{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor - Citable Pages & RAG Chunks", "description": "Extract PDF text as original-numbered pages with document hashes, exact-offset RAG chunks and explicit coverage. Public HTTPS or base64 input. No OCR. Pay only for delivered nonempty pages.", "version": "0.1", "x-build-id": "WXeCgH2i0PrcV1ysD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/natstandridge~pdf-page-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-natstandridge-pdf-page-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/natstandridge~pdf-page-text-extractor/runs": { "post": { "operationId": "runs-sync-natstandridge-pdf-page-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/natstandridge~pdf-page-text-extractor/run-sync": { "post": { "operationId": "run-sync-natstandridge-pdf-page-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Public HTTPS PDF URLs", "maxItems": 10, "type": "array", "description": "Public direct PDF URLs, without credentials, signed query parameters or fragments. Robots rules apply. Up to 10 documents total across urls and pdfs; 10 MiB per download. URLs are processed before inline PDFs.", "items": { "type": "string", "maxLength": 2048 } }, "pdfs": { "title": "Caller-provided base64 PDFs", "maxItems": 10, "type": "array", "description": "Optional inline PDFs you may process. Each entry has name and strict base64 (no data URL prefix). At most 4 MiB total decoded inline bytes; up to 10 documents including URLs. No password or decryption support.", "items": { "type": "object", "additionalProperties": false, "required": [ "name", "base64" ], "properties": { "name": { "type": "string", "title": "PDF name", "description": "Display name only; never used as a filesystem path.", "minLength": 1, "maxLength": 120 }, "base64": { "type": "string", "title": "Base64 PDF", "description": "Strict base64-encoded PDF bytes, without whitespace or a data-URL prefix.", "minLength": 1, "maxLength": 5592408 } } } }, "startPage": { "title": "First physical page", "minimum": 1, "maximum": 10000, "type": "integer", "description": "One-based physical PDF page number, not a printed label. Applies to every document. Beyond the end is a successful empty selected window, reported in coverage.", "default": 1 }, "maxPagesPerDocument": { "title": "Pages to examine per document", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of physical pages in the selected window, including blank pages. Complete coverage refers to this window, not necessarily the entire PDF.", "default": 50 }, "maxResults": { "title": "Maximum delivered text pages", "minimum": 1, "maximum": 300, "type": "integer", "description": "Overall whole-page result cap. Empty, duplicate, failed and skipped pages are uncharged. Later pages/documents may remain unprocessed when this cap is reached.", "default": 100 }, "chunkChars": { "title": "Characters per chunk", "minimum": 200, "maximum": 4000, "type": "integer", "description": "Maximum Unicode code points per deterministic within-page chunk. Character offsets are zero-based with an exclusive end, not token, byte or UTF-16 offsets.", "default": 1200 }, "chunkOverlap": { "title": "Overlap characters", "minimum": 0, "maximum": 500, "type": "integer", "description": "Repeated Unicode code points between adjacent chunks. Must be less than half chunkChars. Chunks never cross page boundaries.", "default": 100 }, "maxRunSeconds": { "title": "Work time limit", "minimum": 30, "maximum": 240, "type": "integer", "description": "Collection and delivery limit; reserves 25 seconds for result delivery. Each download has a 25-second hard limit and each PDF parser a 20-second hard limit. Platform timeout should be at least 300 seconds.", "default": 120 } } }, "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 } } } } } } } } } }