phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix(ollama): register model with the helper first so it gets normalized

Browse source
This commit is contained in:
Ashwin Bharambe 2025-02-21 12:51:38 -08:00
parent 0fe071764f
commit 36162c8c82
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -280,6 +280,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
return EmbeddingsResponse(embeddings=embeddings)
async def register_model(self, model: Model) -> Model:
model = await self.register_helper.register_model(model)
if model.model_type == ModelType.embedding:
log.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
await self.client.pull(model.provider_resource_id)
@ -292,7 +293,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
f"Model '{model.provider_resource_id}' is not available in Ollama. Available models: {', '.join(available_models)}"
)
return await self.register_helper.register_model(model)
return model
async def convert_message_to_openai_dict_for_ollama(message: Message) -> List[dict]: