> For the complete documentation index, see [llms.txt](https://operations.clausebase.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://operations.clausebase.com/updates-november-2024/9-november-2024.md).

# 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&amp;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&amp;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;


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://operations.clausebase.com/updates-november-2024/9-november-2024.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.