Refactor: reintroduce LLM_MODEL Env Variable for Flexible Model Implementation in chatqna-xeon-ui-server

[jotpalch]

Description

This update reintroduces the environment variable LLM_MODEL to the chatqna-xeon-ui-server, enabling flexible model implementation.

• GenAIExamples/ChatQnA/ui/svelte/src/lib/network/chat/Network.ts

  Line 19 in df7c192

  const MODEL_ID = env.MODEL_ID;

Issues

When attempting to use a model other than Intel/neural-chat-7b-v3-3, the request header from the UI service to the backend still contains the fixed model identifier 'model': 'Intel/neural-chat-7b-v3-3', causing issues with model flexibility.

Screenshot:

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

List the newly introduced 3rd party dependency if exists.

Tests

Describe the tests that you ran to verify your changes.

[github-actions]

Dependency Review

✅ No vulnerabilities or license issues found.

Scanned Files