fix: improve import error messages for LLM client dependencies (#4605)

[cwarre33]

Add try-except blocks to model client init.py files (OpenAI, Anthropic, Azure, Ollama) to provide clear, actionable error messages when required dependencies are missing.

This improvement helps users quickly identify and install missing packages instead of encountering generic ImportError messages.

Changes:

• Wrap imports in try-except blocks for all main LLM client modules
• Include specific installation instructions (e.g., pip install autogen-ext[openai])
• Preserve original error context with 'raise ... from e' for debugging
• Consistent error message format across all client implementations

Fixes #4605

Why are these changes needed?

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[cwarre33]

@microsoft-github-policy-service agree