Chatlab

Fixed
- Fixed a bug where the final render of a tool call wasn't using the custom render.

Added
- New `tools` namespace to replace the `builtins` namespace.
- Simplified `Palette` class in `colors.py` for displaying color palettes, now leveraging Pydantic for validation.

Changed
- Default model in `Chat` class constructor now uses the `GPT_3_5_TURBO` enum.
- Migrated `run_cell` to `run_python` to avoid naming confusion and deprecated `run_cell`.
- Updated documentation and examples to reflect the new `tools` namespace and usage patterns.
- Removed `__required__` from `extract_model_from_function` in `registry.py` to suppress Pydantic warnings.

Fixed
- Ensured the final tool call result properly updates the UI to reflect the outcome of tool execution.

- Support parallel tool calling by default in `Chat`.
- Legacy support for function calling is available by passing `legacy_function_calling=True` to the `Chat` constructor.
- :new: `incremental_display` decorator (see https://github.com/rgbkrk/chatlab/pull/136) that allows you to stream visualizations to the user as the model fills out function arguments.


- Support tool call format from `FunctionRegistry`. Enables parallel function calling (note: not in `Chat` yet). https://github.com/rgbkrk/chatlab/pull/122

- Drop Noteable builtin
- ⏃ Automatically instantiate pydantic models when they are passed as parameters to a function call

- Support setting a custom `base_url`

python
from chatlab import Chat
chat = Chat(
base_url="http://localhost:8000/v1",
api_key="functionary"
)