{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: PDF to Text & Markdown, RAG Chunks", "description": "PDF text extractor: PDF URLs or uploads to clean text and markdown, page markers, RAG chunks. $2.50 per 1,000 PDFs. Text PDFs only; scans free.", "version": "0.1", "x-build-id": "T6rufh6xknVf8V8KM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ataism~pdf-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ataism-pdf-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ataism~pdf-to-text/runs": { "post": { "operationId": "runs-sync-ataism-pdf-to-text", "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/ataism~pdf-to-text/run-sync": { "post": { "operationId": "run-sync-ataism-pdf-to-text", "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": "Direct http(s) links to PDF files, one per line. Private, local and internal addresses are blocked. To use a file from your computer, upload it with the next field, or save it to a key-value store and paste its record URL here.", "default": [ "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf" ], "items": { "type": "string" } }, "pdfFiles": { "title": "Uploaded PDF files", "type": "array", "description": "Upload PDFs from your computer to a key-value store of your choice (the editor offers this), or paste a record URL. The Actor reads each file once and stores nothing." }, "pageRange": { "title": "Page range", "type": "string", "description": "Only these pages, e.g. \"1-5,8\" or \"3-\" (page 3 to the end). Leave empty for all pages. Applies to every PDF." }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "type": "integer", "description": "Only the first N pages of each PDF are converted (after the page range). Default 100, maximum 500: a larger value is lowered to 500 with a warning. Cut documents are marked \"truncated\": true. The price is per PDF, not per page.", "default": 100 }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Adds the \"text\" field.", "default": true }, "includeMarkdown": { "title": "Include markdown", "type": "boolean", "description": "Adds the \"markdown\" field: headings (guessed from font size), bullet lists, page markers () and --- between pages.", "default": true }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "Adds a \"pages\" array with the text of each page. Makes the dataset larger.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Splits the text into chunks of about this many characters for search or RAG, cutting at paragraph, sentence or word boundaries. 0 turns chunks off. Otherwise at least 200.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters repeated at the start of the next chunk. Capped at half the chunk size. Only used when chunk size is above 0.", "default": 100 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are skipped with an error, not charged. Hard cap 100 MB. Several large files at once need more run memory; the Actor lowers concurrency to fit.", "default": 50 }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Per file, including redirects.", "default": 60 }, "concurrency": { "title": "Parallel PDFs", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many PDFs are processed at once (1 to 5).", "default": 3 }, "mode": { "title": "Mode", "type": "string", "description": "Internal: \"selfTest\" runs the maintainer health check and saves no items.", "default": "run" } } }, "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 } } } } } } } } } }