Python: Add Deepseek service to concept samples

[TaoChenOSU]

Motivation and Context

Models from DeepSeek are rising fast as one of the most capable and cost-effective open-source models. The community will be eager to test these models out.

Description

It's not hard to use these new models as they are compatible with the OpenAI API. This PR simply adds an option where people can test out the DeepSeek models in the chat concept samples.

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[moonbox3]

I imagine devs would want to use their reasoning model, as well? This model produces reasoning_content that we don't support:

reasoning_content = response.choices[0].message.reasoning_content

https://api-docs.deepseek.com/guides/reasoning_model

[TaoChenOSU]

I imagine devs would want to use their reasoning model, as well? This model produces reasoning_content that we don't support:

reasoning_content = response.choices[0].message.reasoning_content

https://api-docs.deepseek.com/guides/reasoning_model

We still expose it in the inner content of the chat message.