mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
7cb5d3c60f
# What does this PR do? - llama_stack/exceptions.py: Add UnsupportedModelError class - remote inference ollama.py and utils/inference/model_registry.py: Changed ValueError in favor of UnsupportedModelError - utils/inference/litellm_openai_mixin.py: remove `register_model` function implementation from `LiteLLMOpenAIMixin` class. Now uses the parent class `ModelRegistryHelper`'s function implementation Closes #2517 ## Test Plan 1. Create a new `test_run_openai.yaml` and paste the following config in it: ```yaml version: '2' image_name: test-image apis: - inference providers: inference: - provider_id: openai provider_type: remote::openai config: max_tokens: 8192 models: - metadata: {} model_id: "non-existent-model" provider_id: openai model_type: llm server: port: 8321 ``` And run the server with: ```bash uv run llama stack run test_run_openai.yaml ``` You should now get a `llama_stack.exceptions.UnsupportedModelError` with the supported list of models in the error message. --- Tested for the following remote inference providers, and they all raise the `UnsupportedModelError`: - Anthropic - Cerebras - Fireworks - Gemini - Groq - Ollama - OpenAI - SambaNova - Together - Watsonx --------- Co-authored-by: Rohan Awhad <rawhad@redhat.com>
13 lines
545 B
Python
13 lines
545 B
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
|
|
class UnsupportedModelError(ValueError):
|
|
"""raised when model is not present in the list of supported models"""
|
|
|
|
def __init__(self, model_name: str, supported_models_list: list[str]):
|
|
message = f"'{model_name}' model is not supported. Supported models are: {', '.join(supported_models_list)}"
|
|
super().__init__(message)
|