phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 02:32:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add comment about why ps vs list

Browse source
This commit is contained in:
Matthew Farrellee 2025-04-01 15:21:20 -04:00
parent 4e81b1e650
commit a49549063a
1 changed files with 3 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -293,6 +293,9 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
if model.model_type == ModelType.embedding: if model.model_type == ModelType.embedding:
logger.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...") logger.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
await self.client.pull(model.provider_resource_id) await self.client.pull(model.provider_resource_id)
# we use list() here instead of ps() -
# - ps() only lists running models, not available models
# - models not currently running are run by the ollama server as needed
response = await self.client.list() response = await self.client.list()
available_models = [m["model"] for m in response["models"]] available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models: if model.provider_resource_id not in available_models: