Fuzzy Search Dataset Actor
Pricing
from $0.001 / actor start
You can access the Fuzzy Search Dataset Actor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "6Me8viIBc2t2TyVjk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dtrungtin~fuzzy-search-dataset-actor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dtrungtin-fuzzy-search-dataset-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/dtrungtin~fuzzy-search-dataset-actor/runs": { "post": { "operationId": "runs-sync-dtrungtin-fuzzy-search-dataset-actor", "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/dtrungtin~fuzzy-search-dataset-actor/run-sync": { "post": { "operationId": "run-sync-dtrungtin-fuzzy-search-dataset-actor", "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": [ "datasetId", "query" ], "properties": { "datasetId": { "title": "Dataset ID", "type": "string", "description": "The Apify dataset ID that contains the records you want to search. You can find this in the dataset URL or in Apify Console. Example: 'abc123DEF456'." }, "query": { "title": "Search Query", "type": "string", "description": "The text users want to search for. Fuzzy search allows typos and partial matches. Example: searching for 'iphon pro' can still match 'iPhone 15 Pro Max'." }, "fields": { "title": "Search Fields", "type": "array", "description": "List of dataset fields to search in. You can search multiple fields at the same time. Examples: 'title', 'description', 'brand', 'category', or nested fields like 'product.name'.", "items": { "type": "string" }, "default": [ "title" ] }, "limit": { "title": "Maximum Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of search results returned. Lower values improve performance. Recommended: 10 to 100.", "default": 20 }, "threshold": { "title": "Fuzzy Match Strictness", "minimum": 0, "maximum": 1, "type": "number", "description": "Controls how strict the fuzzy search is. Lower values require more accurate matches. Higher values allow more typos and loose matching. Recommended values: 0.2 = strict, 0.35 = balanced, 0.6 = very loose.", "default": 0.35 }, "ignoreLocation": { "title": "Ignore Word Position", "type": "boolean", "description": "When enabled, matches can appear anywhere inside the text. Example: searching 'pro' can match both 'iPhone Pro' and 'Professional Camera'. Recommended: enabled.", "default": true }, "minMatchCharLength": { "title": "Minimum Match Length", "minimum": 1, "type": "integer", "description": "Minimum number of characters required before fuzzy considers a match. Helps reduce noisy results for very short queries. Recommended: 2 or 3.", "default": 2 }, "includeScore": { "title": "Include Relevance Score", "type": "boolean", "description": "Adds a relevance score to each result. Lower scores mean better matches. Useful for debugging, sorting, or displaying search confidence.", "default": true }, "includeMatches": { "title": "Include Match Details", "type": "boolean", "description": "Returns detailed information about which text fragments matched the query. Useful for highlighting matched keywords in a frontend application.", "default": false }, "extendedSearch": { "title": "Enable Advanced Search Syntax", "type": "boolean", "description": "Enables Fuzzy advanced query syntax. Examples: '^apple' = starts with apple, '!samsung' = exclude samsung, '=iphone' = exact match. Recommended for advanced users only.", "default": false }, "weights": { "title": "Field Importance Weights", "type": "object", "description": "Optional JSON object that controls which fields are more important during ranking. Higher weight means higher priority in search results. Example: {\"title\": 0.7, \"description\": 0.2, \"brand\": 0.1}" } } }, "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 Fuzzy Search Dataset Actor 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: