mediapipe-hands",
+		},
+	],
+	demo: {
+		inputs: [
+			{
+				filename: "keypoint-detection-input.png",
+				type: "img",
+			},
+		],
+		outputs: [
+			{
+				filename: "keypoint-detection-output.png",
+				type: "img",
+			},
+		],
+	},
+	metrics: [],
+	models: [
+		{
+			description: "A robust keypoint detection model.",
+			id: "magic-leap-community/superpoint",
+		},
+		{
+			description: "Strong keypoint detection model used to detect human pose.",
+			id: "qualcomm/MediaPipe-Pose-Estimation",
+		},
+	],
+	spaces: [
+		{
+			description: "An application that detects hand keypoints in real-time.",
+			id: "datasciencedojo/Hand-Keypoint-Detection-Realtime",
+		},
+	],
+	summary: "Keypoint detection is the task of identifying meaningful distinctive points or features in an image.",
+	widgetModels: [],
+	youtubeId: "",
+};
+
+export default taskData;

package/src/tasks/object-detection/inference.ts

@@ -8,9 +8,10 @@
  */
 export interface ObjectDetectionInput {
 	/**
-	 * The input image data
+	 * The input image data as a base64-encoded string. If no `parameters` are provided, you can
+	 * also provide the image data as a raw bytes payload.
 	 */
-	inputs: unknown;
+	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */
@@ -34,9 +35,21 @@ export interface ObjectDetectionParameters {
  * image.
  */
 export interface BoundingBox {
+	/**
+	 * The x-coordinate of the bottom-right corner of the bounding box.
+	 */
 	xmax: number;
+	/**
+	 * The x-coordinate of the top-left corner of the bounding box.
+	 */
 	xmin: number;
+	/**
+	 * The y-coordinate of the bottom-right corner of the bounding box.
+	 */
 	ymax: number;
+	/**
+	 * The y-coordinate of the top-left corner of the bounding box.
+	 */
 	ymin: number;
 	[property: string]: unknown;
 }
@@ -51,11 +64,11 @@ export interface ObjectDetectionOutputElement {
 	 */
 	box: BoundingBox;
 	/**
-	 * The predicted label for the bounding box
+	 * The predicted label for the bounding box.
 	 */
 	label: string;
 	/**
-	 * The associated score / probability
+	 * The associated score / probability.
 	 */
 	score: number;
 	[property: string]: unknown;

package/src/tasks/object-detection/spec/input.json

@@ -6,7 +6,8 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input image data"
+			"type": "string",
+			"description": "The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload."
 		},
 		"parameters": {
 			"description": "Additional inference parameters",

package/src/tasks/object-detection/spec/output.json

@@ -9,11 +9,11 @@
 		"properties": {
 			"label": {
 				"type": "string",
-				"description": "The predicted label for the bounding box"
+				"description": "The predicted label for the bounding box."
 			},
 			"score": {
 				"type": "number",
-				"description": "The associated score / probability"
+				"description": "The associated score / probability."
 			},
 			"box": {
 				"$ref": "#/$defs/BoundingBox",
@@ -28,16 +28,20 @@
 			"title": "BoundingBox",
 			"properties": {
 				"xmin": {
-					"type": "integer"
+					"type": "integer",
+					"description": "The x-coordinate of the top-left corner of the bounding box."
 				},
 				"xmax": {
-					"type": "integer"
+					"type": "integer",
+					"description": "The x-coordinate of the bottom-right corner of the bounding box."
 				},
 				"ymin": {
-					"type": "integer"
+					"type": "integer",
+					"description": "The y-coordinate of the top-left corner of the bounding box."
 				},
 				"ymax": {
-					"type": "integer"
+					"type": "integer",
+					"description": "The y-coordinate of the bottom-right corner of the bounding box."
 				}
 			},
 			"required": ["xmin", "xmax", "ymin", "ymax"]

package/src/tasks/summarization/inference.ts

@@ -6,43 +6,44 @@
 
 /**
  * Inputs for Summarization inference
- *
- * Inputs for Text2text Generation inference
  */
 export interface SummarizationInput {
 	/**
-	 * The input text data
+	 * The input text to summarize.
 	 */
 	inputs: string;
 	/**
-	 * Additional inference parameters
+	 * Additional inference parameters.
 	 */
-	parameters?: Text2TextGenerationParameters;
+	parameters?: SummarizationParameters;
 	[property: string]: unknown;
 }
 
