OpenWebUI demo changes (#3740)

### 🛠 Summary
[CVS-175208](https://jira.devtools.intel.com/browse/CVS-175208)
Adding windows commands for demo, using OV models instead of external,
changes in agentic usecase.

[Preview]https://openvino-doc.iotg.sclab.intel.com/preview/model-server/ovms_demos_integration_with_open_webui.html

### 🧪 Checklist

- [ ] Unit tests added.
- [ ] The documentation updated.
- [ ] Change follows security best practices.
``

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Author: przepeck

demos/audio/README.md

@@ -11,7 +11,7 @@ Check supported [Speech Recognition Models](https://openvinotoolkit.github.io/op
 
 **Model preparation**: Python 3.10 or higher with pip
 
-**Model Server deployment**: Installed Docker Engine or OVMS binary package according to the [baremetal deployment guide](../../../docs/deploying_server_baremetal.md)
+**Model Server deployment**: Installed Docker Engine or OVMS binary package according to the [baremetal deployment guide](../../docs/deploying_server_baremetal.md)
 
 **Client**: curl or Python for using OpenAI client package