{ "openapi": "3.0.1", "info": { "title": "Hugging Face Insights Scraper — Models, Datasets & Spaces", "description": "Scrape Hugging Face models, datasets, spaces, and daily papers with downloads, likes, parameters, tags, and growth tracking between runs. Filter by pipeline, library, author, or keyword.", "version": "1.0", "x-build-id": "f0E3K5vgStiamGU0H" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brilliant_gum~huggingface-insights-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brilliant_gum-huggingface-insights-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brilliant_gum~huggingface-insights-scraper/runs": { "post": { "operationId": "runs-sync-brilliant_gum-huggingface-insights-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brilliant_gum~huggingface-insights-scraper/run-sync": { "post": { "operationId": "run-sync-brilliant_gum-huggingface-insights-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "resourceType" ], "properties": { "resourceType": { "title": "Resource Type", "enum": [ "models", "datasets", "spaces", "papers" ], "type": "string", "description": "What to scrape: AI models, datasets, Spaces (demos), or daily research papers.", "default": "models" }, "search": { "title": "Search Keyword", "type": "string", "description": "Filter by keyword (e.g. 'llama', 'sentiment', 'stable diffusion'). Leave empty to browse all.", "default": "" }, "author": { "title": "Author / Organization", "type": "string", "description": "Filter by author or org (e.g. 'meta-llama', 'openai', 'google'). Leave empty for all authors.", "default": "" }, "pipeline_tag": { "title": "Pipeline Tag (Models only)", "enum": [ "", "text-generation", "text-classification", "text-to-image", "image-classification", "automatic-speech-recognition", "translation", "summarization", "question-answering", "fill-mask", "token-classification", "feature-extraction", "sentence-similarity", "object-detection", "image-segmentation", "text-to-speech", "image-to-text", "zero-shot-classification", "depth-estimation", "reinforcement-learning" ], "type": "string", "description": "Filter models by task type.", "default": "" }, "library": { "title": "Library (Models only)", "type": "string", "description": "Filter models by ML library (e.g. 'transformers', 'diffusers', 'sentence-transformers').", "default": "" }, "tags": { "title": "Tags", "type": "string", "description": "Filter by tags like 'license:mit', 'language:en'. Comma-separated.", "default": "" }, "sort": { "title": "Sort By", "enum": [ "downloads", "likes", "lastModified", "createdAt", "trending" ], "type": "string", "description": "How to sort results.", "default": "downloads" }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of items to return. Up to 10000 with pagination.", "default": 100 }, "fetchDetails": { "title": "Fetch Full Details", "type": "boolean", "description": "Fetch detailed info for each item (parameters, architectures, files). Slower but richer data. Not needed for papers.", "default": false }, "minDownloads": { "title": "Min Downloads", "minimum": 0, "type": "integer", "description": "Only include items with at least this many downloads.", "default": 0 }, "minLikes": { "title": "Min Likes", "minimum": 0, "type": "integer", "description": "Only include items with at least this many likes.", "default": 0 }, "minParameters": { "title": "Min Parameters (Models only)", "minimum": 0, "type": "integer", "description": "Only include models with at least this many parameters. E.g. 1000000000 for 1B+. Requires fetchDetails for accuracy.", "default": 0 }, "maxParameters": { "title": "Max Parameters (Models only)", "minimum": 0, "type": "integer", "description": "Only include models with at most this many parameters. 0 = no limit.", "default": 0 }, "excludeGated": { "title": "Exclude Gated", "type": "boolean", "description": "Exclude gated models/datasets that require access approval.", "default": false }, "excludePrivate": { "title": "Exclude Private", "type": "boolean", "description": "Exclude private items (recommended).", "default": true }, "enableHistory": { "title": "Enable History Tracking", "type": "boolean", "description": "Track downloads/likes changes between scheduled runs. Stores snapshots in a named KV store.", "default": false }, "historyStoreName": { "title": "History Store Name", "type": "string", "description": "Name of the Key-Value store for history snapshots.", "default": "hf-history" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional proxy settings. HF API works without proxy, but can help with rate limits." } } }, "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 } } } } } } } } } }