---
title: "Xberg.io - Air Market"
description: "Xberg.io publishes 6 listings on Air Market. Polyglot document intelligence with a Rust core - extract structured data from 97+ formats"
canonical: "https://airmarket.ai/@xberg-io"
---

[Air Market](/) / [Creators](/creators) / Xberg.io

Creator

# Xberg.io

Polyglot document intelligence with a Rust core - extract structured data from 97+ formats

**Xberg.io on Air Market**

|  |  |
| --- | --- |
| Listings | 6 |
| GitHub | [xberg-io](https://github.com/xberg-io) |

**Published listings, with what each one does**

| Listing | Kind | What it does |
| --- | --- | --- |
| [Extracting tables](/app/extracting-tables) | Skill | There is a table inside a PDF, spreadsheet, or picture and you need the data, not the picture. This covers finding tables on the page and g… |
| [Chunking](/app/chunking) | Skill | You have extracted text that is too long to hand to a model or load into a search index. This covers splitting it into pieces: how big each… |
| [Picking a format](/app/picking-a-format) | Skill | You are extracting a document and there are several formats to choose from, with no obvious reason to prefer one. This matches who is going… |
| [Batch extraction](/app/batch-extraction) | Skill | You have a lot of files to pull text out of and running them one at a time is not practical. This covers doing the whole set in one go with… |
| [Extracting keywords, language, and embeddings](/app/extracting-keywords) | Skill | You want to know what a document is about without reading all of it, or you need it indexed for search. This covers pulling keywords out, a… |
| [Extracting with OCR](/app/extracting-with-ocr) | Skill | The PDF you have is a scan, or the page is a photo, so there is no text inside it to copy. This covers reading the text off the image, choo… |

## Links

- [xberg.io](https://xberg.io/)
- [X](https://x.com/kreuzberg_dev)
- [GitHub](https://github.com/xberg-io)

---

Canonical URL: <https://airmarket.ai/@xberg-io>