 /**
- * Additional inference parameters
+ * Additional inference parameters.
  *
- * Additional inference parameters for Text2text Generation
+ * Additional inference parameters for summarization.
  */
-export interface Text2TextGenerationParameters {
+export interface SummarizationParameters {
 	/**
 	 * Whether to clean up the potential extra spaces in the text output.
 	 */
 	clean_up_tokenization_spaces?: boolean;
 	/**
-	 * Additional parametrization of the text generation algorithm
+	 * Additional parametrization of the text generation algorithm.
 	 */
 	generate_parameters?: { [key: string]: unknown };
 	/**
-	 * The truncation strategy to use
+	 * The truncation strategy to use.
 	 */
-	truncation?: Text2TextGenerationTruncationStrategy;
+	truncation?: SummarizationTruncationStrategy;
 	[property: string]: unknown;
 }
 
-export type Text2TextGenerationTruncationStrategy = "do_not_truncate" | "longest_first" | "only_first" | "only_second";
+/**
+ * The truncation strategy to use.
+ */
+export type SummarizationTruncationStrategy = "do_not_truncate" | "longest_first" | "only_first" | "only_second";
 
 /**
  * Outputs of inference for the Summarization task

package/src/tasks/summarization/spec/input.json

@@ -1,7 +1,42 @@
 {
-	"$ref": "/inference/schemas/text2text-generation/input.json",
 	"$id": "/inference/schemas/summarization/input.json",
 	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Inputs for Summarization inference",
 	"title": "SummarizationInput",
-	"description": "Inputs for Summarization inference"
+	"type": "object",
+	"properties": {
+		"inputs": {
+			"description": "The input text to summarize.",
+			"type": "string"
+		},
+		"parameters": {
+			"description": "Additional inference parameters.",
+			"$ref": "#/$defs/SummarizationParameters"
+		}
+	},
+	"$defs": {
+		"SummarizationParameters": {
+			"title": "SummarizationParameters",
+			"description": "Additional inference parameters for summarization.",
+			"type": "object",
+			"properties": {
+				"clean_up_tokenization_spaces": {
+					"type": "boolean",
+					"description": "Whether to clean up the potential extra spaces in the text output."
+				},
+				"truncation": {
+					"title": "SummarizationTruncationStrategy",
+					"type": "string",
+					"description": "The truncation strategy to use.",
+					"enum": ["do_not_truncate", "longest_first", "only_first", "only_second"]
+				},
+				"generate_parameters": {
+					"title": "generateParameters",
+					"type": "object",
+					"description": "Additional parametrization of the text generation algorithm."
+				}
+			}
+		}
+	},
+	"required": ["inputs"]
 }

package/src/tasks/text-classification/spec/output.json

@@ -5,6 +5,7 @@
 	"title": "TextClassificationOutput",
 	"type": "array",
 	"items": {
+		"type": "object",
 		"$ref": "/inference/schemas/common-definitions.json#/definitions/ClassificationOutput"
 	}
 }

package/src/tasks/text-to-image/inference.ts

@@ -9,7 +9,7 @@
  */
 export interface TextToImageInput {
 	/**
-	 * The input text data (sometimes called "prompt"
+	 * The input text data (sometimes called "prompt")
 	 */
 	inputs: string;
 	/**
@@ -64,7 +64,7 @@ export interface TargetSize {
  */
 export interface TextToImageOutput {
 	/**
-	 * The generated image
+	 * The generated image returned as raw bytes in the payload.
 	 */
 	image: unknown;
 	[property: string]: unknown;

package/src/tasks/text-to-image/spec/input.json

@@ -6,7 +6,7 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input text data (sometimes called \"prompt\"",
+			"description": "The input text data (sometimes called \"prompt\")",
 			"type": "string"
 		},
 		"parameters": {

