Support for Phi4 from Ollama

[pafend]

Important

Add support for OLLAMA_PHI4 model in LLMModels enum and get_model_info() in _utils.py.

• Models:
  • Add OLLAMA_PHI4 to LLMModels enum in _utils.py.
  • Update get_model_info() in _utils.py to include OLLAMA_PHI4 with constraints: max_tokens=4096, max_temperature=2.0.

^{This description was created by for ebd6eb8. It will automatically update as commits are pushed.}

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to ebd6eb8 in 12 seconds

More details

• Looked at 25 lines of code in 1 files
• Skipped 0 files when reviewing.
• Skipped posting 1 drafted comments based on config settings.

1. backend/app/nodes/llm/_utils.py:97

• Draft comment:
  The addition of the OLLAMA_PHI4 model is consistent with the existing pattern for adding models. Ensure that the max_tokens value of 4096 is correct for this model.
• Reason this comment was not posted:
  Confidence changes required: 33%
  The addition of the new model 'OLLAMA_PHI4' seems consistent with the existing pattern for adding models. However, the max_tokens value for this model is set to 4096, which is consistent with other Ollama models, so it seems correct.

Workflow ID: wflow_LJVgWgPcHcIrSrJL

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[JeanKaddour]

Thank you @pafend !