{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor — Markdown, Tables, OCR & RAG Chunks", "description": "Extract text, GFM Markdown, tables (2D arrays + CSV) and heading-aware RAG chunks with page anchors from PDFs. URLs, base64 upload, key-value store, password-protected PDFs, page ranges, OCR fallback (eng/deu/fra/spa) only for pages without a text layer. Failed PDFs are never charged.", "version": "0.1", "x-build-id": "R3mFokhcW3rc8zaCm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nanare-sudo~pdf-text-extractor-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nanare-sudo-pdf-text-extractor-rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nanare-sudo~pdf-text-extractor-rag/runs": { "post": { "operationId": "runs-sync-nanare-sudo-pdf-text-extractor-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nanare-sudo~pdf-text-extractor-rag/run-sync": { "post": { "operationId": "run-sync-nanare-sudo-pdf-text-extractor-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "extract", "info", "canary" ], "type": "string", "description": "`extract` = full extraction (charged per processed PDF + per OCR page). `info` = free probe: page count, metadata, encryption status, which pages have a text layer and an OCR-cost estimate — run this first on unknown PDFs. `canary` = free health self-test of the whole pipeline (download, parser, tables, OCR engine).", "default": "extract" }, "urls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files, e.g. `https://arxiv.org/pdf/1706.03762`. Redirects are followed. Combine freely with `base64Files` and `keyValueStoreKeys`.", "default": [], "items": { "type": "string" } }, "base64Files": { "title": "Base64 files", "type": "array", "description": "Inline PDF uploads as objects `{\"name\": \"report.pdf\", \"data\": \"\"}`. `data` may be a raw base64 string or a `data:application/pdf;base64,...` URI. Ideal for API and AI-agent callers that hold the file in memory.", "default": [] }, "keyValueStoreKeys": { "title": "Key-value store keys", "type": "array", "description": "Keys of PDF records in this run's default key-value store (upload the file first via the Apify API or console, then pass its key here).", "default": [], "items": { "type": "string" } }, "password": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs. Applied to every input file that is encrypted; files that fail to decrypt are reported as `failed` and are not charged." }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to extract, 1-based, e.g. `1-5,8,12-` (12- means page 12 to the end). Empty = all pages." }, "maxPdfMb": { "title": "Max PDF size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "PDFs larger than this are rejected (status `failed`, not charged).", "default": 50 }, "maxOcrPages": { "title": "Max OCR pages per run", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Hard cap on OCR-processed pages across the whole run (OCR is the only per-page charge). Set 0 to disable OCR entirely.", "default": 100 }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Tesseract language packs to use for scanned pages. Available in this actor: `eng`, `deu`, `fra`, `spa`. Multiple languages are combined (e.g. eng+deu).", "default": [ "eng" ], "items": { "type": "string" } }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which representations to include in each result item: `text` (plain text), `markdown` (GitHub-flavored, incl. pipe tables), `tables` (2D arrays + CSV strings + page numbers), `chunks` (heading-aware RAG chunks with headingPath and page anchors). Fewer formats = smaller items, same price.", "items": { "type": "string", "enum": [ "text", "markdown", "tables", "chunks" ], "enumTitles": [ "Plain text", "Markdown (GFM)", "Tables (2D + CSV)", "RAG chunks" ] }, "default": [ "text", "markdown", "tables", "chunks" ] }, "chunkTokens": { "title": "Chunk size (tokens)", "minimum": 100, "maximum": 8000, "type": "integer", "description": "Approximate target size of each RAG chunk in tokens (estimated at ~4 characters per token). Chunks break at headings when possible and always carry `headingPath`, `pageStart`, `pageEnd`.", "default": 800 } } }, "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 } } } } } } } } } }