{ "openapi": "3.0.1", "info": { "title": "PDF to LLM Markdown — RAG Chunks & OCR-Ready", "description": "Convert PDF URLs into clean LLM-ready Markdown with page markers and RAG PDF chunks. Built for agents and Apify MCP. Text-layer pages from $0.0002; OCR PDF markdown only when needed. No HTML crawling. LIMITED_PERMISSIONS + pay-per-event for agentic payments.", "version": "0.1", "x-build-id": "4fOUdKfYa31nqIoh9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plugiverse~pdf-to-llm-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plugiverse-pdf-to-llm-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/plugiverse~pdf-to-llm-markdown/runs": { "post": { "operationId": "runs-sync-plugiverse-pdf-to-llm-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/plugiverse~pdf-to-llm-markdown/run-sync": { "post": { "operationId": "run-sync-plugiverse-pdf-to-llm-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": [ "pdfUrls" ], "properties": { "pdfUrls": { "title": "PDF URLs", "maxItems": 100, "type": "array", "description": "http(s) URLs of PDF files. Prefer links ending in .pdf; URLs without .pdf are accepted when the response is application/pdf (checked via Content-Type and %PDF magic). No HTML page crawling. Max 100 per run. Invalid entries come back as free rows with error.code INPUT_INVALID.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "Stop after this many pages (1-500). Useful to cap cost on huge manuals.", "default": 100 }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "type": "integer", "description": "Target size for RAG chunks. 0 disables chunks (markdown only). Minimum 200 when enabled. Chunks include pageStart/pageEnd for citations.", "default": 2000 }, "enableOcr": { "title": "OCR mode", "enum": [ "never", "auto", "always" ], "type": "string", "description": "never = text layer only (cheapest). auto = OCR pages whose text layer is empty (recommended). always = same as auto for empty pages; text-layer pages stay cheap. OCR is stubbed in the local draft and returns OCR_NOT_IMPLEMENTED until enabled on the Apify image; text-layer PDFs work fully.", "default": "auto" }, "includePageMarkers": { "title": "Include markers", "type": "boolean", "description": "Insert HTML comments before each page so LLMs and chunkers can cite page numbers.", "default": true }, "maxPdfMb": { "title": "Max PDF size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Reject downloads larger than this. Hard cap 100 MB.", "default": 50 }, "failOnAllErrors": { "title": "Fail run if every PDF fails", "type": "boolean", "description": "If true, a run where no PDF succeeds ends FAILED with an error summary instead of an empty SUCCEEDED run.", "default": true } } }, "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 } } } } } } } } } }