{ "openapi": "3.0.1", "info": { "title": "🧩 RAG Dataset Builder - Crawl to Embedding-Ready Chunks", "description": "🧩 Crawl a site and get back a FINISHED, embedding-ready RAG dataset — not just clean text. ✅ Semantic chunking on heading boundaries, never mid-code-block or mid-table. ✅ Token estimator, configurable overlap, near-duplicate removal, full provenance per chunk.", "version": "1.0", "x-build-id": "Svpj8hqEGAMj489jy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~rag-dataset-builder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-rag-dataset-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~rag-dataset-builder/runs": { "post": { "operationId": "runs-sync-that_red_bird-rag-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~rag-dataset-builder/run-sync": { "post": { "operationId": "run-sync-that_red_bird-rag-dataset-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "siteUrl" ], "properties": { "siteUrl": { "title": "Site URL", "type": "string", "description": "The site to crawl, e.g. https://docs.example.com. Pages are discovered from its sitemap, or by following same-origin links if there is no sitemap.", "default": "https://docs.apify.com" }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Upper bound on pages to crawl and chunk.", "default": 100 }, "useSitemap": { "title": "Use sitemap.xml", "type": "boolean", "description": "Prefer the site's sitemap (including sitemap indexes) for discovery. Falls back to following same-origin links automatically if none is found.", "default": true }, "includePatterns": { "title": "Only URLs containing", "type": "array", "description": "Keep only URLs containing one of these substrings, e.g. /docs/, /guides/.", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs containing", "type": "array", "description": "Drop URLs containing any of these, e.g. /tag/, /author/, ?page=.", "items": { "type": "string" } }, "targetTokens": { "title": "Target tokens per chunk", "minimum": 20, "maximum": 4000, "type": "integer", "description": "Preferred chunk size. Chunk packing tries to land near this when a section has to be split, and a whole section under maxTokens is always kept as one chunk even if it's smaller or larger than this target.", "default": 350 }, "maxTokens": { "title": "Max tokens per chunk", "minimum": 20, "maximum": 8000, "type": "integer", "description": "Hard cap. No chunk exceeds this except the rare case where a single code block or table is itself bigger than the cap — it is kept whole rather than corrupted (see README limits). Must be >= targetTokens.", "default": 512 }, "overlapTokens": { "title": "Overlap between adjacent chunks (tokens)", "minimum": 0, "maximum": 500, "type": "integer", "description": "How much of the end of one chunk is repeated at the start of the next chunk from the same page, so retrieval doesn't lose context at a chunk boundary. Overlap always lands on a whole sentence or block, never mid-word. Set to 0 to disable.", "default": 40 }, "minChunkTokens": { "title": "Minimum tokens to keep a chunk", "minimum": 0, "maximum": 200, "type": "integer", "description": "Chunks estimated below this many tokens are dropped as too small to be useful on their own (e.g. a lone short heading with no body).", "default": 15 }, "dedupThreshold": { "title": "Near-duplicate similarity threshold (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Two chunks anywhere in the crawl are treated as near-duplicates and merged into one when their shingle-based Jaccard similarity is at or above this. Higher = fewer false merges, more repeated boilerplate left in. Expressed 0-100; 85 means 0.85.", "default": 85 }, "shingleSize": { "title": "Shingle size (words)", "minimum": 2, "maximum": 12, "type": "integer", "description": "Length of the word n-grams used to fingerprint each chunk for near-duplicate detection. Smaller catches shorter overlaps but is noisier; larger is stricter.", "default": 5 }, "includeLinks": { "title": "Keep markdown links", "type": "boolean", "description": "Preserve [text](url) links in the extracted markdown. Turn off for pure prose with no link noise.", "default": true }, "includeDuplicateRows": { "title": "Include removed-duplicate rows", "type": "boolean", "description": "Emit one row per removed near-duplicate chunk (type: \"duplicate\") showing which surviving chunk it matched and the similarity score. Off by default so the dataset stays a clean, ready-to-embed corpus.", "default": false }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages to fetch in parallel.", "default": 5 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional Apify proxy configuration." } } }, "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 } } } } } } } } } }