{ "openapi": "3.0.1", "info": { "title": "PDF to AI-Ready Data (Markdown, Tables, RAG Chunks, OCR)", "description": "Convert PDFs into clean Markdown, JSON/CSV tables and RAG-ready chunks with page metadata. Built-in OCR for scanned PDFs. No AI API calls, no proxies.", "version": "0.1", "x-build-id": "pYX6ihW7hM5nm0IpC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/loris-barce~pdf-to-ai-data/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-loris-barce-pdf-to-ai-data", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/loris-barce~pdf-to-ai-data/runs": { "post": { "operationId": "runs-sync-loris-barce-pdf-to-ai-data", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/loris-barce~pdf-to-ai-data/run-sync": { "post": { "operationId": "run-sync-loris-barce-pdf-to-ai-data", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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). The prefilled example is RFC 2119 (3 text pages), used by the daily automated test.", "items": { "type": "string" } }, "uploadedFiles": { "title": "Uploaded files", "type": "array", "description": "PDFs you uploaded to Apify. Each entry is either the URL of an uploaded file / key-value store record, a record key in this run's default key-value store (e.g. \"my-report.pdf\"), or \"/\" for a record in another key-value store you own.", "items": { "type": "string" } }, "outputs": { "title": "Outputs", "type": "array", "description": "What to produce for each document. markdown = clean Markdown with headings; text = plain text; tables = tables as JSON + CSV; chunks = RAG-ready chunks in the \"chunks\" dataset.", "items": { "type": "string", "enum": [ "markdown", "text", "tables", "chunks" ], "enumTitles": [ "Markdown", "Plain text", "Tables (JSON + CSV)", "RAG chunks" ] }, "default": [ "markdown" ] }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "auto = OCR only pages without a text layer (scans); always = OCR every page; never = never OCR.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages used by Tesseract OCR.", "items": { "type": "string", "enum": [ "eng", "ita", "deu", "fra", "spa" ], "enumTitles": [ "English", "Italian", "German", "French", "Spanish" ] }, "default": [ "eng", "ita" ] }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Maximum length of each RAG chunk, overlap included.", "default": 1000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How many characters from the end of a chunk are repeated at the start of the next one. Must be smaller than half the chunk size.", "default": 150 }, "pageRange": { "title": "Page range", "pattern": "^\\s*(\\d+\\s*(-\\s*\\d*)?\\s*)(,\\s*\\d+\\s*(-\\s*\\d*)?\\s*)*$", "type": "string", "description": "Only process these pages (1-based), e.g. \"1-10,15\" or \"20-\". Leave empty for all pages." }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Cost protection: at most this many pages are processed per document.", "default": 500 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are rejected without being processed.", "default": 50 } } }, "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 } } } } } } } } } }