{ "openapi": "3.0.1", "info": { "title": "Technical Docs To Rag Markdown Chunker", "description": "Convert public documentation into clean Markdown and RAG chunks with source URLs, section context and content hashes. Discover pages through sitemaps and llms.txt, preserve code and tables, and export JSON for embedding and vector database pipelines.", "version": "0.0", "x-build-id": "ymF7p38CLTnWTbLug" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/arezdev~technical-docs-to-rag-markdown-chunker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-arezdev-technical-docs-to-rag-markdown-chunker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/arezdev~technical-docs-to-rag-markdown-chunker/runs": { "post": { "operationId": "runs-sync-arezdev-technical-docs-to-rag-markdown-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/arezdev~technical-docs-to-rag-markdown-chunker/run-sync": { "post": { "operationId": "run-sync-arezdev-technical-docs-to-rag-markdown-chunker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "docsUrls" ], "properties": { "docsUrls": { "title": "Documentation URLs", "type": "array", "description": "Public HTTP or HTTPS pages. With discovery enabled, each URL defines an origin and path prefix. Subpaths match on path boundaries. Up to 2000 URLs.", "default": [ "https://docs.apify.com/actors" ], "items": { "type": "string" } }, "crawlViaSitemap": { "title": "Discover documentation pages", "type": "boolean", "description": "Check llms-full.txt, llms.txt, then sitemap.xml. Follow matching prefix URLs and nested sitemap indexes; otherwise process the supplied URL.", "default": false }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Maximum unique documentation pages attempted across all input URLs. A page can yield multiple billable chunks.", "default": 2 }, "maxItems": { "title": "Maximum output rows (optional)", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Optional additional cap on saved chunks and error rows. Omit for unlimited rows within the page, free-plan, and event-budget limits. The prefilled sample saves at most three rows." }, "maxTokensPerChunk": { "title": "Target maximum tokens per chunk", "minimum": 100, "maximum": 4000, "type": "integer", "description": "Estimated tokens including section context. Uses UTF-8 bytes divided by four, rounded up. Fenced code blocks and indivisible table rows are kept whole and may exceed this target.", "default": 500 }, "overlapTokens": { "title": "Prose overlap tokens", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum trailing prose context repeated in the next chunk when space permits. Must be smaller than maxTokensPerChunk. Code blocks and table rows are not duplicated.", "default": 50 }, "timeoutSecs": { "title": "Request timeout in seconds", "minimum": 3, "maximum": 60, "type": "integer", "description": "Total deadline for one logical request, including DNS, redirect validation, protocol retries, and proxy attempts.", "default": 15 }, "maxConcurrency": { "title": "Maximum request concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Upper bound for parallel page requests. Automatically reduced to one worker per 64 MB of assigned memory to bound parser memory use; four workers at 256 MB.", "default": 25 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Direct connections first, then datacenter fallback for 403, 429, or 503. Configured groups are used only when explicitly enabled. Custom proxy URLs are forced; useApifyProxy: false disables automatic proxies." } } }, "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 } } } } } } } } } }