phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 02:58:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

reverting ollama changes

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-02-10 20:01:13 -05:00
parent 20ddc987c1
commit 553c1fcee0
1 changed files with 9 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -352,24 +352,20 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
return EmbeddingsResponse(embeddings=embeddings)
async def register_model(self, model: Model) -> Model:
# ollama does not have embedding models running. Check if the model is in list of available models.
if model.model_type == ModelType.embedding:
response = await self.client.list()
async def check_model_availability(model_id: str):
response = await self.client.ps()
available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models:
if model_id not in available_models:
raise ValueError(
f"Model '{model.provider_resource_id}' is not available in Ollama. "
f"Available models: {', '.join(available_models)}"
f"Model '{model_id}' is not available in Ollama. Available models: {', '.join(available_models)}"
)
if model.model_type == ModelType.embedding:
await check_model_availability(model.provider_resource_id)
return model
model = await self.register_helper.register_model(model)
models = await self.client.ps()
available_models = [m["model"] for m in models["models"]]
if model.provider_resource_id not in available_models:
raise ValueError(
f"Model '{model.provider_resource_id}' is not available in Ollama. "
f"Available models: [{', '.join(available_models)}]"
)
await check_model_availability(model.provider_resource_id)
return model