{
"openapi": "3.0.1",
"info": {
"title": "PDF to Markdown & RAG Chunks Extractor",
"description": "Turn PDF links into clean text, LLM-ready Markdown and token-counted RAG chunks with page numbers. Reads one PDF or a whole dataset, with document metadata. No browser, no OCR. Not affiliated with any PDF vendor.",
"version": "1.0",
"x-build-id": "r84soPyZyzf3XtGtn"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/mmdincer~pdf-rag-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-mmdincer-pdf-rag-extractor",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/mmdincer~pdf-rag-extractor/runs": {
"post": {
"operationId": "runs-sync-mmdincer-pdf-rag-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/mmdincer~pdf-rag-extractor/run-sync": {
"post": {
"operationId": "run-sync-mmdincer-pdf-rag-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"maxItems": 100,
"type": "array",
"description": "Direct links to PDF files, one per line. Up to 100 per run. The link must return the file itself (an https://…/report.pdf link), not a page that shows a PDF viewer.",
"items": {
"type": "string"
}
},
"datasetId": {
"title": "Read PDF links from a dataset",
"type": "string",
"description": "Optional. Pick an Apify dataset whose items contain PDF links. The Actor looks for pdfUrl, fileUrl, documentUrl, url, link and similar fields, which is how you chain it after a crawler without copying links by hand. The dataset is opened read-only."
},
"mode": {
"title": "What to return",
"enum": [
"both",
"chunks",
"document"
],
"type": "string",
"description": "Document and chunks writes one document row plus its chunk rows. Chunks only skips the document row, so the dataset is exactly what an embedding job wants. Document only returns the text, Markdown and metadata without chunking.",
"default": "both"
},
"chunkSize": {
"title": "Chunk size (tokens)",
"minimum": 64,
"maximum": 4096,
"type": "integer",
"description": "Token budget per chunk, counted with the cl100k_base tokenizer that OpenAI embedding and chat models use. 512 is a good default for retrieval; use 256 for narrow facts and 1024 or more for long arguments.",
"default": 512
},
"chunkOverlap": {
"title": "Chunk overlap (tokens)",
"minimum": 0,
"maximum": 2048,
"type": "integer",
"description": "How much text from the end of one chunk is repeated at the start of the next, so an answer that straddles a boundary is still findable. 64 is the default (an eighth of the chunk size). At most half the chunk size.",
"default": 64
},
"startPage": {
"title": "First page",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Start reading at this page (1-based). Useful when the first pages are a cover and a table of contents you do not want to pay for.",
"default": 1
},
"maxPages": {
"title": "Maximum pages per PDF",
"minimum": 0,
"maximum": 2000,
"type": "integer",
"description": "Stop after this many pages. 0 means the whole document. A 400-page manual you need three pages from costs three pages this way.",
"default": 0
},
"includeMarkdown": {
"title": "Include Markdown",
"type": "boolean",
"description": "Add the markdown field to the document row: headings, paragraphs and lists rebuilt from the page layout. Turn it off if you only want the chunks.",
"default": true
},
"includePages": {
"title": "Include per-page text",
"type": "boolean",
"description": "Add a pages array with the text of every page. Off by default because the Markdown field already covers the content; turn it on when you need to quote a single page.",
"default": false
},
"maxDocuments": {
"title": "Maximum PDFs per run",
"minimum": 1,
"maximum": 100,
"type": "integer",
"description": "Upper bound on how many PDF links are processed in one run, applied after the list and the dataset are merged. A low number is a simple way to cap the cost of a first run.",
"default": 100
},
"maxFileSizeMb": {
"title": "Maximum file size (MB)",
"minimum": 1,
"maximum": 100,
"type": "integer",
"description": "Skip a PDF larger than this instead of downloading it. Larger files are usually scans or image-heavy reports that this Actor reads badly anyway.",
"default": 100
},
"maxChunksPerDocument": {
"title": "Maximum chunks per PDF",
"minimum": 10,
"maximum": 2000,
"type": "integer",
"description": "Safety cap on chunk rows for one document. A very small chunk size on a very long document would otherwise write tens of thousands of rows; the cap keeps the run predictable. Leave it at the default unless you know you need more.",
"default": 2000
},
"requestsPerSecond": {
"title": "Requests per second",
"minimum": 0.2,
"maximum": 10,
"type": "number",
"description": "How fast PDFs are downloaded. 2 is a polite default; lower it to 1 when all files come from one small server.",
"default": 2
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Optional. The Actor downloads public PDF links directly, which works for most sites; use Apify Proxy when the files sit behind a CDN that blocks datacenter IPs."
}
}
},
"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
}
}
}
}
}
}
}
}
}
}