{ "openapi": "3.0.1", "info": { "title": "PDF & Word to Markdown for RAG — Chunks with Page Numbers", "description": "Convert PDF and Word (.docx) files from a URL into clean Markdown and RAG-ready chunks, each tagged with its page numbers. No browser, OCR, or paid APIs.", "version": "0.1", "x-build-id": "DOkYC6IBcp9T1QGV0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/s3nafps~doc-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-s3nafps-doc-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/s3nafps~doc-to-markdown/runs": { "post": { "operationId": "runs-sync-s3nafps-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/s3nafps~doc-to-markdown/run-sync": { "post": { "operationId": "run-sync-s3nafps-doc-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "fileUrls" ], "properties": { "fileUrls": { "title": "File URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Public links to the PDF or Word (.docx) files to convert, up to 100 per run.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "Public link to a PDF or Word (.docx) file." } } } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Choose whether the text comes back as Markdown (with headings and lists), as plain text, or both.", "default": "markdown" }, "chunkContent": { "title": "Split into RAG chunks", "type": "boolean", "description": "Turn this on to also get the text split into pieces of similar size, each tagged with its section and, for PDFs, its page numbers, ready for a vector database.", "default": false }, "chunkSizeTokens": { "title": "Chunk size (tokens)", "minimum": 50, "type": "integer", "description": "Approximate maximum size of each chunk in tokens (about four characters each), used only when chunking is on.", "default": 800 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "type": "integer", "description": "How many tokens each chunk repeats from the end of the previous one, so ideas are not cut off at the boundary (must be smaller than the chunk size).", "default": 100 }, "removeHeadersFooters": { "title": "Remove repeated headers and footers", "type": "boolean", "description": "Drop text that repeats at the top or bottom of at least half the pages (and at least three pages), such as running titles and page numbers, so it does not clutter the content.", "default": true }, "startPage": { "title": "Start at page", "minimum": 1, "type": "integer", "description": "The first page of each PDF to convert, with earlier pages skipped and not charged.", "default": 1 }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "The most pages to convert from each PDF, with later pages skipped and not charged.", "default": 500 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files larger than this size in megabytes are reported as failed instead of being converted.", "default": 50 }, "includeFailedDocuments": { "title": "Save failed files to the dataset", "type": "boolean", "description": "Turn this on to get a dataset row, with the reason, for each file that could not be converted (failed files are never charged either way).", "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 }, "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 } } } } } } } } } }