{ "openapi": "3.0.1", "info": { "title": "Agentic Document Extractor", "description": "Extract RAG-ready chunks with provenance from PDFs, scans, images, DOCX, XLSX, PPTX, CSV, TXT, and Markdown using a local-first Apify Actor.", "version": "0.1", "x-build-id": "Ce9CQWE4FIyjpwD9b" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~agentic-document-extractor-local/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-agentic-document-extractor-local", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~agentic-document-extractor-local/runs": { "post": { "operationId": "runs-sync-solutionssmart-agentic-document-extractor-local", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~agentic-document-extractor-local/run-sync": { "post": { "operationId": "run-sync-solutionssmart-agentic-document-extractor-local", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documents" ], "properties": { "documents": { "title": "๐Ÿ“š Documents", "minItems": 1, "type": "array", "description": "Public document URLs to process.", "items": { "type": "object", "additionalProperties": false, "required": [ "url" ], "properties": { "url": { "title": "๐Ÿ”— Document URL", "type": "string", "description": "Public http or https URL for a document to extract.", "pattern": "^https?://" }, "id": { "title": "๐Ÿ†” Document ID", "type": "string", "description": "Optional stable identifier to use in outputs." }, "label": { "title": "๐Ÿท๏ธ Label", "type": "string", "description": "Optional human-friendly document label." }, "fileName": { "title": "๐Ÿ“ Preferred file name", "type": "string", "description": "Optional file name override used when the URL does not contain a useful name." }, "mimeTypeHint": { "title": "๐Ÿง  MIME type hint", "type": "string", "description": "Optional MIME type hint for ambiguous URLs." } } } }, "maxConcurrency": { "title": "โšก Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of documents to download and process in parallel.", "default": 3 }, "ocrLanguages": { "title": "๐Ÿ”ค OCR languages", "type": "array", "description": "Tesseract language codes used when OCR is required.", "items": { "type": "string" }, "default": [ "eng" ] }, "ocrFallbackMode": { "title": "๐Ÿ‘€ OCR fallback mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Choose whether OCR runs automatically on sparse PDFs, always, or never.", "default": "auto" }, "chunkMaxChars": { "title": "โœ‚๏ธ Chunk max chars", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Maximum approximate character length for each chunk.", "default": 1800 }, "chunkOverlapChars": { "title": "๐Ÿ” Chunk overlap chars", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Approximate overlap between adjacent chunks.", "default": 200 }, "maxPagesPerDocument": { "title": "๐Ÿ“„ Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Hard limit on pages or slides processed from a single document.", "default": 200 }, "emitMarkdown": { "title": "๐Ÿงพ Emit markdown", "type": "boolean", "description": "Include markdown-formatted chunk content when available.", "default": true }, "emitRawText": { "title": "๐Ÿ”ก Emit raw text", "type": "boolean", "description": "Include plain text chunk content.", "default": true }, "emitBoundingBoxes": { "title": "๐Ÿ“ Emit bounding boxes", "type": "boolean", "description": "Include bounding box provenance when the extractor can provide it.", "default": 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 } } } } } } } } } }