{ "openapi": "3.0.1", "info": { "title": "PDF, Image & Word to Text and Markdown (OCR)", "description": "Returns the text, Markdown, tables and page facts of a PDF, PNG, JPEG, TIFF or Word .docx file, one dataset row per page, plus RAG chunks with page spans. Reads the text layer, runs OCR only on scanned or unreadable pages, and flags illegible pages. Input: URL, upload or base64. First page free.", "version": "0.1", "x-build-id": "qKQr36UlCl6usoMvH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/atarivo~pdf-image-text-markdown-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-atarivo-pdf-image-text-markdown-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/atarivo~pdf-image-text-markdown-extractor/runs": { "post": { "operationId": "runs-sync-atarivo-pdf-image-text-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/atarivo~pdf-image-text-markdown-extractor/run-sync": { "post": { "operationId": "run-sync-atarivo-pdf-image-text-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "url": { "title": "Document URL or upload", "type": "string", "description": "Public http(s) link to a PDF, PNG, JPEG, TIFF or .docx file, or upload one here (it is stored in your key-value store and passed as its URL). Up to 50 MB, fetched within 60 seconds. Links to private, loopback or cloud-metadata addresses are refused. Give this or 'base64', not both." }, "base64": { "title": "Document as base64", "type": "string", "description": "The file itself, base64-encoded (a data: URI prefix is accepted). Up to 20 MB decoded. Use this when the file is not online. Give this or 'url', not both. The sample is a 2-page synthetic PDF with one table." }, "fileName": { "title": "File name", "type": "string", "description": "Optional name of the file, such as report.pdf. Used in messages and in the chunks file; the type is always read from the file's bytes." }, "ocr": { "title": "OCR", "enum": [ "auto", "never", "always" ], "type": "string", "description": "auto (default) runs OCR only on pages whose text layer is empty or illegible; never uses the text layer only (images need OCR, so never fails on an image); always OCRs every PDF page. Each OCR'd page adds the page-ocr event.", "default": "auto" }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop after this many pages (default 500, minimum 1, maximum 2000). For .docx a page is 3,000 characters. The document row says truncated: true when pages were left unread.", "default": 500 }, "outputs": { "title": "Outputs", "type": "array", "description": "Which outputs to produce: text, markdown, chunks (RAG chunks JSON with page spans), tables. Default: all four. Without tables, no table-extracted events are charged.", "items": { "type": "string", "enum": [ "text", "markdown", "chunks", "tables" ] }, "default": [ "text", "markdown", "chunks", "tables" ] }, "chunkChars": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target size of each RAG chunk in characters (default 1,500, minimum 200, maximum 20,000). Chunks break at paragraph and table boundaries and record the pages they span.", "default": 1500 } } }, "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 } } } } } } } } } }