{ "openapi": "3.0.1", "info": { "title": "Compliance-Grade Web Intelligence for AI Agents", "description": "The scraper AI agents trust. Extract grounded facts with citations, entities, claims & RAG chunks. Built for LangChain, LlamaIndex, AutoGPT. Quality scoring, auto-citations, 6 task modes.", "version": "0.0", "x-build-id": "AuleDWRWEfO5euxsS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ai_solutionist~compliance-web-intel/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ai_solutionist-compliance-web-intel", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ai_solutionist~compliance-web-intel/runs": { "post": { "operationId": "runs-sync-ai_solutionist-compliance-web-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ai_solutionist~compliance-web-intel/run-sync": { "post": { "operationId": "run-sync-ai_solutionist-compliance-web-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "URLs to crawl. The actor discovers related pages based on task mode. For competitor analysis, start with the homepage. For pricing intel, start with the pricing page directly.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "taskMode": { "title": "Task Mode", "enum": [ "competitor_teardown", "compliance_discovery", "local_seo_audit", "sales_research", "docs_extraction", "pricing_intelligence", "general" ], "type": "string", "description": "Pre-configured extraction focus for common AI agent workflows. Each mode prioritizes different page types and extracts mode-specific intelligence.", "default": "general" }, "maxPages": { "title": "Max Pages to Crawl", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of pages to process per run. Start with 10-20 for initial exploration, scale up for comprehensive coverage. Each page produces one Reasoning Pack.", "default": 50 }, "maxDepth": { "title": "Crawl Depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many link levels deep to follow from start URLs. Depth 1 = only direct links. Depth 2-3 recommended for comprehensive site coverage.", "default": 3 }, "includePatterns": { "title": "Include URL Patterns (Regex)", "type": "array", "description": "Only crawl URLs matching these patterns. Use for focused extraction. Example: '/pricing' to only get pricing pages, '/docs/' for documentation only.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL Patterns (Regex)", "type": "array", "description": "Skip URLs matching these patterns. Recommended: exclude blog posts, news, tags unless specifically needed.", "items": { "type": "string" } }, "minRelevanceScore": { "title": "Minimum URL Relevance Score", "minimum": 0, "maximum": 1, "type": "number", "description": "Only crawl URLs with task-mode relevance above this threshold. 0.5 = moderately relevant, 0.7 = highly relevant. Lower for broader coverage, higher for focused extraction.", "default": 0.5 }, "ragChunkSize": { "title": "RAG Chunk Size (Tokens)", "minimum": 200, "maximum": 2000, "type": "integer", "description": "Target size for RAG-ready chunks. 500-900 tokens optimal for most embedding models. Chunks include 50-token overlap for context continuity.", "default": 750 }, "diffBaseline": { "title": "Baseline Run ID for Change Detection", "type": "string", "description": "Compare against a previous run to detect content changes. Enter the Run ID from a previous execution. Changes are scored by materiality (0-1)." }, "alertWebhook": { "title": "Alert Webhook URL", "type": "string", "description": "Webhook to call when material changes are detected (materialityScore > 0.5). Receives JSON payload with changed pages and diff summary. Perfect for n8n or Zapier triggers." }, "screenshotPages": { "title": "Capture Page Screenshots", "type": "boolean", "description": "Save screenshots of each page to Key-Value Store. Useful for visual comparison and compliance evidence. Increases run time and storage usage.", "default": false }, "extractPricing": { "title": "Extract Pricing Information", "type": "boolean", "description": "Detect and extract pricing from pages (amounts, currencies, periods, tier names). Automatically enabled for pricing_intelligence mode.", "default": true }, "extractEntities": { "title": "Extract Named Entities", "type": "boolean", "description": "Extract people, organizations, locations, money amounts, dates, emails, phones. Each entity includes sourceBlockId for citation.", "default": true }, "proxyConfig": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxy usage. Apify Proxy recommended for reliability. Residential proxies for sites with strict anti-bot measures.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }