{ "openapi": "3.0.1", "info": { "title": "🗂️ Product Taxonomy Classifier - Deep Category Trees", "description": "⚡ Classify thousands of products into a deep, multi-level category tree with no LLM. ✅ Walks the taxonomy level by level so every path is internally consistent, scores with TF-IDF-ish cosine + token overlap + trigram similarity, and routes low-confidence items to a review queue instead of.", "version": "1.0", "x-build-id": "dYtkpVQigPQJfTYW4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~product-taxonomy-classifier/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-product-taxonomy-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~product-taxonomy-classifier/runs": { "post": { "operationId": "runs-sync-that_red_bird-product-taxonomy-classifier", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~product-taxonomy-classifier/run-sync": { "post": { "operationId": "run-sync-that_red_bird-product-taxonomy-classifier", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "taxonomy" ], "properties": { "products": { "title": "Products", "type": "array", "description": "The products to classify, as an array of flat objects with a title, description and/or tags. Combine freely with productDatasetIds.", "default": [ { "title": "Sony WH-1000XM5 Wireless Noise Cancelling Headphones", "description": "Over-ear Bluetooth headphones with active noise cancellation", "tags": [ "audio", "wireless", "bluetooth" ] }, { "title": "KitchenAid 5-Quart Stand Mixer", "description": "Countertop mixer for baking with dough hook and whisk attachments", "tags": [ "kitchen", "baking" ] }, { "title": "Nike Air Zoom Pegasus Running Shoes", "description": "Men's lightweight running shoes with breathable mesh upper", "tags": [ "footwear", "running" ] } ] }, "productDatasetIds": { "title": "Product dataset IDs", "type": "array", "description": "Apify dataset IDs to pull products from, in addition to (or instead of) the inline products list.", "items": { "type": "string" } }, "taxonomy": { "title": "Category taxonomy", "type": "array", "description": "Your category tree. Either an array of path strings (\"Electronics > Audio > Headphones\") or a nested tree of {\"name\":\"Electronics\",\"keywords\":[...],\"children\":[...]} objects. Shapes can be mixed. Classification is always constrained level by level to the accepted parent's own children.", "default": [ "Electronics > Audio > Headphones", "Electronics > Audio > Speakers", "Home & Kitchen > Small Appliances > Mixers", "Home & Kitchen > Small Appliances > Blenders", "Clothing & Shoes > Footwear > Running Shoes", "Clothing & Shoes > Footwear > Boots" ] }, "keywordHints": { "title": "Keyword hints per category", "type": "object", "description": "Optional extra keywords to boost specific categories, keyed by full category path or by bare category name, e.g. {\"Electronics > Audio > Headphones\": [\"earbuds\", \"anc\", \"over-ear\"]}. Merged with each category's own name for scoring." }, "idField": { "title": "Product ID field", "type": "string", "description": "Field on each product to use as its output ID. Defaults to an auto-generated P000001-style ID when omitted or blank." }, "titleField": { "title": "Title field", "type": "string", "description": "Field holding the product's title/name. Carries the strongest classification signal.", "default": "title" }, "descriptionField": { "title": "Description field", "type": "string", "description": "Field holding the product's longer description text.", "default": "description" }, "tagsField": { "title": "Tags field", "type": "string", "description": "Field holding curated tags/attributes (string or array). Weighted between title and description.", "default": "tags" }, "reviewBelow": { "title": "Review below (0-100)", "minimum": 1, "maximum": 100, "type": "integer", "description": "If the best-matching category at any level scores below this confidence, the product stops there and is sent to the review queue instead of being forced into a low-confidence guess. Expressed 0-100; 55 means 0.55.", "default": 55 }, "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 overlapWeight and trigramWeight, so only the ratio between them matters.", "default": 50 }, "overlapWeight": { "title": "Token overlap weight", "minimum": 0, "maximum": 100, "type": "integer", "description": "Relative weight of how much of a category's own vocabulary (name + keywords + hints) is found in the product text.", "default": 30 }, "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": 20 }, "includeCategoryCounts": { "title": "Include per-category counts", "type": "boolean", "description": "Emit one row per used category with how many products landed there.", "default": true }, "includeReviewItems": { "title": "Include review-queue items", "type": "boolean", "description": "Emit rows for products that could not be confidently classified, with the reason and the top candidate categories 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 } } } } } } } } } }