{ "openapi": "3.0.1", "info": { "title": "Docs to Answers Pack — Citable AI-Ready Chunks", "description": "Turn a documentation site into a corpus an AI can answer FROM and CITE. Splits on headings rather than character counts, attaches a heading path and deep link to every chunk, drops boilerplate that repeats across pages, and hashes each chunk so you re-embed only what changed.", "version": "0.1", "x-build-id": "uYdAyIXuQ0krerRPB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/alaudinburki~docs-to-answers/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-alaudinburki-docs-to-answers", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/alaudinburki~docs-to-answers/runs": { "post": { "operationId": "runs-sync-alaudinburki-docs-to-answers", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/alaudinburki~docs-to-answers/run-sync": { "post": { "operationId": "run-sync-alaudinburki-docs-to-answers", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Documentation URLs", "type": "array", "description": "Where to start crawling. Point it at a docs homepage or section index.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pathPrefix": { "title": "Restrict to path prefix", "type": "string", "description": "Only crawl URLs whose path starts with this, e.g. /docs. The single most effective way to keep a blog or marketing site out of your corpus." }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Upper bound on pages fetched.", "default": 100 }, "followLinks": { "title": "Follow links", "type": "boolean", "description": "Crawl onward from the pages given. Turn off to process only the exact URLs supplied.", "default": true }, "sameOriginOnly": { "title": "Stay on the same domain", "type": "boolean", "description": "Only follow links on the same domain as the start URL. Turn off only if your docs span subdomains.", "default": true }, "maxChunkChars": { "title": "Max chunk size (characters)", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Chunks split on headings first and size second, so this is a ceiling rather than a target. ~1500 chars suits most embedding models.", "default": 1500 }, "minChunkChars": { "title": "Min chunk size (characters)", "minimum": 0, "type": "integer", "description": "Anything smaller is folded into the previous chunk instead of being emitted as an unanswerable fragment.", "default": 120 }, "overlapChars": { "title": "Overlap between chunks", "minimum": 0, "maximum": 500, "type": "integer", "description": "Repeat this many characters from the previous chunk so a sentence spanning a boundary stays retrievable from both sides.", "default": 100 }, "dropRepeatedBoilerplate": { "title": "Drop repeated boilerplate", "type": "boolean", "description": "Remove chunks that repeat across pages — \"Was this page helpful?\", licence footers, the same admonition on 90 pages. These match every query and answer none.", "default": true }, "nearDuplicateDetection": { "title": "Also catch near-duplicates", "type": "boolean", "description": "Catch boilerplate that differs by a word or two, not just exact repeats.", "default": true }, "incrementalMode": { "title": "Track changes between runs", "type": "boolean", "description": "Store a hash per chunk and label each one added / changed / unchanged / removed on the next run. Embedding is the expensive step in a RAG pipeline — this lets you re-embed only what actually changed.", "default": false }, "changedOnly": { "title": "Return only what changed", "type": "boolean", "description": "With incremental mode on, return just the added and changed chunks. Turns this into a scheduled corpus-refresh job.", "default": false }, "snapshotKey": { "title": "Snapshot key", "type": "string", "description": "Key-value store key holding the previous run's hashes. Use different keys to track several corpora independently.", "default": "CORPUS_SNAPSHOT" }, "concurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages to fetch at once. Lower it if the docs site is rate-limiting you.", "default": 8 }, "maxItems": { "title": "Max chunks", "minimum": 1, "type": "integer", "description": "Hard cap on results. You are never charged beyond this.", "default": 20000 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Most documentation sites need no proxy." }, "targetChunkChars": { "title": "Target chunk size (characters)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "Consecutive short sections on the same page are merged until they reach roughly this size. A 30-token chunk cannot answer a question — it only adds noise to retrieval. Set to 0 to keep every heading as its own chunk.", "default": 400 } } }, "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 } } } } } } } } } }