{ "openapi": "3.0.1", "info": { "title": "PDF to Text & Markdown Extractor (offline, RAG chunks)", "description": "Extracts plain text, Markdown with headings and lists, per-page text, metadata and RAG-ready chunks from PDFs you link or upload as base64. Runs offline with pdfminer.six: no AI, no third-party API. Respects robots.txt and PDF permissions. Flags scanned pages (no OCR).", "version": "0.1", "x-build-id": "huQbx7tQn7jpjlpwA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/wrentools~pdf-text-markdown-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-wrentools-pdf-text-markdown-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/wrentools~pdf-text-markdown-extractor/runs": { "post": { "operationId": "runs-sync-wrentools-pdf-text-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/wrentools~pdf-text-markdown-extractor/run-sync": { "post": { "operationId": "run-sync-wrentools-pdf-text-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Links to PDF files you are allowed to process. Each file is downloaded once; the site's robots.txt is respected.", "items": { "type": "string" } }, "pdfBase64": { "title": "PDF files as base64", "type": "array", "description": "PDF files sent inline, for files that are not online: a list of base64 strings, or of objects {\"name\": \"invoice.pdf\", \"data\": \"\"}. A data: URL prefix is accepted." }, "outputFormat": { "title": "Output format", "enum": [ "both", "markdown", "text" ], "type": "string", "description": "Plain text, Markdown (headings and lists inferred from the layout), or both.", "default": "both" }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "Add a 'pages' list with each page's text and number.", "default": false }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "When above 0, also split the Markdown into chunks of at most this many characters at paragraph boundaries, each with its page range. 0 turns chunking off; the minimum is 200.", "default": 0 }, "chunkOverlap": { "title": "RAG chunk overlap (characters)", "minimum": 0, "maximum": 25000, "type": "integer", "description": "Characters of the previous chunk repeated at the start of the next (at most half the chunk size).", "default": 200 }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Extract at most this many pages from each PDF; longer files are marked truncated. Pages are charged as extracted.", "default": 500 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger downloads are stopped and reported as file-too-large, without charge.", "default": 50 }, "requestDelayMs": { "title": "Delay between downloads from one site (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Minimum pause between two downloads from the same site.", "default": 500 } } }, "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 } } } } } } } } } }