{ "openapi": "3.0.1", "info": { "title": "PDF & Document to Markdown (LLM / RAG ready)", "description": "Convert PDF (including scanned and password-protected), Word, PowerPoint, Excel and HTML documents from URLs into clean Markdown or plain text with headings, tables, metadata and optional RAG chunks.", "version": "1.0", "x-build-id": "jYVlVf1WCpoGayzuQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/prometheus-maker~pdf-document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-prometheus-maker-pdf-document-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/prometheus-maker~pdf-document-to-markdown/runs": { "post": { "operationId": "runs-sync-prometheus-maker-pdf-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/prometheus-maker~pdf-document-to-markdown/run-sync": { "post": { "operationId": "run-sync-prometheus-maker-pdf-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Document URLs", "type": "array", "description": "Direct links to PDF, DOCX, PPTX, XLSX, HTML, CSV or EPUB files. The file type is detected automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps headings, lists and tables. Text is plain reading-order text.", "default": "markdown" }, "chunkSize": { "title": "Chunk size for RAG (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "If set, also split the Markdown into chunks of about this many characters on paragraph boundaries. Each chunk lists the headings it sits under. 0 = no chunks.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated from the end of one chunk at the start of the next.", "default": 0 }, "pageRange": { "title": "PDF page range", "type": "string", "description": "Only convert these pages, e.g. \"1-5,8,10-\". Empty = all pages." }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "For password-protected PDFs. Used for every PDF in this run and stored encrypted. Leave empty for normal files." }, "maxPagesPerDocument": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "Safety cap on pages converted per PDF (0 = no cap). You pay per page, so this also caps cost.", "default": 0 }, "ocrMode": { "title": "OCR for scanned pages", "enum": [ "auto", "always", "off" ], "type": "string", "description": "Auto: OCR only pages that have no text layer (scans, photos). Always: OCR every page. Off: never. OCR pages are billed separately.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages present in the scanned documents. More languages are slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "rus", "ukr", "ces", "slk", "hun", "ron", "bul", "hrv", "srp", "slv", "ell", "tur", "swe", "dan", "nor", "fin", "est", "lav", "lit", "cat", "ara", "heb", "fas", "hin", "ben", "tha", "vie", "ind", "msa", "jpn", "kor", "chi_sim", "chi_tra" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Russian", "Ukrainian", "Czech", "Slovak", "Hungarian", "Romanian", "Bulgarian", "Croatian", "Serbian (Cyrillic)", "Slovenian", "Greek", "Turkish", "Swedish", "Danish", "Norwegian", "Finnish", "Estonian", "Latvian", "Lithuanian", "Catalan", "Arabic", "Hebrew", "Persian", "Hindi", "Bengali", "Thai", "Vietnamese", "Indonesian", "Malay", "Japanese", "Korean", "Chinese (Simplified)", "Chinese (Traditional)" ] }, "default": [ "eng" ] }, "extractTables": { "title": "Detect tables in PDFs", "type": "boolean", "description": "Render ruled tables as Markdown tables.", "default": true }, "includeTablesJson": { "title": "Also output tables as JSON", "type": "boolean", "description": "Add a 'tables' field with each detected PDF table as rows of cells.", "default": false }, "removeHeadersFooters": { "title": "Remove running headers, footers and page numbers", "type": "boolean", "description": "Drops lines that repeat at the top or bottom of most pages (running titles, page numbers), so they don't break up the text.", "default": true }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many files to download and convert at once. Higher is faster but uses more memory.", "default": 4 } } }, "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 } } } } } } } } } }