{ "openapi": "3.0.1", "info": { "title": "Word, Excel, PowerPoint & HTML to RAG Chunks (JSON, OCR)", "description": "Use to convert a Word document to text for an LLM, extract text from Excel and PowerPoint files, or read text from an image with OCR (also CSV and HTML), with RAG chunks and citations. Input: fileUrls. $0.003 per unit, +$0.01 per OCR image. Not for PDFs or old .doc/.xls files.", "version": "0.1", "x-build-id": "0xxJ30d2tM3MUfE1B" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/landoz~documents-to-json-chunks/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-landoz-documents-to-json-chunks", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/landoz~documents-to-json-chunks/runs": { "post": { "operationId": "runs-sync-landoz-documents-to-json-chunks", "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/landoz~documents-to-json-chunks/run-sync": { "post": { "operationId": "run-sync-landoz-documents-to-json-chunks", "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": { "fileUrls": { "title": "File URLs", "uniqueItems": true, "type": "array", "description": "Public http(s) links to the files to convert, one per line. The type is detected from the file content, not the link, so links without an extension work. Up to 100 URLs per run; files are fetched once, parsed and deleted when the run ends. Example: https://example.com/policy.docx, https://example.com/prices.xlsx.", "default": [ "https://api.apify.com/v2/key-value-stores/jI2vtZmMPBuSQjlKX/records/doc-good-docx" ], "items": { "type": "string" } }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Target characters per RAG chunk. Chunks are cut at sentence or word boundaries, never mid-word, and never cross a unit (part, slide, row block or image). 0 turns chunking off. Example: 1200.", "default": 1200 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters shared by consecutive chunks of the same unit, so a sentence cut at a boundary is whole in one of them. Capped at half the chunk size. Example: 150.", "default": 150 }, "ocr": { "title": "OCR for images", "enum": [ "auto", "off" ], "type": "string", "description": "\"auto\" reads every image (and every TIFF frame) with Tesseract OCR. \"off\" skips images with a free error. Has no effect on Word, PowerPoint, Excel, CSV and HTML files. Example: auto.", "default": "auto" }, "ocrLanguage": { "title": "OCR language", "enum": [ "eng" ], "type": "string", "description": "Tesseract language of the text in images. Only English (\"eng\") is installed. Example: eng.", "default": "eng" }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are refused (free) as soon as the declared or received size passes this limit. Default 50, maximum 200. Example: 50.", "default": 50 }, "maxUnitsPerFile": { "title": "Max units per file", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Safety cap on billable units per file (a unit is about 3,000 characters of a Word or HTML file, one slide, up to 500 spreadsheet rows, or one image). A file with more units returns a free too_many_units error; raise this to process it. Default 200, maximum 1000. Example: 200.", "default": 200 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }