{ "openapi": "3.0.1", "info": { "title": "Actor Dataset Provenance Enricher", "description": "Enrich Apify dataset rows with deterministic field-level provenance, source identity, canonical hashes, lineage, rights indicators, and artifact manifests.", "version": "0.1", "x-build-id": "6BDhlmbCIWvFx0FqQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/flintglade~actor-dataset-provenance-enricher/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-flintglade-actor-dataset-provenance-enricher", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/flintglade~actor-dataset-provenance-enricher/runs": { "post": { "operationId": "runs-sync-flintglade-actor-dataset-provenance-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/flintglade~actor-dataset-provenance-enricher/run-sync": { "post": { "operationId": "run-sync-flintglade-actor-dataset-provenance-enricher", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "includeOriginal" ], "properties": { "inputSchemaVersion": { "title": "Input schema version", "minimum": 1, "maximum": 1, "type": "integer", "description": "Versioned runtime input contract.", "default": 1 }, "datasetIds": { "title": "Authorized datasets", "minItems": 1, "maxItems": 5, "uniqueItems": true, "type": "array", "description": "Select 1-5 Apify datasets to read. The Actor does not discover or mutate datasets." }, "inlineItems": { "title": "Inline JSON rows", "minItems": 1, "maxItems": 100, "type": "array", "description": "Use 1-100 small object rows for demos and health checks instead of datasetIds.", "items": { "type": "object" } }, "profile": { "title": "Upstream profile", "enum": [ "auto", "AP-003", "AP-014", "AP-021", "AP-027", "AP-002", "generic" ], "type": "string", "description": "Auto uses only explicit supported actor/schema markers. Generic requires fieldMappings.", "default": "auto" }, "fieldMappings": { "title": "Generic JSON Pointer mappings", "type": "object", "description": "Explicit RFC 6901 pointers for an unknown dataset. At least one mapping is required when generic is selected.", "properties": { "actorId": { "title": "Actor ID pointer", "description": "Pointer to an explicit source Actor ID.", "type": "string", "pattern": "^/", "maxLength": 500 }, "runId": { "title": "Run ID pointer", "description": "Pointer to an upstream run ID.", "type": "string", "pattern": "^/", "maxLength": 500 }, "datasetId": { "title": "Dataset ID pointer", "description": "Pointer to an upstream dataset ID.", "type": "string", "pattern": "^/", "maxLength": 500 }, "sourceUrl": { "title": "Source URL pointer", "description": "Pointer to a recorded source URL.", "type": "string", "pattern": "^/", "maxLength": 500 }, "sourceIdentifier": { "title": "Source identifier pointer", "description": "Pointer to a source identifier.", "type": "string", "pattern": "^/", "maxLength": 500 }, "observedAt": { "title": "Observed time pointer", "description": "Pointer to an observation timestamp.", "type": "string", "pattern": "^/", "maxLength": 500 }, "retrievedAt": { "title": "Retrieved time pointer", "description": "Pointer to a retrieval timestamp.", "type": "string", "pattern": "^/", "maxLength": 500 }, "rightsIndicators": { "title": "Rights indicators pointer", "description": "Pointer to recorded rights indicators.", "type": "string", "pattern": "^/", "maxLength": 500 }, "upstreamStatus": { "title": "Upstream status pointer", "description": "Pointer to the upstream result status.", "type": "string", "pattern": "^/", "maxLength": 500 }, "lineageParents": { "title": "Lineage parents pointer", "description": "Pointer to recorded lineage parents.", "type": "string", "pattern": "^/", "maxLength": 500 }, "entityKey": { "title": "Entity key pointer", "description": "Pointer to the primary entity key.", "type": "string", "pattern": "^/", "maxLength": 500 } }, "additionalProperties": false }, "includeOriginal": { "title": "Preserve original row", "type": "boolean", "description": "Required true in version 0.1. The original JSON data model is retained unchanged; runtime validation rejects false.", "default": true }, "outputMode": { "title": "Output mode", "enum": [ "default_dataset", "default_and_named" ], "type": "string", "description": "Write to the default dataset only, or also mirror successfully written enriched rows to a named dataset.", "default": "default_dataset" }, "outputDatasetName": { "title": "Named output dataset", "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,62}$", "minLength": 1, "maxLength": 63, "type": "string", "description": "Safe Apify dataset name required only for default_and_named." }, "maxRows": { "title": "Maximum rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Global row-read ceiling across selected inputs.", "default": 10000 }, "startOffset": { "title": "Resume offset", "minimum": 0, "maximum": 2147483647, "type": "integer", "description": "Zero-based starting offset. For multiple datasets, the same resume offset is applied to each selected dataset.", "default": 0 }, "concurrency": { "title": "Processing concurrency", "minimum": 1, "maximum": 1, "type": "integer", "description": "Version 0.1 is deliberately local and streaming.", "default": 1 } } }, "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 } } } } } } } } } }