{ "openapi": "3.0.1", "info": { "title": "Dataset Deduplication & Merge Planner", "description": "Find duplicate groups in Apify datasets, quantify duplicate risk, and generate deterministic merge recommendations without mutating the source. Gen2 adds baseline comparison, economic impact, confidence, and explicit automation decisions. Returns structured, machine-readable results.", "version": "0.0", "x-build-id": "D3k5mmdxEwvTKd0vk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/quanmatrix~dataset-deduplication-merge-planner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-quanmatrix-dataset-deduplication-merge-planner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/quanmatrix~dataset-deduplication-merge-planner/runs": { "post": { "operationId": "runs-sync-quanmatrix-dataset-deduplication-merge-planner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/quanmatrix~dataset-deduplication-merge-planner/run-sync": { "post": { "operationId": "run-sync-quanmatrix-dataset-deduplication-merge-planner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetId": { "title": "Dataset", "type": "string", "description": "Optional Apify dataset selected with least-privilege READ access." }, "items": { "title": "Inline items", "type": "array", "description": "Optional inline JSON objects for tests or small manual runs.", "items": { "type": "object" } }, "maxItems": { "title": "Maximum items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum dataset rows to evaluate.", "default": 10000 }, "keyFields": { "title": "Key fields", "type": "array", "description": "Composite fields that define duplicate identity.", "items": { "type": "string" }, "default": [ "id" ] }, "mergeStrategy": { "title": "Merge strategy", "type": "string", "description": "first, last, or non_null.", "default": "first" }, "previousAnalysis": { "title": "Previous dedup analysis", "type": "object", "description": "Optional prior Actor output for duplicate-rate trend comparison.", "default": {} }, "costPerDuplicateUsd": { "title": "Cost per duplicate (USD)", "minimum": 0, "type": "number", "description": "Optional estimated cost of carrying or remediating one excess duplicate.", "default": 0 }, "monthlyRuns": { "title": "Monthly runs", "minimum": 1, "type": "integer", "description": "Projected monthly equivalent runs for annualized savings estimates.", "default": 1 }, "warnDuplicateRatePct": { "title": "Warn duplicate rate (%)", "minimum": 0, "maximum": 100, "type": "number", "description": "Warn duplicate rate (%). Configure this optional control for the current audit when needed.", "default": 1 }, "blockDuplicateRatePct": { "title": "Block duplicate rate (%)", "minimum": 0, "maximum": 100, "type": "number", "description": "Block duplicate rate (%). Configure this optional control for the current audit when needed.", "default": 10 }, "mcpConnectors": { "title": "MCP output connectors", "type": "array", "description": "Optional MCP connectors authorized in your Apify account. Use them to send or write this Actor result to tools such as Slack, Notion, GitHub, Sentry, Supabase, or another compatible MCP service." }, "mcpToolName": { "title": "MCP tool name", "type": "string", "description": "Optional exact MCP tool name. Leave blank to let the selected MCP action preset discover a compatible tool automatically.", "default": "" }, "mcpToolArguments": { "title": "MCP tool arguments", "type": "object", "description": "JSON object passed to the selected MCP tool. String values may use {{actor_title}}, {{result_summary}}, or {{result_json}} placeholders.", "default": {} }, "mcpFailOnError": { "title": "Fail run if MCP delivery fails", "type": "boolean", "description": "When enabled, an MCP delivery error fails the Actor run. Disabled by default so data extraction and intelligence results remain available even if the external destination is unavailable.", "default": false }, "mcpActionPreset": { "title": "MCP action preset", "enum": [ "AUTO_SAFE_WRITE", "SLACK_MESSAGE", "GITHUB_ISSUE", "NOTION_PAGE", "DATABASE_WRITE", "CUSTOM" ], "type": "string", "description": "Choose a safe action pattern. AUTO_SAFE_WRITE discovers a compatible non-destructive write tool automatically; use a specific preset for Slack, GitHub, Notion, or database delivery.", "default": "AUTO_SAFE_WRITE" } } }, "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 } } } } } } } } } }