{ "openapi": "3.0.1", "info": { "title": "🧹 Contact & Company Deduplicator - Clean Your CRM List", "description": "🧹 Upload one messy contact or company list and get back a clean, de-duplicated list ready to re-import into your CRM. ✅ Fuzzy name/email/phone/company matching, sensible zero-config defaults, plus a duplicates-to-review list and a full merge audit log explaining what was merged and why.", "version": "1.0", "x-build-id": "YwqoS2dASAFv19yff" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~contact-deduplicator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-contact-deduplicator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~contact-deduplicator/runs": { "post": { "operationId": "runs-sync-that_red_bird-contact-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~contact-deduplicator/run-sync": { "post": { "operationId": "run-sync-that_red_bird-contact-deduplicator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "contacts": { "title": "Contacts", "type": "array", "description": "Your messy contact or company list, as an array of flat row objects (e.g. exported from a CRM as JSON). Combine freely with datasetId.", "default": [ { "name": "Jennifer Adams", "company": "Acme Corporation", "email": "jen@acme.com", "phone": "415-555-0100" }, { "name": "Jen Adams", "company": "Acme Corp.", "email": "jen@acme.com", "phone": "" }, { "name": "J. Adams", "company": "ACME, Inc.", "email": "", "phone": "(415) 555 0100" }, { "name": "Michael Chen", "company": "Globex Ltd", "email": "mchen@globex.io", "phone": "212-555-0199" }, { "name": "Mike Chen", "company": "Globex Limited", "email": "mchen@globex.io", "phone": "" } ] }, "datasetId": { "title": "Source dataset ID", "type": "string", "description": "Optional Apify dataset ID to pull additional rows from (e.g. the output of a CRM export actor). Rows are appended to \"contacts\" before deduplication." }, "fields": { "title": "Fields to compare (advanced)", "type": "array", "description": "Leave empty to auto-detect name/email/phone/company/address columns from your data. For manual control pass objects: {\"field\":\"email\",\"type\":\"email\",\"weight\":5}. Types: email, phone, person, company, address, numeric, text, exact." }, "matchThreshold": { "title": "Match threshold (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pairs scoring at or above this are merged automatically. Higher = safer (fewer wrong merges) but misses more real duplicates. Expressed 0-100; 85 means 0.85.", "default": 85 }, "reviewThreshold": { "title": "Review threshold (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pairs scoring between this and the match threshold are reported for you to review instead of being merged automatically. Silently fusing two different people is worse than missing a duplicate.", "default": 70 }, "survivorshipStrategy": { "title": "Which value wins on conflict", "enum": [ "mostComplete", "longest", "mostCommon", "first" ], "type": "string", "description": "When merged contacts disagree on a field (e.g. two different phone numbers), this decides which value survives into the clean record.", "default": "mostComplete" }, "maxBlockSize": { "title": "Max block size (advanced)", "minimum": 10, "maximum": 20000, "type": "integer", "description": "Groups of records sharing a generic key (e.g. a common email domain) larger than this are skipped for comparison, to avoid a slowdown on huge lists.", "default": 500 }, "includeDuplicatesOnly": { "title": "Include a duplicates-to-review list", "type": "boolean", "description": "Emit the merged duplicate groups plus any ambiguous pairs that scored too low to auto-merge, so you can sanity-check the run.", "default": true }, "includeMergeLog": { "title": "Include a merge audit log", "type": "boolean", "description": "Emit one row per merged group explaining what was merged, which fields agreed, which fields conflicted, and which value was kept.", "default": true } } }, "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 } } } } } } } } } }