# 9 November 2024

## Multi-summaries

<mark style="background-color:orange;">New feature</mark> In the *Summaries* module of ClauseBuddy, you can now create "multi-summaries". Those summaries consist of a concatenation of individual summaries, applied together on one document.&#x20;

For example, assume you are a legal counsel who has to provide an overview of every contract for which you sign off, in which you have to list (1) all deadlines mentioned in the clauses; (2) all interest rates; and (3) all partner companies co-signing the agreement. With the help of the multi-summaries tool, you can now perform this in one go, instead of having to run several summaries after each other.&#x20;

<figure><img src="https://1414353930-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fc1g6bv00az2hAVxclF4w%2Fuploads%2FzeEVNRC7uMF1iF3UeWtH%2Fimage.png?alt=media&#x26;token=cd1ab041-7799-4687-95ad-8f979088ae1b" alt="" width="563"><figcaption></figcaption></figure>

## Semantic Search

<mark style="background-color:purple;">Improvement</mark>   The *Semantic Search* part of DocAnswer has been upgraded to make use of the additional intelligence layers we [introduced in October](https://operations.clausebase.com/updates-october-2024/20-october-2024#enhanced-clause-search-intelligence).

Essentially, you can now specify a search query, and DocAnswer will provide a list of all parts of the document that are semantically associated with the search term. For example, when searching for "GPDR" in a license agreement, the software will not only show a definition that literally contains this term, but also a clause that does not mention this term exactly.&#x20;

This semantic search facility is still ideal for situations where MS Word's literal search capabilities fall short — so you should try it when you're quickly searching for something in a long document and your literal search doesn't deliver any results. Unlike the *"Ask Questions"* part of DocAnswer, it does not involve any LLM.

<figure><img src="https://1414353930-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fc1g6bv00az2hAVxclF4w%2Fuploads%2FLeRq1ihc9W3IrTsq9276%2Fimage.png?alt=media&#x26;token=8fff4205-79b7-4d82-9e89-3362ff6d13b4" alt=""><figcaption></figcaption></figure>

## Chunking (API)

<mark style="background-color:orange;">New feature</mark> Our API now provides an endpoint for "chunking" a document, i.e. split it into pieces (usually clauses, but potentially also other types of divisions).&#x20;

This allows for intelligent splitting of documents, which can help to have LLMs analyse your documents.&#x20;

## Rate limitations

&#x20;To protect against programming errors or abuse, Clause9, ClauseBuddy and the API now include automatic rate limitations. When a certain customer or user is over-using the server, an error will thus be generated.&#x20;

In normal situations, you should never encounter these errors — if you do and you are affected by it, please let us know.&#x20;