{ "openapi": "3.0.1", "info": { "title": "PDF to Text & Markdown Extractor for RAG", "description": "Convert PDFs from URLs or a dataset to clean text or Markdown with tables, metadata and RAG-ready chunks (page ranges + token estimates). Optional OCR for scanned pages. $0.003 per PDF; failed or password-protected PDFs are free.", "version": "1.0", "x-build-id": "SaMDJir22x0iRk2YH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/impressionable_lupine~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-impressionable_lupine-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/impressionable_lupine~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-impressionable_lupine-pdf-text-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/impressionable_lupine~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-impressionable_lupine-pdf-text-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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files (http/https). arXiv /abs/ links, Google Drive share links, Dropbox ?dl=0 links and GitHub blob links are converted to direct downloads automatically. Duplicates are removed. Up to 10,000 per run.", "items": { "type": "string" } }, "datasetId": { "title": "Read URLs from dataset (optional)", "type": "string", "description": "ID or name of an Apify dataset whose items contain PDF URLs, e.g. the output of a crawler or another Actor. Combined with the list above." }, "datasetUrlField": { "title": "URL field in the dataset", "type": "string", "description": "Field that holds the PDF URL. Dot paths (e.g. \"document.pdfUrl\") and arrays of URLs are supported.", "default": "url" }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "Markdown keeps headings, lists and tables (best for LLMs and RAG). Text is plain reflowed text (tables are tab-separated).", "default": "markdown" }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Detect tables from column alignment and return them as rows (and Markdown tables). Best effort: works on most digitally-created PDFs; merged cells and borderless complex layouts may split.", "default": true }, "chunkSize": { "title": "RAG chunk size (tokens)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "Target maximum tokens per chunk (estimate: ~4 characters per token). Chunks follow paragraph, heading and sentence boundaries. Set 0 to disable chunks.", "default": 800 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Tokens repeated from the end of the previous chunk at the start of the next one. Capped at half the chunk size.", "default": 100 }, "removeHeadersFooters": { "title": "Remove running headers, footers and page numbers", "type": "boolean", "description": "Drops lines that repeat in the top/bottom margin of most pages, plus bare page numbers. Recommended for RAG.", "default": true }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "Adds a pages[] array with the text of each page and its kind (text, ocr, needs_ocr, blank). Increases item size.", "default": false }, "ocr": { "title": "OCR scanned pages", "type": "boolean", "description": "Run OCR (Tesseract, English) on pages that have no text layer. Adds $0.002 per OCR page read. Off: scanned pages are listed in pagesNeedingOcr and a fully scanned PDF gets status needs_ocr (free).", "default": false }, "maxOcrPagesPerPdf": { "title": "Max OCR pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "Upper bound on OCR pages per PDF to keep cost and time predictable.", "default": 20 }, "maxPages": { "title": "Max pages per PDF", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Only the first N pages are processed (item.truncated = true when the PDF is longer). 0 = all pages, up to the hard cap of 2,000.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped with status too_large (not charged).", "default": 50 }, "timeoutSecs": { "title": "Time limit per PDF (seconds)", "minimum": 10, "maximum": 900, "type": "integer", "description": "Download + extraction budget per PDF. If reached after some pages, the item is returned with status partial; with no text, status timeout (not charged).", "default": 180 }, "maxConcurrency": { "title": "Parallel PDFs", "minimum": 1, "maximum": 10, "type": "integer", "description": "PDFs processed at the same time. 3 fits comfortably in 1 GB; raise memory before raising this.", "default": 3 } } }, "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 } } } } } } } } } }