We're now using this validator for more than just `TopP`, and a new name is in order.

These tests should work and do work locally. But they fail in GitHub CI – for an unknown reason that almost certainly is in Ollama, not in our code.

Add min-p sampling for `ollamaChat`

Co-authored-by: MiriamScharnke <mscharnk@mathworks.com>

…story

Special error message for removing from empty history

`openAIChat.generate` needs to use the given `openAIChat`'s model as the default, not a static `gpt-4o-mini"`.

Fixes #80.

Use correct `ModelName` default

Adding support for [⁠the new o1-preview and o1-mini models](https://openai.com/index/introducing-openai-o1-preview/).

Note that these two no longer support the name we translate our `MaxNumTokens` into. Fortunately, the new name does get accepted in the older models, too.

```
================================================================================
Error occurred in topenAIChat/canUseModel(ModelName=o1-preview) and it did not run to completion.
    ---------
    Error ID:
    ---------
    'llms:apiReturnedError'
    --------------
    Error Details:
    --------------
    Error using openAIChat/generate (line 259)
    Server returned error indicating: "Unsupported parameter: 'max_tokens' is not supported with this model. Use
    'max_completion_tokens' instead."

    Error in topenAIChat/canUseModel (line 100)
                testCase.verifyClass(generate(openAIChat(ModelName=ModelName),"hi",MaxNumTokens=1),"string");
================================================================================
```

* Documentation: Reference Pages

We have added a new directory `functions` to the `doc` directory. The `functions` folder contains documentation for these functions and objects:
- openAIChat
- azureChat
- ollamaChat
- generate
- openAIFunction
- addParameter
- openAIImages
- openAIImages.generate
- edit
- createVariation
- messageHistory
- addSystemMessage
- addUserMessage
- addUserMessageWithImages
- addToolMessage
- addResponseMessage
- removeMessage