Update lightrag_azure_openai_demo.py

[Hammton]

Description

[Briefly describe the changes made in this pull request.]

Related Issues

[Reference any related issues or tasks addressed by this pull request.]

Changes Made

[List the specific changes made in this pull request.]

Checklist

• Changes tested locally
• Code reviewed
• Documentation updated (if necessary)
• Unit tests added (if applicable)

Additional Notes

[Add any additional notes or context for the reviewer(s).]

[danielaskdd]

Thanks for your interest in the LightRAG. We welcome your contributions to the community. Below are a few improvement suggestions for your PR:

1. Please ensure that WORKING_DIR remains set to "./dickens" and avoid using Windows-style path syntax—Python inherently handles cross-platform path compatibility.
2. The demo code should not directly import AzureOpenAI. Instead, use the azure_openai_complete_if_cache function from the llm/azure_openai.py module. If there are issues in azure_openai.py, please resolve them before submitting the PR.
3. Adhere to LightRAG’s environment variable conventions: when LLM_BINDING=azure_openai, the variables LLM_MODEL, LLM_BINDING_HOST, and LLM_BINDING_API_KEY should take precedence over AZURE_OPENAI_DEPLOYMENT, AZURE_OPENAI_ENDPOINT, and AZURE_OPENAI_API_KEY.