Corpus Coverage Gate
Under maintenancePricing
from $0.10 / conclusive audit
Go to Apify Store
Corpus Coverage Gate
Under maintenanceCheck a website text export against expected URLs or an earlier crawl before updating a RAG corpus.
Corpus Coverage Gate
Under maintenancePricing
from $0.10 / conclusive audit
Check a website text export against expected URLs or an earlier crawl before updating a RAG corpus.
You can access the Corpus Coverage Gate programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "ckRfzfvDBMVXW5sqw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/owlects~corpus-coverage-gate/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-owlects-corpus-coverage-gate", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/owlects~corpus-coverage-gate/runs": { "post": { "operationId": "runs-sync-owlects-corpus-coverage-gate", "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/owlects~corpus-coverage-gate/run-sync": { "post": { "operationId": "run-sync-owlects-corpus-coverage-gate", "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": [ "current" ], "properties": { "current": { "title": "Current source", "type": "object", "description": "Use {runId: ...} for a completed Apify run, or {items: [...], complete: true} for an attested export. Optional datasetId must match the run." }, "baseline": { "title": "Baseline source", "type": "object", "description": "Previous accepted source, same format as current." }, "expectedUrls": { "title": "Expected URLs", "type": "array", "description": "Optional reference manifest. Without it coverage is relative to baseline URLs.", "items": { "type": "string" } }, "urlField": { "title": "URL field", "enum": [ "url", "crawl.loadedUrl" ], "type": "string", "description": "Field containing the page URL.", "default": "url" }, "textField": { "title": "Content field", "enum": [ "text", "markdown" ], "type": "string", "description": "Field containing the main text to inspect.", "default": "text" }, "minimumCoverage": { "title": "Minimum coverage", "minimum": 0, "maximum": 1, "type": "number", "description": "Minimum fraction of expected URLs required to pass the gate.", "default": 0.98 }, "minimumTextLength": { "title": "Minimum text length", "minimum": 1, "type": "integer", "description": "Minimum number of text characters required for an observed page.", "default": 1 }, "minimumLengthRatio": { "title": "Shortening warning ratio", "minimum": 0, "maximum": 1, "type": "number", "description": "Minimum current-to-baseline text length ratio.", "default": 0.5 }, "maxRecords": { "title": "Maximum records per source", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum records read per source.", "default": 50000 }, "maxBytes": { "title": "Maximum JSON bytes per source", "minimum": 1, "maximum": 268435456, "type": "integer", "description": "Maximum bytes read per source.", "default": 67108864 }, "acceptBaseline": { "title": "Save accepted manifest on pass", "type": "boolean", "description": "Creates a separate version in this run storage; never updates a shared baseline pointer.", "default": false } } }, "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 Corpus Coverage Gate 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: