RAG Evidence & Citation Auditor
Pricing
from $50.00 / 1,000 rag evidence audits
Audit RAG claims for citation coverage, evidence support, freshness, and provenance integrity with deterministic, privacy-safe reports.
You can access the RAG Evidence & Citation Auditor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "47JHBwv9jNWgJoZXS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rayanna~rag-evidence-citation-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rayanna-rag-evidence-citation-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/rayanna~rag-evidence-citation-auditor/runs": { "post": { "operationId": "runs-sync-rayanna-rag-evidence-citation-auditor", "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/rayanna~rag-evidence-citation-auditor/run-sync": { "post": { "operationId": "run-sync-rayanna-rag-evidence-citation-auditor", "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": [ "datasets" ], "properties": { "datasets": { "title": "RAG evaluation datasets", "minItems": 1, "maxItems": 5, "type": "array", "description": "Each dataset needs a name and exactly one of inline records or a public HTTPS JSON/NDJSON URL.", "items": { "type": "object", "properties": { "name": { "title": "Dataset name", "description": "Stable display name used to identify this evaluation bundle in reports.", "type": "string", "editor": "textfield", "minLength": 1, "maxLength": 160 }, "url": { "title": "Public JSON/NDJSON URL", "description": "Public HTTPS URL. Query strings are never retained in output.", "type": "string", "editor": "textfield" }, "records": { "title": "Inline RAG records", "description": "Use JSON view for records with question, answer, at most 100 sources, and at most 200 optional explicit claims.", "type": "array", "editor": "json", "items": { "type": "object" } }, "format": { "title": "Remote file format", "description": "Choose auto detection, JSON array, or newline-delimited JSON for remote input.", "type": "string", "enum": [ "auto", "json", "ndjson" ], "default": "auto", "editor": "select" } }, "required": [ "name" ], "additionalProperties": false } }, "qualityThreshold": { "title": "Quality gate score", "minimum": 0, "maximum": 100, "type": "number", "description": "Reports below this score fail the quality gate.", "default": 75 }, "minSupportOverlap": { "title": "Minimum deterministic token overlap", "minimum": 0, "maximum": 1, "type": "number", "description": "Minimum normalized claim-to-source token overlap required for deterministic evidence support.", "default": 0.2 }, "maxSourceAgeDays": { "title": "Maximum source age in days", "minimum": 0, "maximum": 36500, "type": "integer", "description": "Sources retrieved earlier than this age are reported as stale.", "default": 365 }, "requireSourceUrl": { "title": "Require a provenance URL for every source", "type": "boolean", "description": "Mark a source incomplete when it does not include a provenance URL.", "default": true }, "requireRetrievedAt": { "title": "Require retrievedAt for every source", "type": "boolean", "description": "Mark a source incomplete when it does not include an ISO 8601 retrieval timestamp.", "default": true }, "requireDeclaredHash": { "title": "Require a declared SHA-256 for every source", "type": "boolean", "description": "Mark a source incomplete when it does not include a declared SHA-256 content hash.", "default": true }, "includeClaimText": { "title": "Include claim text in output", "type": "boolean", "description": "Disabled by default so reports contain hashes and metrics instead of raw answer text.", "default": false }, "failOnQuality": { "title": "Fail the run when the quality gate fails", "type": "boolean", "description": "The report is delivered before the run is marked failed.", "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 RAG Evidence & Citation Auditor 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: