odtparser

Parse ODT (OpenDocument Text) files to markdown or text. Powered by LlamaParse v2. Zero dependencies, Node 18+.

Handles .odt, .ott, .odp, .ods, and other OpenDocument formats out of the box — plus PDF, DOCX, PPTX, XLSX, and other common formats.

Install

npm install odtparser

Quick Start

Set your API key:

export LLAMA_CLOUD_API_KEY=llx-...

Parse an ODT file:

import { parse } from "odtparser";

const result = await parse("./document.odt");
console.log(result.markdown);

Advanced Usage

import { ODTParser } from "odtparser";

const parser = new ODTParser({ apiKey: "llx-..." });

// Parse an ODT file with options
const result = await parser.parse("./report.odt", {
  tier: "agentic",
  processing_options: { language: "fr" },
});

// Parse a buffer (e.g. from an upload)
const buffer = fs.readFileSync("./document.odt");
const result = await parser.parse(buffer, {
  fileName: "document.odt",
});

Supported Formats

| Extension | Format | |-----------|--------| | .odt | OpenDocument Text | | .ott | OpenDocument Text Template | | .odp | OpenDocument Presentation | | .otp | OpenDocument Presentation Template | | .ods | OpenDocument Spreadsheet | | .ots | OpenDocument Spreadsheet Template | | .odg | OpenDocument Graphics | | .pdf | PDF | | .docx / .doc | Microsoft Word | | .pptx / .ppt | Microsoft PowerPoint | | .xlsx / .xls | Microsoft Excel | | .html | HTML | | .csv | CSV | | .txt | Plain text | | .png / .jpg / .tiff / .bmp / .webp / .gif | Images (OCR) |

API

parse(input, options?)

Uploads a document, waits for parsing to complete, and returns the result.

Input: file path (string) or file contents (Buffer | Uint8Array)

Options:

| Option | Type | Default | Description | |--------|------|---------|-------------| | tier | string | "fast" | Parsing tier: fast, cost_effective, agentic, agentic_plus | | version | string | "latest" | API version | | apiKey | string | env var | Override API key | | expand | string[] | ["markdown_full", "text_full"] | Fields to expand | | pollIntervalMs | number | 1000 | Polling interval in ms | | timeoutMs | number | 300000 | Max wait time in ms | | fileName | string | "document.odt" | Filename hint for buffer input | | mimeType | string | auto-detected | MIME type for buffer input | | signal | AbortSignal | — | Cancellation signal | | processing_options | object | — | LlamaParse processing options (language, disable_ocr, etc.) | | agentic_options | object | — | Agentic options (custom_prompt) | | page_ranges | object | — | Page range options (max_pages, target_pages) | | disable_cache | boolean | — | Disable document caching |

Returns: ParseResult

interface ParseResult {
  markdown: string;     // Full markdown output
  text: string;         // Full text output
  job: JobResponse;     // Job metadata (id, status, etc.)
  _raw: object;         // Raw API response
}

new ODTParser(config?)

Create an instance with explicit configuration.

| Option | Type | Default | Description | |--------|------|---------|-------------| | apiKey | string | LLAMA_CLOUD_API_KEY | API key | | baseUrl | string | https://api.cloud.llamaindex.ai | API base URL |

License

MIT