# June 2023 release

## 👀 Composites and enrichments in table format

<figure><img src="/files/0CtesKCWWvGVFojHJgfR" alt=""><figcaption></figcaption></figure>

We've listened to your feedback and are pleased to introduce a much-requested feature: the ability to view line items and their enrichments in an easy-to-read table format. In the annotations section, you'll now find a new table view option. What's more, we've added a bonus feature that allows you to customize the order of columns and choose which entities and enrichments you want to display in the table format. To access this experimental feature, kindly reach out to your IT administrator.

{% content-ref url="/pages/BNtSQqr40Dd28gCWgIQn" %}
[Documents](/project/production/documents.md)
{% endcontent-ref %}

<figure><img src="/files/3H5ZHjH1TuBprRZfYg1j" alt=""><figcaption></figcaption></figure>

## 🐲 Hydra model

<figure><img src="/files/2DnULP7VQf2txIRcfmFc" alt=""><figcaption></figcaption></figure>

One of the key advantages of an Adaptive IDP platform is its ability to train a single model using data from various sources or projects, even when those projects have different entity extraction requirements. To enhance the shared model experience, the Metamaze machine learning team has introduced a new model architecture called Hydra! This advanced architecture surpasses its predecessor in handling partially annotated data, which is commonly encountered when sharing models across projects with varying entity extraction requirements&#x20;

Key takeaways:&#x20;

* Train one model based on different sets of entities, with data from different projects&#x20;
* No need to relabel existing training data when adding/removing entities&#x20;
* Up to 20% higher Straight Through Processing Rate&#x20;
* Up to 9% higher F1 score&#x20;
* Up to 18% less false positives&#x20;
* No actions needed, we take care of everything 🤗&#x20;

Check out the full blog post [here](https://metamaze.eu/hydra-model-architecture/).

<figure><img src="/files/3H5ZHjH1TuBprRZfYg1j" alt=""><figcaption></figcaption></figure>

## 🖹 Excel file support

To further streamline your workflow, we've added support for Excel documents. With this new update, you can now effortlessly process your tabular data within the Metamaze platform.

{% content-ref url="/pages/-MCC\_qqBdtTyWcA7D0tY" %}
[Uploading data](/getting-started/processing-documents/input-of-files.md)
{% endcontent-ref %}

<figure><img src="/files/3H5ZHjH1TuBprRZfYg1j" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs-old.app.metamaze.eu/release-notes/release-archive/release-archive-2023/june-2023-release.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.