{ "openapi": "3.0.1", "info": { "title": "Company Name Normalizer & Deduplicator for CRM", "description": "Normalize messy company names and group duplicates in your CRM, leads or vendor lists. Strips Inc, LLC, Ltd and GmbH, splits d/b/a names, fixes caps, punctuation and common aliases (IBM, P&G), and returns a clean name, canonical key, legal form and duplicate group ID per row.", "version": "0.1", "x-build-id": "ApWFYX4j46zroWAiW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ultimatemc~company-name-canonicalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ultimatemc-company-name-canonicalizer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ultimatemc~company-name-canonicalizer/runs": { "post": { "operationId": "runs-sync-ultimatemc-company-name-canonicalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ultimatemc~company-name-canonicalizer/run-sync": { "post": { "operationId": "run-sync-ultimatemc-company-name-canonicalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "names": { "title": "Company names", "type": "array", "description": "One company name per line, as messy as you have them. The prefill has ten examples; replace them with your own list.", "items": { "type": "string" } }, "records": { "title": "Records (optional)", "type": "array", "description": "Objects with an \"id\" and a company name field (companyName, company, employer, organization, businessName, vendor, name ... detected automatically, or set Name field). The whole record is copied to the output under \"record\"." }, "datasetId": { "title": "Dataset ID (optional)", "type": "string", "description": "Apify dataset to clean, for example the output of a leads, jobs or Google Maps scraper. The company name field is detected automatically; override with Name field." }, "nameField": { "title": "Name field (optional)", "type": "string", "description": "Field holding the company name in records or dataset items, e.g. \"companyName\" or \"employer\". Leave empty to detect it." }, "groupDuplicates": { "title": "Group duplicates", "type": "boolean", "description": "Give names that normalize to the same company the same groupId (exact canonical key, known aliases, and spacing or plural variants like 'HospiceMD' / 'Hospice MD').", "default": true }, "fuzzyTypos": { "title": "Also group typos (fuzzy)", "type": "boolean", "description": "Also group names that differ by one or two letters ('Deloite' / 'Deloitte'). Catches typos, but can join different companies with similar names ('Computek' / 'Computer'), so review rows where matchMethod starts with 'fuzzy'. Off by default.", "default": false }, "fuzzyThreshold": { "title": "Fuzzy similarity threshold", "minimum": 0.8, "maximum": 1, "type": "number", "description": "Minimum similarity (0-1) for typo grouping. Higher is stricter.", "default": 0.92 }, "expandAbbreviations": { "title": "Expand abbreviations", "type": "boolean", "description": "In the canonical key, expand Intl, Mfg, Svcs, Assoc, Bros, Natl, Mgmt, St./Mt. at the start and similar, so 'Acme Intl Mfg' matches 'Acme International Manufacturing'. The cleaned display name keeps your wording.", "default": true }, "stripStoreNumbers": { "title": "Remove store / location numbers", "type": "boolean", "description": "Remove trailing '#1234', 'Store 55' or 'Location 3' so branches group with the brand.", "default": true }, "stripCountryQualifiers": { "title": "Remove country qualifiers", "type": "boolean", "description": "Remove a trailing US / USA / NA / North America / UK / Canada / India qualifier from the key ('Deel US LLC' = 'Deel Inc'), except in names like 'Bank of America' or 'BMW of North America'.", "default": true }, "aliases": { "title": "Your aliases (optional)", "type": "object", "description": "Extra alias -> canonical name pairs, e.g. {\"Big Blue\": \"International Business Machines\", \"MSFT\": \"Microsoft\"}. Added to the built-in list of common aliases." }, "outputMode": { "title": "Output", "enum": [ "allRows", "onePerGroup" ], "type": "string", "description": "All rows (one result per input name, with its group) or one row per group (deduplicated list; you pay only for those rows).", "default": "allRows" }, "includeOriginal": { "title": "Copy original record", "type": "boolean", "description": "For records and dataset items, copy the original item into the output field \"record\".", "default": true }, "maxItems": { "title": "Max names", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Maximum number of names to process in this run (grouping happens across all of them).", "default": 10000 } } }, "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 } } } } } } } } } }