{ "openapi": "3.0.1", "info": { "title": "Q&A Knowledge Extractor (Stack Exchange)", "description": "Extracts RAG-ready Q&A pairs from the Stack Exchange network via the official API. Returns coupled question+answer records with full attribution, license metadata, and incremental diff support for growing datasets.", "version": "0.1", "x-build-id": "qjJYchNvXCakUinM5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datahoeven~qa-knowledge-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datahoeven-qa-knowledge-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datahoeven~qa-knowledge-extractor/runs": { "post": { "operationId": "runs-sync-datahoeven-qa-knowledge-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datahoeven~qa-knowledge-extractor/run-sync": { "post": { "operationId": "run-sync-datahoeven-qa-knowledge-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "site": { "title": "Stack Exchange site", "type": "string", "description": "The Stack Exchange network site to query. Use the site's subdomain (e.g. 'stackoverflow', 'serverfault', 'superuser', 'askubuntu'). Full list at stackexchange.com/sites.", "default": "stackoverflow" }, "tags": { "title": "Tags (AND filter)", "type": "array", "description": "Only return Q&A pairs tagged with ALL of the specified tags. Leave empty to skip tag filtering.", "default": [], "items": { "type": "string" } }, "query": { "title": "Search query", "type": "string", "description": "Free-text search term (passed as 'q' to /search/advanced). Can be combined with tags.", "default": "" }, "acceptedOnly": { "title": "Accepted answers only", "type": "boolean", "description": "When enabled, only questions with an accepted answer are returned. When disabled, questions without an accepted answer get their highest-scoring answer instead.", "default": true }, "minQuestionScore": { "title": "Minimum question score", "minimum": 0, "type": "integer", "description": "Only return Q&A pairs where the question has at least this score (upvotes minus downvotes). Useful for filtering out low-quality content.", "default": 0 }, "minAnswerScore": { "title": "Minimum answer score", "minimum": 0, "type": "integer", "description": "Only return Q&A pairs where the linked answer has at least this score. Applied after fetching; answers below this threshold are excluded.", "default": 0 }, "sort": { "title": "Sort order", "enum": [ "votes", "activity", "creation" ], "type": "string", "description": "Sort questions by votes (highest-scoring first), activity (most recently active first), or creation (newest first). Note: incremental mode always overrides this to 'activity'.", "default": "votes" }, "fromDate": { "title": "From date (ISO 8601)", "pattern": "^(\\d{4}-\\d{2}-\\d{2})?$", "type": "string", "description": "Only return Q&A pairs with activity on or after this date (ISO 8601, e.g. '2024-01-01'). Ignored when 'incremental' is enabled — the stored high-water-mark is used instead.", "default": "" }, "incremental": { "title": "Incremental mode", "type": "boolean", "description": "When enabled, each run stores a high-water-mark (the latest activity date seen). Subsequent runs only fetch Q&A pairs updated after that mark, so you only pay for new or changed content.", "default": true }, "enableChunking": { "title": "Enable RAG chunking", "type": "boolean", "description": "When enabled, the combined Q&A text is split into overlapping chunks on natural boundaries (paragraphs, code blocks). Each record gets a 'chunks' array ready to embed. Code blocks are never split mid-block.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 8000, "type": "integer", "description": "Target chunk size in characters when RAG chunking is enabled. Actual chunks may be slightly larger to avoid splitting code blocks.", "default": 1200 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Number of characters to overlap between consecutive chunks when RAG chunking is enabled. Helps preserve context across chunk boundaries.", "default": 100 }, "maxItems": { "title": "Max Q&A pairs", "minimum": 0, "type": "integer", "description": "Hard limit on the number of Q&A pairs returned per run. Set to 0 for no limit. Use this to control costs on large queries.", "default": 0 }, "apiKey": { "title": "Stack Exchange API key", "type": "string", "description": "Optional Stack Exchange application key. Without a key the daily quota is ~300 requests/IP; with a free key it rises to ~10,000/day. Register at stackapps.com." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy settings. Datacenter proxies are sufficient for the Stack Exchange API.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }