{ "openapi": "3.0.1", "info": { "title": "Rag Evaluation Dataset Generator", "description": "Generate citation-grounded RAG evaluation datasets from websites, sitemaps, PDFs, text, and inline documents. Create validated factual, multi-hop, unanswerable, and adversarial test cases with exact evidence quotes, grading hints, and JSONL, CSV, or RAGAS-ready exports.", "version": "0.0", "x-build-id": "7fddWaaTbFLHWcBvN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/systra_ai~systra-ai-rag-evaluation-dataset-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-systra_ai-systra-ai-rag-evaluation-dataset-generator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/systra_ai~systra-ai-rag-evaluation-dataset-generator/runs": { "post": { "operationId": "runs-sync-systra_ai-systra-ai-rag-evaluation-dataset-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/systra_ai~systra-ai-rag-evaluation-dataset-generator/run-sync": { "post": { "operationId": "run-sync-systra_ai-systra-ai-rag-evaluation-dataset-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sourceUrls": { "title": "Source URLs", "type": "array", "description": "Public webpages, sitemap XML files, text/JSON documents, or PDFs to use as ground truth.", "default": [], "items": { "type": "string" } }, "inlineDocuments": { "title": "Inline documents", "type": "array", "description": "Optional documents supplied directly as JSON objects with title, content, and optional sourceUrl.", "items": { "type": "object", "additionalProperties": false, "properties": { "title": { "title": "Document title", "description": "Human-readable source title.", "type": "string", "editor": "textfield", "minLength": 1 }, "content": { "title": "Document content", "description": "Plain-text source content used as ground truth.", "type": "string", "editor": "textarea", "minLength": 1 }, "sourceUrl": { "title": "Canonical source URL", "description": "Optional public URL recorded with citations.", "type": "string", "editor": "textfield" } }, "required": [ "title", "content" ] }, "default": [] }, "crawlMode": { "title": "Crawl mode", "enum": [ "single-page", "same-domain", "sitemap" ], "type": "string", "description": "Process only supplied pages, follow same-domain links, or expand sitemap URLs.", "default": "single-page" }, "browserRendering": { "title": "JavaScript rendering", "enum": [ "auto", "never", "always" ], "type": "string", "description": "Automatically render thin HTML pages in Chromium, never use a browser, or render every HTML page.", "default": "auto" }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 500, "type": "integer", "description": "Hard cap on fetched source documents.", "default": 30 }, "maxDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 8, "type": "integer", "description": "Used only for same-domain crawling.", "default": 2 }, "testCaseCount": { "title": "Target evaluation cases", "minimum": 1, "maximum": 1000, "type": "integer", "description": "The Actor may return fewer cases when generated evidence fails grounding or duplicate checks.", "default": 30 }, "questionTypes": { "title": "Question types", "type": "array", "description": "Mix of evaluation cases to generate.", "items": { "type": "string", "enum": [ "factual", "paraphrase", "procedural", "policy", "numerical", "temporal", "multi_hop", "unanswerable", "adversarial" ] }, "default": [ "factual", "paraphrase", "procedural", "multi_hop", "unanswerable", "adversarial" ] }, "language": { "title": "Question language", "type": "string", "description": "Language name or BCP-47 code for questions and reference answers.", "default": "English" }, "model": { "title": "OpenAI model", "type": "string", "description": "A model that supports Structured Outputs.", "default": "gpt-5.6-luna" }, "openAIApiKey": { "title": "OpenAI API key override", "type": "string", "description": "Optional. When omitted, the Actor uses its OPENAI_API_KEY environment variable." }, "maxChunkCharacters": { "title": "Maximum chunk characters", "minimum": 800, "maximum": 15000, "type": "integer", "description": "Approximate maximum source characters provided per evidence chunk.", "default": 5000 }, "chunkOverlapCharacters": { "title": "Chunk overlap characters", "minimum": 0, "maximum": 3000, "type": "integer", "description": "Context repeated between adjacent chunks.", "default": 400 }, "generationBatchSize": { "title": "Cases per model call", "minimum": 1, "maximum": 15, "type": "integer", "description": "Smaller batches improve grounding; larger batches reduce model calls.", "default": 6 }, "maxSourceBytes": { "title": "Maximum bytes per source", "minimum": 100000, "maximum": 50000000, "type": "integer", "description": "Safety limit for each downloaded document.", "default": 10000000 } } }, "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 } } } } } } } } } }