{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor & Change Monitor", "description": "Extract text, page content, metadata, and RAG-ready chunks from PDFs. Monitor content, page, and metadata changes across runs.", "version": "0.1", "x-build-id": "NyqvTzAMetr2527ja" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/produkdigitalali~pdf-text-extractor-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-produkdigitalali-pdf-text-extractor-change-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/produkdigitalali~pdf-text-extractor-change-monitor/runs": { "post": { "operationId": "runs-sync-produkdigitalali-pdf-text-extractor-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/produkdigitalali~pdf-text-extractor-change-monitor/run-sync": { "post": { "operationId": "run-sync-produkdigitalali-pdf-text-extractor-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "uploadedPdf": { "title": "Upload or select one PDF", "type": "string", "description": "Optional single PDF uploaded to an Apify key-value store or supplied by URL." }, "pdfUrls": { "title": "PDF URLs", "maxItems": 1000, "uniqueItems": true, "type": "array", "description": "Public http(s) PDF URLs to process. Add multiple URLs for batch extraction.", "items": { "type": "string" } }, "documents": { "title": "Advanced document definitions", "type": "array", "description": "Optional JSON objects with url, documentId and label. Use documentId to keep monitoring identity stable when signed/query URLs change.", "default": [] }, "maxDocuments": { "title": "Maximum documents", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of unique PDFs processed in this run.", "default": 100 }, "includeFullText": { "title": "Include full document text", "type": "boolean", "description": "Include normalized text from all text-bearing pages in the result.", "default": true }, "includePageText": { "title": "Include per-page text", "type": "boolean", "description": "Include text, character count and stable text hash for each page.", "default": true }, "includeChunks": { "title": "Create RAG-ready chunks", "type": "boolean", "description": "Create page-aware text chunks with stable chunk IDs and hashes for downstream RAG/vector pipelines.", "default": false }, "chunkSizeCharacters": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 10000, "type": "integer", "description": "Target maximum chunk length when RAG-ready chunks are enabled.", "default": 1800 }, "chunkOverlapCharacters": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Character overlap between adjacent chunks on the same page.", "default": 200 }, "maxChunksPerPdf": { "title": "Maximum chunks per PDF", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Safety cap for generated RAG chunks per document.", "default": 5000 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Optional password for encrypted PDFs. Stored as a secret input." }, "monitorMode": { "title": "Monitoring mode", "type": "boolean", "description": "Compare each successfully processed PDF with persistent state from previous runs using the same monitor key and document identity.", "default": false }, "emitChangesOnly": { "title": "Emit changes only", "type": "boolean", "description": "When monitoring, omit UNCHANGED documents from the default dataset.", "default": false }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Namespace for persistent monitoring state. Keep it unchanged across related runs.", "default": "default" }, "storeTextForDiff": { "title": "Store previous text for line-level diffs", "type": "boolean", "description": "Stores bounded per-page text in persistent monitoring state so changed pages can include added/removed line snippets.", "default": true }, "maxStateCharactersPerPdf": { "title": "Maximum stored monitoring text per PDF", "minimum": 10000, "maximum": 5000000, "type": "integer", "description": "Maximum characters retained per PDF in persistent state for future line-level diffs.", "default": 500000 }, "maxDiffLinesPerPage": { "title": "Maximum diff lines per changed page", "minimum": 1, "maximum": 500, "type": "integer", "description": "Caps added/removed line snippets emitted for each changed page while preserving total line counts.", "default": 50 }, "removeTrackingParams": { "title": "Ignore common tracking parameters in document identity", "type": "boolean", "description": "Removes common utm/fbclid/gclid parameters when deriving stable IDs. The original URL is still downloaded unchanged.", "default": true }, "concurrency": { "title": "Download concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum PDFs downloaded/processed concurrently.", "default": 5 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Per-document download safety limit.", "default": 50 }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Rejects PDFs above this page count to keep runtime predictable.", "default": 2000 }, "maxExtractedCharacters": { "title": "Maximum extracted characters per PDF", "minimum": 1000, "maximum": 20000000, "type": "integer", "description": "Safety cap for extracted text stored per PDF. The result marks textTruncated when reached.", "default": 2000000 }, "requestTimeoutSeconds": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Timeout for downloading each PDF.", "default": 30 }, "maxRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries transient network/429/5xx failures before recording a document failure.", "default": 2 } } }, "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 } } } } } } } } } }