{ "openapi": "3.0.1", "info": { "title": "LLM Wiki & OKF Bundle Generator: Website to Knowledge Base", "description": "Turn any docs site, help center or Apify dataset into an Open Knowledge Format (OKF) bundle for AI agents: markdown concepts with frontmatter, index files, a zip and a graph viewer.", "version": "0.1", "x-build-id": "bGSKaW6ReEROs5ov0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrape-lads~llm-wiki-okf-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrape-lads-llm-wiki-okf-generator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrape-lads~llm-wiki-okf-generator/runs": { "post": { "operationId": "runs-sync-scrape-lads-llm-wiki-okf-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrape-lads~llm-wiki-okf-generator/run-sync": { "post": { "operationId": "run-sync-scrape-lads-llm-wiki-okf-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Websites or sections to turn into concepts, for example a docs site, help center or API reference. With the default scope the crawler stays under each URL's path, so https://docs.apify.com/academy only crawls pages under /academy. Leave empty to build a bundle from datasets only.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "datasetIds": { "title": "Apify datasets", "type": "array", "description": "Optional. Pick Apify datasets to document (read-only access). Each dataset becomes one concept with its inferred schema, fill rates, sample items and joins to the other datasets." }, "aiEnrichment": { "title": "AI summaries and classification", "type": "boolean", "description": "Each concept gets an AI-written type, one-line description, tags, summary and key facts. Turn off for a cheaper bundle with the page content only.", "default": true }, "includePageContent": { "title": "Include full page content", "type": "boolean", "description": "Keep the cleaned page Markdown under # Content in each concept. Turn off for compact concepts with only the AI summary and key facts (always kept when AI is off).", "default": true }, "groupBy": { "title": "Folder layout", "enum": [ "url", "type" ], "type": "string", "description": "How concept files are arranged in the bundle. Grouping by type needs AI enrichment; without it the URL layout is used.", "default": "url" }, "bundleName": { "title": "Bundle name", "type": "string", "description": "Name of the bundle folder and viewer title. Defaults to the website's host name." }, "staleAfterDays": { "title": "Stale after (days)", "minimum": 0, "maximum": 3650, "type": "integer", "description": "Sets each concept's stale_after date this many days ahead, so agents know when to refresh it. 0 leaves it out.", "default": 90 }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many pages. Each page becomes one concept, so this is also your price cap.", "default": 50 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many links away from a start URL to follow. 0 crawls only the start URLs.", "default": 5 }, "crawlScope": { "title": "Crawl scope", "enum": [ "path", "hostname", "domain" ], "type": "string", "description": "Which discovered links to follow. \"Same path\" stays under the start URL's folder, \"Same hostname\" allows the whole host, \"Same domain\" also allows subdomains.", "default": "path" }, "includeUrlGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Optional. Only follow links matching one of these glob patterns, e.g. https://example.com/docs/**. Applied on top of the crawl scope.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeUrlGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Optional. Never follow links matching these glob patterns, e.g. **/changelog/** or **/*?page=*.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "useSitemaps": { "title": "Discover pages from sitemaps", "type": "boolean", "description": "Also read robots.txt Sitemap entries and /sitemap.xml to find pages that are not linked. In-scope sitemap URLs are crawled alongside discovered links.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the site's robots.txt disallows.", "default": true }, "removeBoilerplate": { "title": "Remove boilerplate", "type": "boolean", "description": "Strip navigation, headers, footers, sidebars, cookie banners and share widgets, and keep the main content only.", "default": true }, "removeElementsCssSelector": { "title": "Extra elements to remove (CSS selector)", "type": "string", "description": "Optional CSS selector of additional elements to delete before conversion, e.g. .ad-slot, #comments." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel HTTP requests. Browser pages are always limited to a few at a time.", "default": 10 }, "crawlerType": { "title": "Crawler type", "enum": [ "auto", "http" ], "type": "string", "description": "Auto fetches pages over HTTP and renders only empty JavaScript app shells in a headless browser.", "default": "auto" }, "datasetSampleSize": { "title": "Dataset sample size", "minimum": 10, "maximum": 5000, "type": "integer", "description": "How many items of each dataset are read to infer its schema.", "default": 500 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }