{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & Text for AI/RAG", "description": "Convert PDF URLs to clean Markdown or plain text for LLMs, RAG and AI agents. Keeps headings, lists and tables, removes headers/footers, and can return heading-aware chunks. Works with Google Drive, Dropbox and password-protected PDFs. Failed files are not charged.", "version": "0.0", "x-build-id": "oo8dKPQnguQ0xrrXL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bigochelo~pdf-to-markdown-text-for-ai-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bigochelo-pdf-to-markdown-text-for-ai-rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bigochelo~pdf-to-markdown-text-for-ai-rag/runs": { "post": { "operationId": "runs-sync-bigochelo-pdf-to-markdown-text-for-ai-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bigochelo~pdf-to-markdown-text-for-ai-rag/run-sync": { "post": { "operationId": "run-sync-bigochelo-pdf-to-markdown-text-for-ai-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "pdfUrls" ], "properties": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Public links to PDF files, one per line. Example: [\"https://arxiv.org/pdf/1706.03762\"]. Google Drive, Dropbox and GitHub share links are converted automatically.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "\"markdown\" (default, keeps headings, lists and tables; best for LLMs), \"text\" (plain text) or \"both\".", "default": "markdown" }, "chunking": { "title": "Split into RAG chunks", "type": "boolean", "description": "If true, adds a 'chunks' array: heading-aware pieces with their section path, ready for embeddings / vector databases. Example: true with chunkSize 1500.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "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 between consecutive chunks to keep context.", "default": 150 }, "aiSafety": { "title": "AI safety scan (prompt injection)", "type": "boolean", "description": "Removes text a human cannot see (white-on-white, tiny or off-page text) and reports hidden instructions aimed at AI, invisible characters and data-exfiltration links in an 'aiSafety' object. Free and on by default.", "default": true }, "wrapAsUntrusted": { "title": "Wrap output as untrusted data", "type": "boolean", "description": "If true, the Markdown is wrapped in tags telling the LLM to treat it as data, not instructions.", "default": false }, "includePages": { "title": "Include per-page content", "type": "boolean", "description": "If true, adds a 'pages' array with each page's content and tables (useful for citing page numbers).", "default": false }, "extractTables": { "title": "Detect tables", "type": "boolean", "description": "Converts tables into Markdown tables (and raw rows in per-page output).", "default": true }, "removeHeadersFooters": { "title": "Remove repeated headers & footers", "type": "boolean", "description": "Drops running headers, footers and page numbers that repeat on most pages.", "default": true }, "maxPages": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "Only process the first N pages of each PDF. 0 = all pages.", "default": 0 }, "password": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs (applied to all files in this run)." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 50 }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many PDFs are processed at the same time.", "default": 4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Only needed if a website blocks downloads from the cloud.", "default": { "useApifyProxy": 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 }, "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 } } } } } } } } } }