Ai-ML-scraper
Pricing
from $0.50 / 1,000 results
Go to Apify Store
Ai-ML-scraper
Search AI/ML models, research papers, and trending papers from HuggingFace Hub and arXiv. No API key required.
Ai-ML-scraper
Pricing
from $0.50 / 1,000 results
Search AI/ML models, research papers, and trending papers from HuggingFace Hub and arXiv. No API key required.
You can access the Ai-ML-scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "ogdwzmruRrVR6mJuH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/labrat011~ai-ml-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-labrat011-ai-ml-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/labrat011~ai-ml-scraper/runs": { "post": { "operationId": "runs-sync-labrat011-ai-ml-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/labrat011~ai-ml-scraper/run-sync": { "post": { "operationId": "run-sync-labrat011-ai-ml-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": [ "mode" ], "properties": { "mode": { "title": "Scraping mode", "enum": [ "search_models", "search_papers", "trending_papers" ], "type": "string", "description": "What type of AI/ML data to search for.", "default": "search_models" }, "query": { "title": "Search query", "type": "string", "description": "Search keyword for models or papers. For arXiv, searches titles and abstracts." }, "sort": { "title": "Sort by", "enum": [ "downloads", "likes", "trending", "relevance", "submittedDate", "lastUpdatedDate" ], "type": "string", "description": "How to sort results. Options depend on the mode.", "default": "downloads" }, "pipelineTag": { "title": "Pipeline task (Models only)", "enum": [ "", "text-generation", "text-classification", "token-classification", "question-answering", "summarization", "translation", "fill-mask", "text2text-generation", "conversational", "text-to-image", "image-to-text", "image-classification", "object-detection", "image-segmentation", "automatic-speech-recognition", "text-to-speech", "audio-classification", "feature-extraction", "sentence-similarity", "zero-shot-classification", "reinforcement-learning", "depth-estimation", "image-to-image", "video-classification" ], "type": "string", "description": "Filter models by pipeline task. Leave empty for all tasks.", "default": "" }, "libraryFilter": { "title": "Framework / Library (Models only)", "enum": [ "", "transformers", "diffusers", "pytorch", "tensorflow", "jax", "onnx", "safetensors", "gguf", "spacy", "keras", "sklearn", "sentence-transformers", "peft", "adapter-transformers" ], "type": "string", "description": "Filter models by ML framework. Leave empty for all frameworks.", "default": "" }, "arxivCategory": { "title": "arXiv category", "enum": [ "", "cs.AI", "cs.LG", "cs.CL", "cs.CV", "cs.NE", "cs.RO", "cs.IR", "cs.MA", "stat.ML", "cs.SD", "eess.AS", "cs.HC", "cs.CR" ], "type": "string", "description": "Filter papers by arXiv category. Leave empty to search all AI/ML categories.", "default": "" }, "author": { "title": "Author name (Papers only)", "type": "string", "description": "Filter arXiv papers by author name." }, "dateFrom": { "title": "Date from (Papers only)", "type": "string", "description": "Filter papers published from this date (YYYY-MM-DD)." }, "dateTo": { "title": "Date to (Papers only)", "type": "string", "description": "Filter papers published up to this date (YYYY-MM-DD)." }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of results to return. Free users are limited to 25 results per run.", "default": 100 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Ai-ML-scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: