{ "openapi": "3.0.1", "info": { "title": "Dataset Deduplicate & Merge (Fuzzy)", "description": "Merge multiple Apify datasets or CSV/JSON/XLSX files and remove duplicates with normalised or fuzzy matching. Only-new mode returns just items you have not seen before.", "version": "0.1", "x-build-id": "ziuAVXbzTvVfIrlSD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/larchrow~dataset-dedupe-merge-fuzzy/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-larchrow-dataset-dedupe-merge-fuzzy", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/larchrow~dataset-dedupe-merge-fuzzy/runs": { "post": { "operationId": "runs-sync-larchrow-dataset-dedupe-merge-fuzzy", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/larchrow~dataset-dedupe-merge-fuzzy/run-sync": { "post": { "operationId": "run-sync-larchrow-dataset-dedupe-merge-fuzzy", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetIds": { "title": "Dataset IDs", "type": "array", "description": "Apify datasets to merge (IDs or names). Read in order; earlier datasets win with mergeStrategy=first." }, "sourceUrls": { "title": "JSON/CSV URLs", "type": "array", "description": "Optional public JSON, JSONL, CSV or XLSX files to merge in.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "items": { "title": "Inline items", "type": "array", "description": "Optional items passed directly." }, "fields": { "title": "Dedupe key fields", "type": "array", "description": "Fields forming the key, dot paths allowed. Optional normaliser after a colon: exact, text, url, phone, email, company. Example: website:url or name:company, city:text. Empty = whole item.", "items": { "type": "string" } }, "normalize": { "title": "Default normaliser", "enum": [ "exact", "text", "url", "phone", "email", "company" ], "type": "string", "description": "Default normaliser.", "default": "text" }, "mergeStrategy": { "title": "Merge strategy", "enum": [ "first", "last", "most-complete", "fill", "fill-and-combine" ], "type": "string", "description": "first/last keep one item; most-complete keeps the duplicate with the most filled fields; fill fills empty fields from duplicates; fill-and-combine also unions list fields.", "default": "first" }, "fuzzyField": { "title": "Fuzzy field (optional)", "type": "string", "description": "e.g. name:company – near-identical values (typos, punctuation) are merged. Different words such as other city names are never merged." }, "fuzzyThreshold": { "title": "Fuzzy threshold", "type": "string", "description": "Fuzzy threshold.", "default": "0.92" }, "onlyNewAcrossRuns": { "title": "Only new items across runs", "type": "boolean", "description": "Remembers keys in a named key-value store and outputs only items never seen in earlier runs (monitoring).", "default": false }, "stateKey": { "title": "State store name", "type": "string", "description": "State store name.", "default": "dedupe-merge-state" }, "skipEmptyKeys": { "title": "Items with empty key are kept unmerged", "type": "boolean", "description": "Items with empty key are kept unmerged.", "default": true }, "keepEmptyKeyItems": { "title": "Keep items with empty key", "type": "boolean", "description": "Keep items with empty key.", "default": true }, "addSourceField": { "title": "Add __source field", "type": "boolean", "description": "Add __source field.", "default": true }, "addDupeCount": { "title": "Add __dupes count", "type": "boolean", "description": "Add __dupes count.", "default": true }, "renameFields": { "title": "Rename fields", "type": "object", "description": "e.g. {\"Firma\":\"company\"}. Applied before dedupe, so key fields use the new names.", "default": {} }, "fieldsToKeep": { "title": "Keep only these fields", "type": "array", "description": "Output only these fields (after renaming). Empty = all.", "items": { "type": "string" } }, "fieldsToDrop": { "title": "Drop fields", "type": "array", "description": "Drop fields.", "items": { "type": "string" } }, "requiredFields": { "title": "Required fields", "type": "array", "description": "Items where any of these is empty are dropped.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }