phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 09:21:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: allow ollama to use 'latest' if available but not specified

Browse source 
ollama's CLI supports running models via commands such as 'ollama run llama3.2'
this syntax does not work with the INFERENCE_MODEL llamastack var as currently
specifying a tag such as 'latest' is required

this commit will check to see if the 'latest' model is available and use that
model if a user passes a model name without a tag but the 'latest' is available
in ollama

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
This commit is contained in:
Nathan Weinberg 2025-04-08 15:56:19 -04:00
parent 2fcb70b789
commit 0e5574cf9d
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -313,6 +313,12 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
response = await self.client.list()
available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models:
available_models_latest = [m["model"].split(":latest")[0] for m in response["models"]]
if model.provider_resource_id in available_models_latest:
logger.warning(
f"Imprecise provider resource id was used but 'latest' is available in Ollama - using '{model.provider_resource_id}:latest'"
)
return model
raise ValueError(
f"Model '{model.provider_resource_id}' is not available in Ollama. Available models: {', '.join(available_models)}"
)