{ "openapi": "3.0.1", "info": { "title": "DOCX to Text & Markdown Converter", "description": "Convert Word .docx files to Markdown, plain text, HTML or JSON, with tables as rows, images, properties and RAG chunks. Use when you need Word content as text.", "version": "0.0", "x-build-id": "ptixHp6761hXjlFSg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plainpipe~docx-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plainpipe-docx-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/plainpipe~docx-to-text/runs": { "post": { "operationId": "runs-sync-plainpipe-docx-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/plainpipe~docx-to-text/run-sync": { "post": { "operationId": "run-sync-plainpipe-docx-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "docxUrls": { "title": "DOCX URLs", "type": "array", "description": "Direct links to Word .docx files, one per line. Dropbox share links ending in ?dl=0 are fixed automatically. Example: https://raw.githubusercontent.com/python-openxml/python-docx/master/tests/test_files/test.docx. Old .doc files are detected and skipped with a hint to save them as .docx.", "items": { "type": "string" } }, "docxFile": { "title": "Upload a DOCX (optional)", "type": "string", "description": "Or upload one .docx file instead of (or in addition to) the links above, up to 50 MB. Leave empty when you only use DOCX URLs. Example: policy.docx." }, "datasetId": { "title": "Dataset ID (batch input)", "type": "string", "description": "Optional. ID or name of an Apify dataset whose items hold .docx links, for example the output of another Actor. Every item's \"Dataset URL field\" is read. Example: aBcD1234efGh5678." }, "datasetUrlField": { "title": "Dataset URL field", "type": "string", "description": "Field of each dataset item that holds the link (dot path for nested fields; a list of links also works). Default: url. Example: file.url.", "default": "url" }, "keyValueStoreId": { "title": "Key-value store ID (batch input)", "type": "string", "description": "Optional. ID or name of an Apify key-value store that holds .docx files as records. Records whose key ends in .docx are converted; if none do, every record is tried. Example: my-word-files." }, "keyValueStoreKeys": { "title": "Key-value store keys", "type": "array", "description": "Optional. Only convert these record keys from the key-value store above. Leave empty to pick the records automatically. Example: [\"contract.docx\", \"offer.docx\"].", "items": { "type": "string" } }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which versions of the content each row gets: markdown (headings, lists, links, tables), text (plain text), html (mammoth HTML, whole documents only) and structure (JSON list of blocks: heading/paragraph/list/table/footnote). Default: [\"markdown\", \"text\"].", "items": { "type": "string", "enum": [ "markdown", "text", "html", "structure" ], "enumTitles": [ "Markdown", "Plain text", "HTML", "JSON block structure" ] }, "default": [ "markdown", "text" ] }, "extractTables": { "title": "Tables as structured rows", "type": "boolean", "description": "Add a tables field with every Word table as rows of cell text (array of arrays; merged cells padded so columns line up). Default: true.", "default": true }, "extractImages": { "title": "Save images", "type": "boolean", "description": "Save every embedded picture to the run's key-value store and link it from the Markdown as ![alt](link). The first row of each document lists them in images (key, link, type, size). Default: false.", "default": false }, "includeMetadata": { "title": "Document properties", "type": "boolean", "description": "Add a metadata field from the file's own properties: title, subject, keywords, description, author, language, created and modified dates, revision, saved page and word counts, application. Off by default because author is a property of the document; turn on only if you need it. Default: false.", "default": false }, "includeHeadersFooters": { "title": "Headers and footers", "type": "boolean", "description": "Add headers and footers fields with the distinct text of the page headers and footers. Default: false.", "default": false }, "includeFootnotes": { "title": "Footnotes and endnotes", "type": "boolean", "description": "Keep footnotes and endnotes: references become [^1] in Markdown and [1] in text, with the notes listed at the end. Turn off to drop them. Default: true.", "default": true }, "includeComments": { "title": "Review comments", "type": "boolean", "description": "Add a comments field with the text of each Word review comment and the passage it refers to (quotedText). Comment authors are never output. Default: false.", "default": false }, "splitBy": { "title": "Split each document", "enum": [ "document", "heading", "page" ], "type": "string", "description": "document = one row per file (default). heading = one row per section, cut at Heading 1-3, with section and headingPath. page = one row per page, using the page breaks Word stored in the file (manual breaks and the layout of the last save).", "default": "document" }, "chunkWords": { "title": "Chunk size (words)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "0 = off (default). When set, each document (or section/page) is split into chunks of about this many words, cut between paragraphs and never right after a heading, one row per chunk with chunkIndex and headingPath. Each chunk is one billed result. Example: 300 for RAG embeddings.", "default": 0 }, "maxItems": { "title": "Max results", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many rows in total (documents, or sections/pages/chunks when splitting). You are charged per row. Default 100. Example: 10.", "default": 100 } } }, "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 } } } } } } } } } }