{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & Text Extractor with OCR (DOCX)", "description": "PDF to Markdown converter and PDF text extractor for RAG and AI agents. Turn PDFs, scanned PDFs, DOCX, HTML and images into clean Markdown or text with page-aware chunks. OCR runs only on scanned pages. $3 per 1,000 documents, failed files free.", "version": "1.0", "x-build-id": "Gr0dBR2fxjyN7Avw9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hanielazevedo~document-to-markdown-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hanielazevedo-document-to-markdown-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/hanielazevedo~document-to-markdown-ocr/runs": { "post": { "operationId": "runs-sync-hanielazevedo-document-to-markdown-ocr", "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/hanielazevedo~document-to-markdown-ocr/run-sync": { "post": { "operationId": "run-sync-hanielazevedo-document-to-markdown-ocr", "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": { "urls": { "title": "Document URLs", "maxItems": 10000, "type": "array", "description": "Public http(s) links to documents: PDF, DOCX, ODT, RTF, EPUB, HTML, TXT/MD, PNG, JPG, TIFF, WEBP, BMP, GIF. Format is detected from the file content, not the extension. Private/internal addresses are blocked.", "items": { "type": "string" } }, "files": { "title": "Upload files", "type": "array", "description": "Upload one or more files (stored in your key-value store) or paste file URLs." }, "keyValueStoreId": { "title": "Key-value store (convert all its files)", "type": "string", "description": "Pick one of your key-value stores. Every record in it is converted (up to 1,000), unless you list specific keys below. The Actor gets read-only access to this store only." }, "keyValueStoreKeys": { "title": "Keys in that store", "type": "array", "description": "Optional: only convert these record keys from the selected key-value store.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "Markdown keeps headings, lists, tables (GitHub-flavored) and links. Plain text strips all markup (tables become tab-separated).", "default": "markdown" }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto = use the PDF text layer and OCR only pages that are scanned/image-only or have broken text (recommended). always = OCR every PDF page (for PDFs with garbage text layers). never = never OCR (scanned pages produce no text; images fail with NO_TEXT_FOUND). Each OCRed page is billed as one ocr-page event.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes joined with +. Installed: eng, por, spa, fra, deu, ita, nld. Fewer languages = faster and more accurate.", "default": "eng+por" }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Only convert the first N pages of each PDF / multi-page TIFF. Empty = all pages (hard limit 2,000). Useful to cap OCR cost." }, "enableChunking": { "title": "Split into RAG chunks", "type": "boolean", "description": "Add heading-aware chunks (with heading path, character offsets and page range) to each item, ready for embedding.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target maximum characters per chunk (about 4 characters per token).", "default": 1500 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated from the end of the previous chunk.", "default": 150 }, "includeContentInDataset": { "title": "Include full content in dataset", "type": "boolean", "description": "Put the Markdown/text into the dataset item. The full file is always saved to the key-value store (link in outputFileUrl). Turn off for very large documents if you only need the files.", "default": true }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are rejected with FILE_TOO_LARGE (not charged).", "default": 50 }, "timeoutSecondsPerDocument": { "title": "Timeout per document", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Download + conversion time limit per document. If OCR runs out of time, the pages done so far are returned with a TIMEOUT_PARTIAL_OUTPUT warning.", "default": 600 }, "maxConcurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many documents are processed at the same time.", "default": 2 }, "keyValueStoreRecords": { "title": "Key-value store records (advanced)", "type": "array", "description": "Advanced: records as \"storeId/key\" strings. Stores must be readable by the run (prefer the key-value store picker above).", "items": { "type": "string" } } } }, "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 } } } } } } } } } }