phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 01:09:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-watsonx-inference-adapter

Browse source
This commit is contained in:
Sajikumar JS 2025-04-10 10:17:08 +05:30
commit 47d919333a
59 changed files with 10982 additions and 94 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -307,9 +307,10 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
if model.model_type == ModelType.embedding:
logger.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
await self.client.pull(model.provider_resource_id)
response = await self.client.list()
else:
response = await self.client.ps()
# 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()
available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models:
raise ValueError(