{ "openapi": "3.0.1", "info": { "title": "HuggingFace Models Scraper", "description": "Scrapes HuggingFace Hub for AI/ML models — trending, most downloaded, by task type, by author. Extracts model name, author, downloads, likes, task category, tags, pipeline tag, last modified, model card URL. Uses the HuggingFace JSON API for reliable structured data extraction.", "version": "1.0", "x-build-id": "C89Cc9e9gilTf1L36" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/resounding_diplomacy~huggingface-models-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-resounding_diplomacy-huggingface-models-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/resounding_diplomacy~huggingface-models-scraper/runs": { "post": { "operationId": "runs-sync-resounding_diplomacy-huggingface-models-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/resounding_diplomacy~huggingface-models-scraper/run-sync": { "post": { "operationId": "run-sync-resounding_diplomacy-huggingface-models-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "mode": { "title": "Mode", "enum": [ "trending", "downloads", "likes" ], "type": "string", "description": "How to sort/filter models", "default": "trending" }, "task": { "title": "Task Filter", "enum": [ "", "text-generation", "text-classification", "token-classification", "question-answering", "summarization", "translation", "text2text-generation", "fill-mask", "feature-extraction", "image-classification", "object-detection", "image-segmentation", "automatic-speech-recognition", "text-to-speech", "audio-classification", "image-generation", "text-to-image", "image-to-text", "visual-question-answering", "document-question-answering", "image-to-image", "mask-generation", "zero-shot-image-classification", "zero-shot-object-detection", "reinforcement-learning", "robotics", "tabular-classification", "tabular-regression", "image-to-video", "text-to-video", "video-classification", "voice-activity-detection" ], "type": "string", "description": "Filter models by pipeline/task type. Leave empty to get all tasks.", "default": "" }, "author": { "title": "Author Filter", "type": "string", "description": "Filter models by a specific author or organization (e.g. 'openai', 'meta-llama', 'mistralai'). Leave empty for all authors.", "default": "" }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of models to scrape (1–1000)", "default": 100 }, "includeModelCard": { "title": "Include Model Card Text", "type": "boolean", "description": "Fetch and include the full model card README text for each model. Slower but provides detailed descriptions.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }