{ "openapi": "3.0.1", "info": { "title": "Text Cleaner For RAG", "description": "Clean web text for RAG by removing boilerplate, normalizing whitespace, and producing chunk-ready text.", "version": "1.0", "x-build-id": "P2BFY1e3cLcOeoxij" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~text-cleaner-for-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-text-cleaner-for-rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~text-cleaner-for-rag/runs": { "post": { "operationId": "runs-sync-junipr-text-cleaner-for-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~text-cleaner-for-rag/run-sync": { "post": { "operationId": "run-sync-junipr-text-cleaner-for-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "documents": { "title": "Documents", "type": "array", "description": "Document objects with text or HTML content.", "items": { "type": "object" } }, "text": { "title": "Single Text Document", "type": "string", "description": "Optional plain text document to clean." }, "html": { "title": "Single HTML Document", "type": "string", "description": "Optional HTML document to strip and clean." }, "chunkSize": { "title": "Chunk Size", "minimum": 200, "maximum": 4000, "type": "integer", "description": "Target maximum characters per output chunk.", "default": 900 }, "chunkOverlap": { "title": "Chunk Overlap", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Approximate character overlap between adjacent chunks.", "default": 120 }, "minChunkChars": { "title": "Minimum Chunk Characters", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Minimum useful chunk length unless the document is shorter.", "default": 80 }, "removeBoilerplate": { "title": "Remove Boilerplate", "type": "boolean", "description": "Remove common web boilerplate such as cookie, newsletter, social, and navigation lines.", "default": true }, "dedupeRepeatedLines": { "title": "Deduplicate Repeated Lines", "type": "boolean", "description": "Drop repeated normalized lines inside each document.", "default": true }, "stripMarkdownLinks": { "title": "Strip Markdown Links", "type": "boolean", "description": "Convert markdown links to visible text.", "default": false }, "preserveHeadings": { "title": "Preserve Headings", "type": "boolean", "description": "Keep markdown heading markers for downstream retrieval context.", "default": true }, "maxDocuments": { "title": "Max Documents", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum documents to process.", "default": 25 }, "maxItems": { "title": "Maximum Output Chunks", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum cleaned chunks emitted across all documents.", "default": 100 }, "maxTextBytes": { "title": "Maximum Bytes Per Document", "minimum": 1000, "maximum": 5000000, "type": "integer", "description": "Maximum UTF-8 bytes cleaned from each document.", "default": 1000000 }, "includeReport": { "title": "Include Report Artifacts", "type": "boolean", "description": "Write cleaned markdown, chunks JSON, and summary reports to the key-value store.", "default": true }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and write a dry-run summary without PPE charges or dataset output.", "default": false }, "debug": { "title": "Debug Logs", "type": "boolean", "description": "Enable debug logs.", "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 } } } } } } } } } }