sxipresentationparser
v1.0.0
Published
Simple SXI (StarOffice/OpenOffice Impress) presentation parser powered by LlamaParse v2
Maintainers
Readme
sxipresentationparser
Parse SXI (StarOffice/OpenOffice Impress) presentation files to markdown or text. Powered by LlamaParse v2. Zero dependencies, Node 18+.
Handles .sxi files out of the box — plus .odp, .pptx, .ppt, .pdf, and image formats.
Install
npm install sxipresentationparserQuick Start
Set your API key:
export LLAMA_CLOUD_API_KEY=llx-...Parse an SXI presentation:
import { parse } from "sxipresentationparser";
const result = await parse("./presentation.sxi");
console.log(result.markdown);Advanced Usage
import { SXIPresentationParser } from "sxipresentationparser";
const parser = new SXIPresentationParser({ apiKey: "llx-..." });
// Parse an SXI presentation with options
const result = await parser.parse("./slides.sxi", {
tier: "agentic",
processing_options: { language: "fr" },
});
// Parse a buffer (e.g. from an upload)
const buffer = fs.readFileSync("./legacy-slides.sxi");
const result = await parser.parse(buffer, {
fileName: "legacy-slides.sxi",
});Supported Formats
| Extension | Format |
|-----------|--------|
| .sxi | StarOffice/OpenOffice Impress Presentation |
| .sxd | StarOffice/OpenOffice Draw |
| .odp | OpenDocument Presentation |
| .pptx / .ppt | Microsoft PowerPoint |
| .pdf | PDF |
| .png / .jpg / .tiff / .bmp / .webp / .gif | Images (OCR) |
API
parse(input, options?)
Uploads a presentation, 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 | "presentation.sxi" | 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 SXIPresentationParser(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