package/src/tasks/text-to-image/spec/output.json

@@ -6,7 +6,7 @@
 	"type": "object",
 	"properties": {
 		"image": {
-			"description": "The generated image"
+			"description": "The generated image returned as raw bytes in the payload."
 		}
 	},
 	"required": ["image"]

package/src/tasks/translation/inference.ts

@@ -6,43 +6,54 @@
 
 /**
  * Inputs for Translation inference
- *
- * Inputs for Text2text Generation inference
  */
 export interface TranslationInput {
 	/**
-	 * The input text data
+	 * The text to translate.
 	 */
 	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */
-	parameters?: Text2TextGenerationParameters;
+	parameters?: TranslationParameters;
 	[property: string]: unknown;
 }
 
 /**
  * Additional inference parameters
  *
- * Additional inference parameters for Text2text Generation
+ * Additional inference parameters for Translation
  */
-export interface Text2TextGenerationParameters {
+export interface TranslationParameters {
 	/**
 	 * Whether to clean up the potential extra spaces in the text output.
 	 */
 	clean_up_tokenization_spaces?: boolean;
 	/**
-	 * Additional parametrization of the text generation algorithm
+	 * Additional parametrization of the text generation algorithm.
 	 */
 	generate_parameters?: { [key: string]: unknown };
 	/**
-	 * The truncation strategy to use
+	 * The source language of the text. Required for models that can translate from multiple
+	 * languages.
+	 */
+	src_lang?: string;
+	/**
+	 * Target language to translate to. Required for models that can translate to multiple
+	 * languages.
 	 */
-	truncation?: Text2TextGenerationTruncationStrategy;
+	tgt_lang?: string;
+	/**
+	 * The truncation strategy to use.
+	 */
+	truncation?: TranslationTruncationStrategy;
 	[property: string]: unknown;
 }
 
-export type Text2TextGenerationTruncationStrategy = "do_not_truncate" | "longest_first" | "only_first" | "only_second";
+/**
+ * The truncation strategy to use.
+ */
+export type TranslationTruncationStrategy = "do_not_truncate" | "longest_first" | "only_first" | "only_second";
 
 /**
  * Outputs of inference for the Translation task

package/src/tasks/translation/spec/input.json

@@ -1,7 +1,50 @@
 {
-	"$ref": "/inference/schemas/text2text-generation/input.json",
 	"$id": "/inference/schemas/translation/input.json",
 	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Inputs for Translation inference",
 	"title": "TranslationInput",
-	"description": "Inputs for Translation inference"
+	"type": "object",
+	"properties": {
+		"inputs": {
+			"description": "The text to translate.",
+			"type": "string"
+		},
+		"parameters": {
+			"description": "Additional inference parameters",
+			"$ref": "#/$defs/TranslationParameters"
+		}
+	},
+	"$defs": {
+		"TranslationParameters": {
+			"title": "TranslationParameters",
+			"description": "Additional inference parameters for Translation",
+			"type": "object",
+			"properties": {
+				"src_lang": {
+					"type": "string",
+					"description": "The source language of the text. Required for models that can translate from multiple languages."
+				},
+				"tgt_lang": {
+					"type": "string",
+					"description": "Target language to translate to. Required for models that can translate to multiple languages."
+				},
+				"clean_up_tokenization_spaces": {
+					"type": "boolean",
+					"description": "Whether to clean up the potential extra spaces in the text output."
+				},
+				"truncation": {
+					"title": "TranslationTruncationStrategy",
+					"type": "string",
+					"description": "The truncation strategy to use.",
+					"enum": ["do_not_truncate", "longest_first", "only_first", "only_second"]
+				},
+				"generate_parameters": {
+					"title": "generateParameters",
+					"type": "object",
+					"description": "Additional parametrization of the text generation algorithm."
+				}
+			}
+		}
+	},
+	"required": ["inputs"]
 }

package/src/tasks/zero-shot-classification/spec/output.json

@@ -5,6 +5,7 @@
 	"title": "ZeroShotClassificationOutput",
 	"type": "array",
 	"items": {
+		"type": "object",
 		"$ref": "/inference/schemas/common-definitions.json#/definitions/ClassificationOutput"
 	}
 }