phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

if client.initialize fails, the example should exit (#954)

Browse source 
# What does this PR do?

the example script can gracefully exit if the boolean returned from
initialize is used properly

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-02-04 16:54:21 -05:00 • committed by GitHub
parent 981bb52b59
commit 26aef50bc5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
docs/source/getting_started/index.md
View file

@ -98,6 +98,7 @@ llama-stack-client \
Here is a simple example to perform chat completions using the SDK.
```python
import os
import sys
def create_http_client():
@ -112,7 +113,9 @@ def create_library_client(template="ollama"):
from llama_stack import LlamaStackAsLibraryClient
client = LlamaStackAsLibraryClient(template)
client.initialize()
if not client.initialize():
print("llama stack not built properly")
sys.exit(1)
return client

2
llama_stack/distribution/library_client.py
View file

@ -196,7 +196,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
self.custom_provider_registry = custom_provider_registry
self.provider_data = provider_data
async def initialize(self):
async def initialize(self) -> bool:
try:
self.impls = await construct_stack(self.config, self.custom_provider_registry)
except ModuleNotFoundError as _e: