{ "openapi": "3.0.1", "info": { "title": "PDF Intelligence", "description": "Stop fighting PDFs. Extract text, tables, and insights from any document, scanned or digital. Get RAG-ready chunks for LangChain & LlamaIndex. AI-powered summaries, classification, entity extraction. Use our API keys or bring your own (50% discount). From PDF chaos to clean data in minutes.", "version": "0.0", "x-build-id": "3l9G41sppyXBghBfR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/marielise.dev~pdf-intelligence/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-marielise.dev-pdf-intelligence", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/marielise.dev~pdf-intelligence/runs": { "post": { "operationId": "runs-sync-marielise.dev-pdf-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/marielise.dev~pdf-intelligence/run-sync": { "post": { "operationId": "run-sync-marielise.dev-pdf-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "runMode": { "title": "Run Mode", "enum": [ "one-click", "byok", "mcp-server" ], "type": "string", "description": "How to run: 'One Click' processes your PDF with platform AI (you pay PPE), 'BYOK' uses your API keys (50% savings), 'MCP Server' starts the server for Claude/MCP clients.", "default": "one-click" }, "pdfUrl": { "title": "PDF URL", "type": "string", "description": "URL of the PDF to process. Works with any public PDF link." }, "pdfContent": { "title": "Or Paste Base64 Content", "type": "string", "description": "Alternative: paste base64-encoded PDF content if you don't have a URL." }, "action": { "title": "What do you want to do?", "enum": [ "extract_text", "extract_tables", "get_metadata", "chunk_for_rag", "full_analysis" ], "type": "string", "description": "Choose what to extract from your PDF. All options use AI automatically when beneficial.", "default": "extract_text" }, "pages": { "title": "Specific Pages (optional)", "maxItems": 500, "type": "array", "description": "Process only specific pages (1-indexed). Leave empty for all pages. For very large PDFs (300+ pages), consider processing in batches.", "items": { "type": "integer" } }, "maxPages": { "title": "Max Pages to Process", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Limit processing to first N pages. Useful for very large documents. Leave empty or 0 for no limit.", "default": 0 }, "outputFormat": { "title": "Table Format", "enum": [ "json", "csv", "markdown" ], "type": "string", "description": "Output format for tables (only for Extract Tables action)", "default": "json" }, "chunkSize": { "title": "Chunk Size", "minimum": 100, "maximum": 10000, "type": "integer", "description": "Target chunk size in characters (only for Chunk for RAG action)", "default": 1000 }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key. Enables GPT-4 Vision for OCR and intelligent extraction." }, "anthropicApiKey": { "title": "Anthropic API Key", "type": "string", "description": "Your Anthropic API key. Enables Claude Vision for OCR and analysis." }, "googleApiKey": { "title": "Google API Key", "type": "string", "description": "Your Google API key for Gemini. Enables Gemini Vision for OCR." }, "preferredProvider": { "title": "Preferred AI Provider", "enum": [ "auto", "openai", "anthropic", "gemini" ], "type": "string", "description": "Which AI to use first. Auto tries: OpenAI -> Anthropic -> Gemini.", "default": "auto" }, "enableHttpApi": { "title": "Enable HTTP API", "type": "boolean", "description": "Enable REST API endpoint at /api for external integrations.", "default": true }, "debug": { "title": "Debug Mode", "type": "boolean", "description": "Enable verbose logging for troubleshooting.", "default": false } } }, "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 } } }, "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 } } } } } } } } } }