{ "openapi": "3.0.1", "info": { "title": "RAG Dataset Quality Auditor", "description": "Find duplicate, stale, incomplete, repetitive, and poorly chunked documents before they weaken RAG retrieval.", "version": "0.2", "x-build-id": "gwd95YbEO6VY3Rlkh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gifted_wagon~rag-dataset-quality-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gifted_wagon-rag-dataset-quality-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gifted_wagon~rag-dataset-quality-auditor/runs": { "post": { "operationId": "runs-sync-gifted_wagon-rag-dataset-quality-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gifted_wagon~rag-dataset-quality-auditor/run-sync": { "post": { "operationId": "run-sync-gifted_wagon-rag-dataset-quality-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "datasetId": { "title": "Dataset to audit", "type": "string", "description": "Select an existing Apify dataset. Each item should contain a text-like field such as text, markdown, content, or body." }, "documents": { "title": "Inline documents", "type": "array", "description": "Optional documents pasted directly. Each item may contain id, url, title, text, updatedAt, and metadata.", "items": { "type": "object", "additionalProperties": true, "properties": { "id": { "title": "Document ID", "type": "string", "description": "Stable source identifier.", "editor": "textfield" }, "url": { "title": "Source URL", "type": "string", "description": "Canonical source URL.", "editor": "textfield" }, "title": { "title": "Document title", "type": "string", "description": "Descriptive title used by retrieval consumers.", "editor": "textfield" }, "text": { "title": "Document text", "type": "string", "description": "Plain-text content to audit.", "editor": "textarea" }, "updatedAt": { "title": "Updated at", "type": "string", "description": "ISO 8601 freshness timestamp.", "editor": "textfield" }, "metadata": { "title": "Metadata", "type": "object", "description": "Optional source metadata retained in the input only.", "editor": "json" } } } }, "maxDocuments": { "title": "Maximum documents", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of documents to read and charge for across both sources.", "default": 500 }, "minWords": { "title": "Minimum useful words", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Documents below this threshold receive a too-short issue.", "default": 80 }, "maxWords": { "title": "Maximum useful words", "minimum": 50, "maximum": 100000, "type": "integer", "description": "Documents above this threshold receive a too-long issue and should usually be chunked.", "default": 2000 }, "staleAfterDays": { "title": "Stale after days", "minimum": 0, "maximum": 3650, "type": "integer", "description": "Documents with a valid updatedAt older than this threshold receive a stale-content issue. Set 0 to disable.", "default": 365 }, "nearDuplicateThreshold": { "title": "Near-duplicate similarity", "minimum": 0.7, "maximum": 1, "type": "number", "description": "Jaccard similarity threshold for candidate documents identified by the fingerprint index.", "default": 0.92 }, "contentFields": { "title": "Dataset content fields", "type": "array", "description": "First matching field is used as document text when reading a dataset.", "items": { "type": "string" }, "default": [ "text", "markdown", "content", "body" ] }, "titleFields": { "title": "Dataset title fields", "type": "array", "description": "First matching field is used as the document title when reading a dataset.", "items": { "type": "string" }, "default": [ "title", "name", "heading" ] }, "urlFields": { "title": "Dataset URL fields", "type": "array", "description": "First matching field is used as the canonical source URL when reading a dataset.", "items": { "type": "string" }, "default": [ "url", "sourceUrl", "canonicalUrl" ] }, "updatedAtFields": { "title": "Dataset freshness fields", "type": "array", "description": "First matching field is used as the freshness timestamp when reading a dataset.", "items": { "type": "string" }, "default": [ "updatedAt", "lastModified", "modifiedAt", "publishedAt" ] }, "includeContentPreview": { "title": "Include content preview", "type": "boolean", "description": "Include a short normalized preview in each result. Leave off for sensitive corpora.", "default": false }, "contentPreviewCharacters": { "title": "Preview characters", "minimum": 50, "maximum": 2000, "type": "integer", "description": "Maximum number of normalized document characters to include when previews are enabled.", "default": 280 }, "payload": { "title": "Integration payload", "type": "object", "description": "Automatically supplied by Apify when this Actor is connected to another Actor run.", "additionalProperties": 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 } } } } } } } } } }