{ "openapi": "3.0.1", "info": { "title": "File-to-Dataset Ingestion & Normalization Pipeline", "description": "A mixed-format ingestion layer that converts external structured files into normalized Apify Dataset rows, not merely a profiler or dataset-to-dataset transformer.", "version": "0.0", "x-build-id": "eCK8GlzOHOhov1PHc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/quanmatrix~file-to-dataset-processing-pipeline/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-quanmatrix-file-to-dataset-processing-pipeline", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/quanmatrix~file-to-dataset-processing-pipeline/runs": { "post": { "operationId": "runs-sync-quanmatrix-file-to-dataset-processing-pipeline", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/quanmatrix~file-to-dataset-processing-pipeline/run-sync": { "post": { "operationId": "run-sync-quanmatrix-file-to-dataset-processing-pipeline", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documents" ], "properties": { "documents": { "title": "Documents", "type": "array", "description": "CSV, JSON, JSONL or XML sources. Use either content or a public HTTP(S) URL.", "default": [ { "name": "sample", "format": "json", "content": "[{\"id\":1,\"name\":\"alpha\"},{\"id\":2,\"name\":\"beta\"}]" } ] }, "maxRows": { "title": "Maximum output rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of normalized rows to write to the default Dataset across all supplied documents.", "default": 10000 }, "addProvenance": { "title": "Add provenance fields", "type": "boolean", "description": "Add _sourceIndex and _rowIndex fields so downstream workflows can trace each output row to its input source and position.", "default": true }, "previousAnalysis": { "title": "Previous Gen2 analysis", "type": "object", "description": "Optional prior Gen2 output used to calculate decision-metric deltas and regression." }, "valuePerImpactUnitUsd": { "title": "Value per impact unit (USD)", "minimum": 0, "type": "number", "description": "Optional user-supplied economic value per impact unit. Leave empty to avoid monetary estimation." }, "monthlyRuns": { "title": "Monthly run volume", "minimum": 1, "type": "integer", "description": "Optional expected monthly run count used only with valuePerImpactUnitUsd for economic impact estimation.", "default": 1 }, "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 } } } } } } } } } }