Fix the model name initialization for LLMs that use the model kwarg.

Vikaslakkacs · Jul 12, 2023 · ee701ae · ee701ae
1 parent 9204cf6
commit ee701ae
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [#58](https://github.com/NVIDIA/NeMo-Guardrails/issues/58): Fix install on Mac OS 13.
 - [#55](https://github.com/NVIDIA/NeMo-Guardrails/issues/55): Fix bug in example causing config.py to crash on computers with no CUDA-enabled GPUs.
+- Fixed the model name initialization for LLMs that use the `model` kwarg.
 
 
 ## [0.3.0] - 2023-06-30

diff --git a/nemoguardrails/rails/llm/llmrails.py b/nemoguardrails/rails/llm/llmrails.py
@@ -133,7 +133,8 @@ def _init_llm(self):
  ]:
  kwargs["model_name"] = main_llm_config.model
  else:
- if hasattr(provider_cls, "model"):
+ # The `__fields__` attribute is computed dynamically by pydantic.
+ if "model" in provider_cls.__fields__:
  kwargs["model"] = main_llm_config.model
 
  self.llm = provider_cls(**kwargs)