{ "openapi": "3.0.1", "info": { "title": "llms.txt Generator: Website to LLM & RAG Pack", "description": "Turn any website or docs site into a ready-to-use LLM pack: llms.txt (llmstxt.org format), llms-full.txt, clean Markdown pages and RAG-ready chunks.jsonl with URL and title metadata. Crawls sitemaps and links. For ChatGPT, Claude, custom GPTs, vector databases and AI SEO.", "version": "0.1", "x-build-id": "hnLhxQZ1bSBrt8Qy0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blond_terrarium~site-to-llm-pack/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blond_terrarium-site-to-llm-pack", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blond_terrarium~site-to-llm-pack/runs": { "post": { "operationId": "runs-sync-blond_terrarium-site-to-llm-pack", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blond_terrarium~site-to-llm-pack/run-sync": { "post": { "operationId": "run-sync-blond_terrarium-site-to-llm-pack", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "websites" ], "properties": { "websites": { "title": "Websites or docs URLs", "type": "array", "description": "One pack per URL. A homepage packs the whole site; a section URL (https://docs.example.com/guide/) packs just that section.", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Max pages per pack", "minimum": 1, "maximum": 5000, "type": "integer", "description": "One pack is charged per started 50 pages (1-50 pages = 1 pack, 51-100 = 2).", "default": 50 }, "crawlScope": { "title": "Crawl scope", "enum": [ "auto", "samePath", "sameHostname", "sameDomain" ], "type": "string", "description": "Which pages to include.", "default": "auto" }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Also discover pages from sitemap.xml (finds pages that are not linked).", "default": true }, "maxCrawlDepth": { "title": "Max link depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many clicks away from the start URL to follow links.", "default": 5 }, "contentMode": { "title": "Content extraction", "enum": [ "article", "fullPage" ], "type": "string", "description": "How to pick the text of each page.", "default": "article" }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Chunks split on headings and paragraphs for vector databases. 0 = one chunk per page.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated between consecutive chunks.", "default": 200 }, "includeUrlPatterns": { "title": "Only URLs matching (optional)", "type": "array", "description": "Regex or text patterns; only matching URLs are packed.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs matching (optional)", "type": "array", "description": "Regex or text patterns to leave out (for example /tag/, /login).", "items": { "type": "string" } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site asks crawlers not to visit.", "default": true }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many websites to pack at once.", "default": 2 }, "maxChargedPacks": { "title": "Max packs to charge (0 = no limit)", "minimum": 0, "type": "integer", "description": "Stop after this many charged packs. The run also stops at your \"Max cost per run\".", "default": 0 } } }, "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 } } } } } } } } } }