phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-29 03:14:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: consolidate most distros into "starter"

Browse source 
* Removes a bunch of distros
* Removed distros were added into the "starter" distribution
* Doc for "starter" has been added
* Partially reverts https://github.com/meta-llama/llama-stack/pull/2482
  since inference providers are disabled by default and can be turned on
  manually via env variable.
* Disables safety in starter distro

Closes: #2502
Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-06-25 16:09:41 +02:00
parent 0ddb293d77
commit bedfea38c3
No known key found for this signature in database
127 changed files with 758 additions and 10771 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -91,7 +91,6 @@ class OllamaInferenceAdapter(
def __init__(self, config: OllamaImplConfig) -> None:
self.register_helper = ModelRegistryHelper(MODEL_ENTRIES)
self.url = config.url
self.raise_on_connect_error = config.raise_on_connect_error
@property
def client(self) -> AsyncClient:
@ -105,10 +104,7 @@ class OllamaInferenceAdapter(
logger.debug(f"checking connectivity to Ollama at `{self.url}`...")
health_response = await self.health()
if health_response["status"] == HealthStatus.ERROR:
if self.raise_on_connect_error:
raise RuntimeError("Ollama Server is not running, start it using `ollama serve` in a separate terminal")
else:
logger.warning("Ollama Server is not running, start it using `ollama serve` in a separate terminal")
raise RuntimeError("Ollama Server is not running, start it using `ollama serve` in a separate terminal")
async def health(self) -> HealthResponse:
"""