{ "openapi": "3.0.1", "info": { "title": "Docs → RAG Corpus Builder (LLM-ready Markdown + llms.txt)", "description": "Crawl any documentation site into an embeddings-ready corpus: clean markdown chunks with heading-path metadata, generated llms.txt, corpus.jsonl, and optional OpenAI embeddings.", "version": "0.1", "x-build-id": "Lvx3AUojv8SwYKsyO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yasaslive~docs-rag-builder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yasaslive-docs-rag-builder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yasaslive~docs-rag-builder/runs": { "post": { "operationId": "runs-sync-yasaslive-docs-rag-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yasaslive~docs-rag-builder/run-sync": { "post": { "operationId": "run-sync-yasaslive-docs-rag-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Documentation site entry points. The actor stays on the same origin(s) as these URLs. Sitemap discovery (/robots.txt + /sitemap.xml) is attempted first; link crawling is the fallback.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includeGlobs": { "title": "Include globs", "type": "array", "description": "Optional minimatch globs. When set, only URLs matching at least one glob are crawled. Globs are tested against both the full URL (e.g. `https://docs.example.com/api/**`) and the pathname (e.g. `/api/**`).", "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude globs", "type": "array", "description": "Optional minimatch globs. URLs matching any glob are skipped. Tested against both the full URL and the pathname.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on the number of pages crawled.", "default": 500 }, "versionMode": { "title": "Version mode", "enum": [ "all", "latest-only" ], "type": "string", "description": "`all` crawls every matched URL and tags each with its detected docs version. `latest-only` drops URLs whose path matches the version pattern (unless they match the pinned version), keeping only unversioned = latest pages.", "default": "all" }, "versionPattern": { "title": "Version pattern (regex)", "type": "string", "description": "Regex applied to the URL path to detect a docs version segment. The first match (first capture group if present) becomes `detectedVersion` on every chunk.", "default": "/(v\\d+(\\.\\d+)*|\\d+\\.\\d+)/" }, "pinnedVersion": { "title": "Pinned version", "type": "string", "description": "In `latest-only` mode, versioned URLs whose detected version equals this value (e.g. `v2` or `3.1`) are kept instead of dropped." }, "maxChunkTokens": { "title": "Max tokens per chunk", "minimum": 64, "maximum": 8192, "type": "integer", "description": "Token budget per chunk (cl100k_base estimate via js-tiktoken). Sections are split on heading boundaries first, then packed into chunks up to this size. Fenced code blocks are never split — oversized ones become single chunks flagged `oversized: true`.", "default": 512 }, "chunkOverlapTokens": { "title": "Chunk overlap tokens", "minimum": 0, "maximum": 2048, "type": "integer", "description": "Approximate token overlap carried between consecutive chunks split from the same section (trailing sentences only, never code).", "default": 64 }, "openaiApiKey": { "title": "OpenAI API key (optional)", "type": "string", "description": "When set, every chunk is embedded (batches of 100) and `embeddings.jsonl` is written to the key-value store. The key is only sent to api.openai.com and never stored or logged." }, "embeddingModel": { "title": "Embedding model", "type": "string", "description": "OpenAI embedding model used when an API key is provided.", "default": "text-embedding-3-small" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy to use for crawling. Apify Proxy (automatic) is recommended for reliability on protected sites." } } }, "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 } } } } } } } } } }