{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown Converter — LLM-Ready Text & RAG Chunks", "description": "Convert PDF URLs to clean, LLM-ready Markdown: headings, paragraphs and lists rebuilt from the layout, running headers and page numbers removed, plus plain text, per-page content, RAG chunks and metadata. Finds PDFs linked from web pages. $3 per 1,000 PDFs + $0.20 per 1,000 pages.", "version": "0.1", "x-build-id": "wJgrvFyiYwlizM96g" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~pdf-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~pdf-to-markdown/runs": { "post": { "operationId": "runs-sync-actor-forge-pdf-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/actor-forge~pdf-to-markdown/run-sync": { "post": { "operationId": "run-sync-actor-forge-pdf-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": [ "urls" ], "properties": { "urls": { "title": "PDF URLs", "type": "array", "description": "Links to PDF files. You can also add a web page (e.g. a reports or publications page): every PDF it links to is converted.", "items": { "type": "string" } }, "outputMode": { "title": "Output rows", "enum": [ "document", "pages" ], "type": "string", "description": "One row per PDF (whole document), or one row per page (handy for page-level citations).", "default": "document" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which content fields to return. Same price whatever you pick.", "items": { "type": "string", "enum": [ "markdown", "text" ], "enumTitles": [ "Markdown", "Plain text" ] }, "default": [ "markdown" ] }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Also split each PDF into chunks (one-row-per-PDF mode only) of at most this many characters for embedding, split at headings and paragraphs, each with its heading path. 0 = no chunks. Around 1,500–4,000 suits most embedding models.", "default": 0 }, "includePages": { "title": "Include per-page content", "type": "boolean", "description": "In one-row-per-PDF mode, also add a pages array with each page's Markdown/text and word count.", "default": false }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Convert at most this many pages of each PDF (from the start). Longer PDFs are marked truncated.", "default": 1000 }, "maxPdfs": { "title": "Max PDFs", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after converting this many PDFs (including ones found on web pages).", "default": 1000 }, "findPdfLinks": { "title": "Find PDF links on web pages", "type": "boolean", "description": "When a URL is a web page rather than a PDF, convert the PDFs it links to (one level, robots.txt respected).", "default": true }, "password": { "title": "PDF password", "type": "string", "description": "For password-protected PDFs you are entitled to open. Used for every PDF in the run." } } }, "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 } } } } } } } } } }