Merge pull request #355 from tisnik/lcore-336-bump-up-llama-stack-to-0.2.17

LCORE-336: bump-up Llama Stack to 0.2.17

Author: tisnik

pyproject.toml

@@ -25,8 +25,8 @@ dependencies = [
     "fastapi>=0.115.6",
     "uvicorn>=0.34.3",
     "kubernetes>=30.1.0",
-    "llama-stack==0.2.16",
-    "llama-stack-client==0.2.16",
+    "llama-stack==0.2.17",
+    "llama-stack-client==0.2.17",
     "rich>=14.0.0",
     "cachetools>=6.1.0",
     "prometheus-client>=0.22.1",

src/client.py

@@ -4,7 +4,7 @@
 
 from typing import Optional
 
-from llama_stack.distribution.library_client import (
+from llama_stack import (
     AsyncLlamaStackAsLibraryClient,  # type: ignore
     LlamaStackAsLibraryClient,  # type: ignore
 )

src/utils/common.py

@@ -6,7 +6,7 @@
 from logging import Logger
 
 from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient
-from llama_stack.distribution.library_client import (
+from llama_stack import (
     AsyncLlamaStackAsLibraryClient,
 )
 

test.containerfile

@@ -8,7 +8,6 @@ ENV PATH="$PATH:/root/.local/bin"
 WORKDIR ${APP_ROOT}
 COPY run.yaml ./
 
-
 RUN microdnf install -y --nodocs --setopt=keepcache=0 --setopt=tsflags=nodocs \
     python3.12 python3.12-devel python3.12-pip git tar
 
@@ -17,7 +16,7 @@ RUN curl -LsSf https://astral.sh/uv/install.sh | sh
 RUN uv -h
 
 RUN uv venv && \
-    uv pip install llama-stack==0.2.16 \
+    uv pip install llama-stack==0.2.17 \
     fastapi \
     opentelemetry-sdk \
     opentelemetry-exporter-otlp \
@@ -36,4 +35,4 @@ RUN uv venv && \
     peft \
     trl
 
-CMD ["uv", "run", "llama", "stack", "run", "run.yaml"]
+CMD ["uv", "run", "llama", "stack", "run", "run.yaml"]