{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper", "description": "Extract AI models, datasets, spaces, and papers from Hugging Face Hub. Filter by task, library, author, or language. Sort by downloads, likes, or trending. No API key needed.", "version": "0.1", "x-build-id": "LIcyX0Y35y38Dt3qN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~huggingface-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-huggingface-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~huggingface-scraper/runs": { "post": { "operationId": "runs-sync-automation-lab-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~huggingface-scraper/run-sync": { "post": { "operationId": "run-sync-automation-lab-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "resourceType": { "title": "🗂️ Resource type", "enum": [ "models", "datasets", "spaces", "papers" ], "type": "string", "description": "Choose what to scrape: AI models, datasets, spaces (apps/demos), or research papers.", "default": "models" }, "searchQuery": { "title": "Search query", "type": "string", "description": "Search keyword to filter results (e.g. \"llama\", \"stable diffusion\", \"bert\"). Leave empty to browse all items." }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "Maximum number of items to extract. Set 0 for unlimited (use with caution — HF has millions of models).", "default": 100 }, "trendingMode": { "title": "🔥 Trending models mode", "type": "boolean", "description": "When enabled, overrides Resource type to Models and Sort by to Trending. Quickly get the hottest models gaining momentum right now.", "default": false }, "comparisonMode": { "title": "📊 Comparison mode (models only)", "type": "boolean", "description": "When enabled, saves a structured comparison table to the Key-Value Store under key MODEL_COMPARISON. Each row includes rank, license, downloads, likes, framework, and README excerpt — ideal for diffing models side by side.", "default": false }, "includeReadmeExcerpt": { "title": "📄 Include README excerpt (models only)", "type": "boolean", "description": "When enabled, fetches the first 500 characters of each model's README card. Adds one API request per model — use with small maxItems (≤20) to avoid slow runs.", "default": false }, "sortBy": { "title": "Sort by", "enum": [ "downloads", "likes", "trendingScore", "createdAt", "lastModified" ], "type": "string", "description": "Sort results by downloads, likes, trending score, or creation date. \"Trending\" reflects recent momentum. Ignored when Trending mode is enabled.", "default": "downloads" }, "pipelineTag": { "title": "Task / pipeline tag", "enum": [ "", "text-generation", "text-classification", "token-classification", "question-answering", "summarization", "translation", "fill-mask", "text2text-generation", "image-classification", "image-segmentation", "object-detection", "image-to-text", "text-to-image", "text-to-video", "automatic-speech-recognition", "audio-classification", "text-to-speech", "sentence-similarity", "feature-extraction", "zero-shot-classification", "zero-shot-image-classification", "visual-question-answering", "document-question-answering", "depth-estimation", "video-classification", "reinforcement-learning", "tabular-classification", "tabular-regression", "time-series-forecasting" ], "type": "string", "description": "Filter models/datasets by ML task type. Leave empty for all tasks." }, "library": { "title": "Library / framework", "enum": [ "", "transformers", "diffusers", "sentence-transformers", "timm", "peft", "llama-cpp", "pytorch", "tensorflow", "jax", "keras", "onnx", "safetensors", "mlx", "fastai", "flair", "spacy", "openai-whisper", "stable-baselines3" ], "type": "string", "description": "Filter models by ML framework. Leave empty for all frameworks. Models only." }, "license": { "title": "License", "enum": [ "", "mit", "apache-2.0", "openrail", "openrail++", "llama3", "llama3.1", "llama3.2", "llama3.3", "gemma", "gpl-3.0", "lgpl-3.0", "bsd-3-clause", "bsd-2-clause", "cc-by-4.0", "cc-by-sa-4.0", "cc-by-nc-4.0", "cc-by-nc-sa-4.0", "cc0-1.0", "wtfpl", "other", "unlicense" ], "type": "string", "description": "Filter models by license type. Useful for finding commercially usable open-source models. Leave empty for all licenses. Models only." }, "author": { "title": "Author / organization", "type": "string", "description": "Filter by author username or organization name. Examples: meta-llama, google, microsoft, mistralai, stabilityai." }, "language": { "title": "Language", "type": "string", "description": "Filter models/datasets by language code. Examples: en, fr, zh, de, es, ja, ar." }, "batchSize": { "title": "Batch size (items per request)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of items fetched per API request. Maximum 100. Reduce to 25-50 if you hit rate limits.", "default": 100 }, "maxRetries": { "title": "Max retries per request", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of retry attempts for failed HTTP requests.", "default": 3 } } }, "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 } } } } } } } } } }