{ "openapi": "3.0.1", "info": { "title": "🏭 Industry Classifier - NAICS & SIC Code Assignment", "description": "⚡ Assign a company a NAICS and/or SIC industry code with confidence and evidence, no LLM. ✅ Walks an embedded sector-then-detail code tree, scores with TF-IDF + phrase hits, and uses negative keywords so \"SaaS for dentists\" lands in software, not dentistry.", "version": "1.0", "x-build-id": "sr9f0OYyFeaX0hU3R" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~industry-classifier/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-industry-classifier", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~industry-classifier/runs": { "post": { "operationId": "runs-sync-that_red_bird-industry-classifier", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~industry-classifier/run-sync": { "post": { "operationId": "run-sync-that_red_bird-industry-classifier", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "companies": { "title": "Companies", "type": "array", "description": "The companies to classify, as an array of flat objects with a name, description/tags, and/or a url. Combine freely with companyDatasetIds.", "default": [ { "name": "Bright Smile Dental Clinic", "description": "A friendly dental clinic offering checkups, cleanings, and orthodontist services for the whole family.", "tags": [ "dental", "healthcare" ] }, { "name": "DentaFlow", "description": "SaaS practice management software platform for dentists and dental clinics, built as a cloud app with an API.", "tags": [ "software", "saas" ] }, { "name": "Joe's Diner", "description": "A full-service, sit-down restaurant serving breakfast, lunch and dinner off a bistro menu.", "tags": [ "restaurant" ] } ] }, "companyDatasetIds": { "title": "Company dataset IDs", "type": "array", "description": "Apify dataset IDs to pull companies from, in addition to (or instead of) the inline companies list.", "items": { "type": "string" } }, "fetchSite": { "title": "Fetch each company's website", "type": "boolean", "description": "If true, fetch the page at each company's url field and append its meta description + visible text to the description before classifying. If false (default), classification uses only the text you already supplied.", "default": false }, "nameField": { "title": "Name field", "type": "string", "description": "Field holding the company's name. Carries the strongest classification signal.", "default": "name" }, "descriptionField": { "title": "Description field", "type": "string", "description": "Field holding the company's longer description text (what fetched site text, if any, is appended to).", "default": "description" }, "tagsField": { "title": "Tags field", "type": "string", "description": "Field holding curated tags/keywords (string or array). Weighted between name and description.", "default": "tags" }, "urlField": { "title": "URL field", "type": "string", "description": "Field holding the company's website URL, used only when fetchSite is true.", "default": "url" }, "idField": { "title": "Company ID field", "type": "string", "description": "Field on each company to use as its output ID. Defaults to an auto-generated C000001-style ID when omitted or blank." }, "reviewBelow": { "title": "Review below (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "If the best-matching sector, or the best-matching detail code within the accepted sector, scores below this confidence, classification stops there and the company is sent to the review queue instead of a forced guess. Expressed 0-100; 55 means 0.55.", "default": 55 }, "negativePenalty": { "title": "Negative keyword penalty (0-100)", "minimum": 0, "maximum": 100, "type": "integer", "description": "How hard a matched negative keyword (e.g. \"software\"/\"saas\" on Offices of Dentists) crushes that code's score. 0 disables negative keywords entirely; 100 zeroes the score outright the moment one is found. Expressed 0-100; 80 means the score is multiplied by 0.2.", "default": 80 }, "tfidfWeight": { "title": "TF-IDF weight", "minimum": 0, "maximum": 100, "type": "integer", "description": "Relative weight of TF-IDF-ish cosine similarity in the score. Weights are normalized against the other three weights, so only the ratio between them matters.", "default": 40 }, "overlapWeight": { "title": "Token overlap weight", "minimum": 0, "maximum": 100, "type": "integer", "description": "Relative weight of how much of a code's own vocabulary (title + keywords) is found in the company text.", "default": 25 }, "trigramWeight": { "title": "Trigram similarity weight", "minimum": 0, "maximum": 100, "type": "integer", "description": "Relative weight of character-trigram Dice similarity, which tolerates typos and word-order drift that token matching misses.", "default": 15 }, "phraseWeight": { "title": "Phrase-hit weight", "minimum": 0, "maximum": 100, "type": "integer", "description": "Relative weight of exact multi-word keyword-phrase matches (e.g. \"point of sale\", \"custom software development\") — the strongest single signal when it fires, and what is surfaced back to you as evidence.", "default": 20 }, "fetchTimeoutSecs": { "title": "Site fetch timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per company website fetch, only used when fetchSite is true.", "default": 30 }, "includeSicCrosswalk": { "title": "Include SIC crosswalk", "type": "boolean", "description": "Include the approximate crosswalked SIC code(s) alongside the NAICS detail code on each classified row.", "default": true }, "includeReviewItems": { "title": "Include review-queue items", "type": "boolean", "description": "Emit rows for companies that could not be confidently classified, with the reason and the top candidate sectors/codes that were considered.", "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 } } } } } } } } } }