{ "openapi": "3.0.1", "info": { "title": "Suchi.Anantasutra: llms.txt & llms-full.txt Generator", "description": "Generate a spec-compliant llms.txt and llms-full.txt for any website: robots.txt-respecting crawl, sitemap-first discovery and clean Markdown per page. Pay per page, no subscription.", "version": "0.1", "x-build-id": "8mssKZZljoxpZhfVv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/motivating_bracelet~suchi-anantasutra/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-motivating_bracelet-suchi-anantasutra", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/motivating_bracelet~suchi-anantasutra/runs": { "post": { "operationId": "runs-sync-motivating_bracelet-suchi-anantasutra", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/motivating_bracelet~suchi-anantasutra/run-sync": { "post": { "operationId": "run-sync-motivating_bracelet-suchi-anantasutra", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl" ], "properties": { "startUrl": { "title": "Website URL", "type": "string", "description": "Homepage or docs root, e.g. https://docs.example.com/ or https://example.com/docs/. By default only pages under this path are included, which also lets you build a section-level llms.txt such as /docs/llms.txt." }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many pages to include. Each processed page is billed once; skipped pages (robots.txt, noindex, little text, near-duplicate copies under session IDs or crawl-trap URLs) are not. llms.txt lists every processed page; llms-full.txt contains their full text.", "default": 20 }, "crawlScope": { "title": "Crawl scope", "enum": [ "path", "site" ], "type": "string", "description": "Only pages under the start URL's path (default), or the whole site.", "default": "path" }, "includeGlobs": { "title": "Include only paths", "type": "array", "description": "Optional path globs to include, e.g. /docs/** or /guides/*. ** matches any depth, * one path segment. Empty = everything in scope.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude paths", "type": "array", "description": "Path globs to skip, e.g. /blog/** or /tag/*.", "default": [], "items": { "type": "string" } }, "optionalGlobs": { "title": "Paths for the Optional section", "type": "array", "description": "Pages matching these globs are listed under \"## Optional\" in llms.txt (secondary links agents may skip), e.g. /blog/** or /changelog/**.", "default": [], "items": { "type": "string" } }, "sectionMode": { "title": "Section grouping", "enum": [ "path", "single" ], "type": "string", "description": "Group links by their first path segment (Docs, Guides, API ...) or list everything in one section.", "default": "path" }, "siteName": { "title": "Site name (H1)", "type": "string", "description": "Overrides the detected site name used as the llms.txt H1." }, "siteSummary": { "title": "Summary (blockquote)", "type": "string", "description": "Overrides the detected one-paragraph summary shown under the H1." }, "useSitemap": { "title": "Use sitemap.xml", "type": "boolean", "description": "Discover pages from the sitemaps declared in robots.txt (or /sitemap.xml) before following links.", "default": true }, "preferMarkdownLinks": { "title": "Link to Markdown versions when available", "type": "boolean", "description": "If a page declares , llms.txt links to that Markdown URL, as the llmstxt.org proposal recommends.", "default": true }, "skipNoindex": { "title": "Skip noindex pages", "type": "boolean", "description": "Do not include pages marked with a robots noindex meta tag.", "default": true }, "includeMarkdownInDataset": { "title": "Include Markdown in dataset rows", "type": "boolean", "description": "Store each page's Markdown in its dataset row (useful for RAG pipelines). Turn off for smaller datasets.", "default": true }, "maxCharsPerPage": { "title": "Maximum characters per page", "minimum": 1000, "maximum": 200000, "type": "integer", "description": "Longer pages are truncated in llms-full.txt and the dataset.", "default": 30000 }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 5, "type": "integer", "description": "Pages fetched at the same time (1-5). A Crawl-delay in robots.txt forces 1.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 60, "type": "integer", "description": "Timeout for each HTTP request.", "default": 20 } } }, "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 } } } } } } } } } }