{ "openapi": "3.0.1", "info": { "title": "P2M AI Feeder – PDF to Markdown Converter", "description": "Convert digital and scanned PDFs into clean Markdown, structured JSON, and deterministic chunks for AI agents and RAG pipelines. Supports OCR, tables, image descriptions, batch processing, and downloadable artifacts.", "version": "0.1", "x-build-id": "00Ay6FKjcKsPrivgc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gtgyani206~p2m-aifeeder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gtgyani206-p2m-aifeeder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gtgyani206~p2m-aifeeder/runs": { "post": { "operationId": "runs-sync-gtgyani206-p2m-aifeeder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gtgyani206~p2m-aifeeder/run-sync": { "post": { "operationId": "run-sync-gtgyani206-p2m-aifeeder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sources" ], "properties": { "sources": { "title": "PDF files or URLs", "minItems": 1, "maxItems": 20, "type": "array", "description": "Upload one or more PDFs, or provide publicly reachable HTTP(S) PDF URLs.", "items": { "type": "string" } }, "doOcr": { "title": "Enable OCR", "type": "boolean", "description": "Use local EasyOCR for scanned pages and text inside sufficiently large bitmap images. CPU-intensive; enable it for scans or image-based text.", "default": false }, "forceFullPageOcr": { "title": "Force full-page OCR", "type": "boolean", "description": "Replace the PDF text layer with OCR for every page. Enable only for scans or PDFs with a broken hidden text layer because it is slower and can reduce native-text accuracy.", "default": false }, "describeImages": { "title": "Describe images", "type": "boolean", "description": "Use the bundled local SmolVLM model to turn photos, diagrams, figures, and charts into searchable Markdown descriptions. This is CPU-intensive and disabled by default. No external AI API is used.", "default": false }, "imageDescriptionPrompt": { "title": "Image description instructions", "minLength": 1, "maxLength": 2000, "type": "string", "description": "Instructions for the local vision model. Ask for the visual details most useful to your downstream agent or RAG pipeline.", "default": "Describe the image for retrieval. Extract important readable text and explain the main visual structure. Do not guess." }, "extractTables": { "title": "Extract table structure", "type": "boolean", "description": "Reconstruct table rows and columns. Disable this for plain-text documents or as a last-resort fallback when table analysis is too expensive.", "default": true }, "tableMode": { "title": "Table extraction mode", "enum": [ "fast", "accurate" ], "type": "string", "description": "Fast mode is the practical default. Accurate mode is slower and intended for complex tables.", "default": "fast" }, "pageBatchSize": { "title": "Pages per conversion batch", "minimum": 1, "maximum": 50, "type": "integer", "description": "Convert and persist this many pages at a time. Smaller batches isolate slow pages and preserve more progress; larger batches have less overhead.", "default": 6 }, "chunkSizeChars": { "title": "Chunk size", "minimum": 1000, "maximum": 30000, "type": "integer", "description": "Approximate maximum number of characters per agent-ready chunk.", "default": 6000 }, "chunkOverlapChars": { "title": "Chunk overlap", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Approximate content overlap retained between adjacent chunks.", "default": 500 }, "includeMarkdownInDataset": { "title": "Include full Markdown in dataset", "type": "boolean", "description": "Embed full Markdown in document rows for small PDFs; the key-value-store copy is always created.", "default": false }, "includeChunksInDataset": { "title": "Include chunks in dataset", "type": "boolean", "description": "Push one dataset row per chunk so agents can consume content directly.", "default": true }, "exportDoclingJson": { "title": "Export structured Docling JSON", "type": "boolean", "description": "Build and store Docling's lossless document representation with layout and provenance metadata. Disabled by default to avoid serializing a large structure that many runs do not use.", "default": false }, "maxDoclingJsonPages": { "title": "Maximum pages for Docling JSON", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Skip structured Docling JSON when a PDF exceeds this page count, even if exportDoclingJson is enabled. Markdown and chunks are still produced.", "default": 50 }, "maxPages": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Reject an individual PDF when its page count exceeds this limit.", "default": 250 }, "maxFileSizeMb": { "title": "Maximum file size", "minimum": 1, "maximum": 500, "type": "integer", "description": "Reject an individual PDF when its downloaded size exceeds this limit.", "default": 50 }, "doclingTimeoutSeconds": { "title": "Docling batch timeout", "minimum": 30, "maximum": 3570, "type": "integer", "description": "Cooperative Docling processing limit for one page batch. Docling may return usable partial output when this limit is reached.", "default": 540 }, "workerTimeoutSeconds": { "title": "Hard worker batch timeout", "minimum": 60, "maximum": 3600, "type": "integer", "description": "Hard subprocess limit for one page batch. Must be at least 30 seconds greater than the Docling timeout so partial output has time to serialize.", "default": 600 }, "documentTimeoutSeconds": { "title": "Legacy hard timeout", "minimum": 60, "maximum": 3600, "type": "integer", "description": "Deprecated compatibility alias used only when workerTimeoutSeconds is absent. New inputs should use the separate Docling and worker batch timeouts." }, "failFast": { "title": "Stop on first failure", "type": "boolean", "description": "When disabled, report a failed document and continue processing the remaining PDFs.", "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 } } } } } } } } } }