{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown & Text Converter for LLMs and RAG", "description": "Convert PDFs (URLs or uploads) to clean Markdown or text for LLMs and RAG: headings, lists, tables, headers/footers and page numbers removed. One item per PDF, per page or RAG chunks with overlap. Pay per page; scans and failed files are free.", "version": "0.1", "x-build-id": "TFdfvgLB8TshaGs56" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rjmacarthy~pdf-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rjmacarthy-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rjmacarthy~pdf-to-markdown/runs": { "post": { "operationId": "runs-sync-rjmacarthy-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rjmacarthy~pdf-to-markdown/run-sync": { "post": { "operationId": "run-sync-rjmacarthy-pdf-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "urls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files, one per line, e.g. https://arxiv.org/pdf/1706.03762. arXiv abstract pages, GitHub file pages, Dropbox and Google Drive share links are rewritten to their download URL automatically. The file must be public (no login).", "items": { "type": "string" } }, "uploadedFile": { "title": "Or upload a PDF file", "type": "string", "description": "Upload a PDF from your computer (stored in a key-value store) or paste a link to one. Converted together with the URLs above." }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps structure (# headings, - lists, | tables |) and is the best input for LLMs. Plain text has no markup. \"Both\" fills both fields.", "default": "markdown" }, "granularity": { "title": "One dataset item per", "enum": [ "document", "page", "chunks" ], "type": "string", "description": "Document: the whole PDF in one item. Page: one item per page (with its page number, good for citations). Chunks: fixed-size, overlapping pieces with their heading path and page range, ready for embeddings / RAG.", "default": "document" }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Target chunk size when \"One dataset item per\" is Chunks, in approximate LLM tokens (1 token ≈ 4 characters of English). Chunks end at sentence, list-item or table-row boundaries and start fresh at headings when possible.", "default": 500 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "How much text each chunk repeats from the end of the previous one (whole sentences, never across a heading). At most half the chunk size.", "default": 50 }, "includePageMarkers": { "title": "Insert page markers", "type": "boolean", "description": "In Document output, insert (Markdown) or --- Page N --- (text) where each page starts, so you can cite page numbers. (Chunk and page items carry pageFrom/pageTo instead.)", "default": false }, "pageRange": { "title": "Page range", "type": "string", "description": "Only convert these pages of every PDF, e.g. \"1-10, 15, 20-\" (\"20-\" = page 20 to the end). Leave empty for all pages." }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 0, "type": "integer", "description": "Convert at most this many pages of each PDF (after the page range). 0 = no limit.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 500, "type": "integer", "description": "Skip PDFs larger than this (reported as an error item, not charged). Very large files need more memory: use 1024 MB+ memory for files over 100 MB.", "default": 50 }, "removeHeadersFooters": { "title": "Remove running headers, footers and page numbers", "type": "boolean", "description": "Drop text that repeats at the top or bottom of at least half of the pages (needs 3+ pages) and lone page numbers. Recommended for LLM / RAG use.", "default": true }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Only for your own password-protected PDFs: the password to open them (used for every file in this run). Without it, protected files are reported as errors and not charged." }, "maxConcurrency": { "title": "Max parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many PDFs are downloaded at the same time (at most 3 from one website). Conversion itself runs one PDF at a time.", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Not needed for most PDFs. Enable Apify Proxy (datacenter) if a website blocks downloads from Apify's servers (HTTP 403/429), or add your own proxy URLs. Residential and SERP proxy groups are not supported: the run falls back to Apify datacenter proxy.", "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 } } } } } } } } } }