Pricing
$0.10 / 1,000 results
A powerful AI Apify Actor that intelligently matches products between two datasets using advanced machine learning algorithms and configurable similarity scoring. Perfect for e-commerce catalog matching, product deduplication, and inventory reconciliation.
0.0 (0)
Pricing
$0.10 / 1,000 results
0
2
2
Last modified
23 days ago
You can access the Advanced Product Matcher Pro programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "n4fsdaq29FfegfcF4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datawhisperers~advanced-product-matcher-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datawhisperers-advanced-product-matcher-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/datawhisperers~advanced-product-matcher-pro/runs": { "post": { "operationId": "runs-sync-datawhisperers-advanced-product-matcher-pro", "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/datawhisperers~advanced-product-matcher-pro/run-sync": { "post": { "operationId": "run-sync-datawhisperers-advanced-product-matcher-pro", "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": [ "dataFormat", "dataSource", "dataset1", "dataset1PrimaryKey", "dataset2", "dataset2PrimaryKey", "threshold", "attributes" ], "properties": { "dataFormat": { "title": "Data Format", "enum": [ "csv", "json" ], "type": "string", "description": "Choose between CSV or JSON format", "default": "json" }, "csvSeparator": { "title": "CSV Separator", "type": "string", "description": "CSV separator (only applies to CSV Data Format)", "default": "," }, "dataSource": { "title": "Data Source", "enum": [ "keyvaluestore", "datasets" ], "type": "string", "description": "Choose between KeyValueStore files or Datasets", "default": "datasets" }, "keyValuestoreNameOrId": { "title": "Name or ID of KeyValueStore", "type": "string", "description": "If sourcing data from a KeyValueStore, enter the name or Id of the store" }, "dataset1": { "title": "Dataset 1 Key/Dataset 1 ID", "type": "string", "description": "Data Soure = KeyValueStore > KV store key name where first dataset is stored. For Data Source = Dataset > Apify dataset ID containing data" }, "dataset1Name": { "title": "Name of dataset 1", "type": "string", "description": "Friendly name for dataset 1 - used as a prefix to fields output from dataset 1 for easier identification in the matched results", "default": "Dataset1" }, "dataset1PrimaryKey": { "title": "Name of primary row identifier in dataset 1", "type": "string", "description": "Must match the actual data record, is used to form a match with dataset 2", "default": "ProductId" }, "dataset2": { "title": "Dataset 2 Key/Dataset 2 ID", "type": "string", "description": "Data Soure = KeyValueStore > KV store key name where second dataset is stored. For Data Source = Dataset > Apify dataset ID containing data" }, "dataset2Name": { "title": "Name of dataset 2", "type": "string", "description": "Friendly name for dataset 2 - used as a prefix to fields output from dataset 2 for easier identification in the matched results", "default": "Dataset2" }, "dataset2PrimaryKey": { "title": "Name of primary row identifier in dataset 2", "type": "string", "description": "Must match the actual data record, is used to form a match with dataset 1", "default": "ProductId" }, "attributes": { "title": "Matching Attributes", "type": "array", "description": "Configure attributes for matching with simple or advanced cleaning options", "default": [ { "name": "title", "weight": 1, "useForMatching": true, "wordsToRemove": [ "new", "used", "refurbished" ], "wordReplacements": { "&": "and", "w/": "with" } }, { "name": "brand", "weight": 0.8, "useForMatching": true, "wordsToRemove": [ "inc", "llc", "ltd", "corp" ], "wordReplacements": { "apple": "apple inc", "samsung": "samsung electronics" } }, { "name": "description", "jsonPath": "product.description", "weight": 0.6, "useForMatching": true, "wordsToRemove": [ "brand new", "excellent condition", "fast shipping" ], "regex": "\\b(color|colour):\\s*\\w+\\b", "normalizationRegex": "[^a-zA-Z0-9\\s]", "normalizationReplacement": "" }, { "name": "model", "weight": 0.9, "useForMatching": true, "wordsToRemove": [ "model", "version" ], "wordReplacements": { "v1": "version 1", "v2": "version 2" } }, { "name": "price", "weight": 1, "useForMatching": false, "regex": "\\D" } ] }, "threshold": { "title": "Matching Threshold", "type": "string", "description": "Minimum similarity score for matches (0.0 to 1.0)", "default": "0.5" }, "maxMatches": { "title": "Max Matches per Item", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of matches to return for each item", "default": 2 }, "groupByAttribute": { "title": "Group By Attribute", "type": "string", "description": "Attribute to group by for more efficient matching (optional)", "default": "" }, "language": { "title": "Language/Model", "enum": [ "en", "multilingual", "es", "fr", "de", "it", "pt", "nl" ], "type": "string", "description": "Language of your data to select appropriate embedding model", "default": "en" }, "includeOriginalValues": { "title": "Include Original Values", "type": "boolean", "description": "Include all original attribute values in output", "default": true }, "dataset1OutputFields": { "title": "Output Fields Dataset 1", "type": "array", "description": "If not including all fields in the output, specifiy individual fields from dataset 1 data to include in output", "default": [] }, "dataset2OutputFields": { "title": "Output Fields Dataset 2", "type": "array", "description": "If not including all fields in the output, specifiy individual fields from dataset 2 data to include in output", "default": [] } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Advanced Product Matcher Pro from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: