{ "openapi": "3.0.1", "info": { "title": "Website Services Finder", "description": "Automatically extract and analyze company services from any business website using advanced AI. Choose from 5 AI providers and 23+ models to intelligently identify and categorize a company’s offered services — perfect for lead generation, market research, and competitive analysis.", "version": "0.0", "x-build-id": "SUJ5ybVghuomJEkbo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rigelbytes~website-services-finder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rigelbytes-website-services-finder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rigelbytes~website-services-finder/runs": { "post": { "operationId": "runs-sync-rigelbytes-website-services-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rigelbytes~website-services-finder/run-sync": { "post": { "operationId": "run-sync-rigelbytes-website-services-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls", "provider" ], "properties": { "urls": { "title": "Start URLs", "type": "array", "description": "URLs of company websites to extract services from" }, "custom_prompt": { "title": "Custom Prompt", "type": "string", "description": "Custom prompt to guide the AI in extracting services (optional)" }, "provider": { "title": "AI Provider", "enum": [ "groq", "openai", "anthropic", "gemini", "huggingface" ], "type": "string", "description": "Select the AI provider to use for service extraction", "default": "openai" }, "openai_api_key": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key (required if using OpenAI model)." }, "anthropic_api_key": { "title": "Anthropic API Key", "type": "string", "description": "Your Anthropic API key (required if using Anthropic model)." }, "groq_api_key": { "title": "Groq API Key", "type": "string", "description": "Your Groq API key (required if using Groq model)." }, "huggingface_api_key": { "title": "Hugging Face API Key", "type": "string", "description": "Your Hugging Face API key (required if using Hugging Face model)." }, "gemini_api_key": { "title": "Gemini API Key", "type": "string", "description": "Your Google Gemini API key (required if using Gemini model)." }, "model_name": { "title": "AI Model", "enum": [ "llama-3.3-70b-versatile", "llama-3.1-70b-versatile", "llama-3.1-8b-instant", "mixtral-8x7b-32768", "gemma2-9b-it", "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4", "gpt-3.5-turbo", "claude-3-5-sonnet-latest", "claude-3-5-haiku-latest", "claude-3-opus-latest", "claude-3-sonnet-20240229", "claude-3-haiku-20240307", "gemini-1.5-pro", "gemini-1.5-flash", "gemini-2.0-flash-exp", "meta-llama/Meta-Llama-3-8B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct", "mistralai/Mistral-7B-Instruct-v0.3", "microsoft/Phi-3-mini-4k-instruct", "Qwen/Qwen2.5-7B-Instruct" ], "type": "string", "description": "AI model to use (only if AI Provider is Groq)", "default": "gpt-4o" }, "provider_name": { "title": "Hugging Face Provider Name", "type": "string", "description": "Provider Name for Hugging Face (Cerebras, Together AI, Cohere..etc) https://hf.co/settings/inference-providers" }, "maxRequestsPerCrawl": { "title": "Max Requests per Crawl", "minimum": 0, "type": "integer", "description": "Maximum number of pages to scrape (0 = unlimited)", "default": 100 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for web scraping", "default": { "useApifyProxy": false } }, "groupServices": { "title": "Group Similar Services", "type": "boolean", "description": "Group companies by similar services after scraping. Uses AI embeddings to identify semantically similar services (e.g., 'QuickBooks Hosting' and 'QuickBooks Cloud Hosting')", "default": false }, "similarityThreshold": { "title": "Service Similarity Threshold", "minimum": 0.7, "maximum": 0.95, "type": "number", "description": "Threshold for grouping similar services (0.70-0.95). Higher values = stricter matching. Recommended: 0.85", "default": 0.85 } } }, "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 } } } } } } } } } }