Upgrade to llama stack 0.6.0

.github/workflows/test-external-providers.yml

@@ -72,7 +72,6 @@ jobs:
           # temporary hack for file writing that should be done by the pip setup script
           # https://github.com/containers/ramalama-stack/issues/53
           mkdir -p ~/.llama/distributions/ramalama/
-          cp -r $GITHUB_WORKSPACE/src/ramalama_stack/providers.d/ ~/.llama/
           cp $GITHUB_WORKSPACE/src/ramalama_stack/ramalama-run.yaml ~/.llama/distributions/ramalama/ramalama-run.yaml
 
       - name: Run 'test-build.sh'

.github/workflows/test-lls-integration.yml

@@ -56,7 +56,6 @@ jobs:
           # temporary hack for file writing that should be done by the pip setup script
           # https://github.com/containers/ramalama-stack/issues/53
           mkdir -p ~/.llama/distributions/ramalama/
-          cp -r $GITHUB_WORKSPACE/src/ramalama_stack/providers.d/ ~/.llama/
           cp $GITHUB_WORKSPACE/src/ramalama_stack/ramalama-run.yaml ~/.llama/distributions/ramalama/ramalama-run.yaml
 
       - name: Run 'test-build.sh'

MANIFEST.in

@@ -1,2 +1 @@
-recursive-include ramalama_stack/providers.d *
 include ramalama_stack/ramalama-run.yaml

README.md

@@ -17,7 +17,6 @@ This will install Llama Stack and RamaLama as well if they are not installed alr
 > [!WARNING]
 > The following workaround is currently needed to run this provider - see https://github.com/containers/ramalama-stack/issues/53 for more details
 > ```bash
-> curl --create-dirs --output ~/.llama/providers.d/remote/inference/ramalama.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v0.2.5/src/ramalama_stack/providers.d/remote/inference/ramalama.yaml
 > curl --create-dirs --output ~/.llama/distributions/ramalama/ramalama-run.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v0.2.5/src/ramalama_stack/ramalama-run.yaml
 > ```
 

pyproject.toml

@@ -21,8 +21,10 @@ dependencies = [
     "datasets>=3.6.0",
     "fastapi>=0.115.12",
     "httpx>=0.28.1",
-    "llama-stack==0.2.14",
+    "llama-stack==0.6.0",
+    "llama-stack-client==0.6.0",
     "mcp>=1.9.2",
+    "milvus-lite>=2.5.1",
     "numpy>=2.2.6",
     "openai>=1.82.0",
     "opentelemetry-exporter-otlp-proto-http>=1.33.1",
@@ -31,7 +33,6 @@ dependencies = [
     "psutil>=7.0.0",
     "pydantic>=2.11.5",
     "pymilvus>=2.5.10",
-    "ramalama==0.10.1",
     "requests>=2.32.3",
     "sentence-transformers>=3.0.0",
     "six>=1.17.0",
@@ -40,6 +41,7 @@ dependencies = [
     "trl>=0.18.1",
     "urllib3>=2.4.0",
     "uvicorn>=0.34.2",
+    "setuptools<70",
 ]
 
 [dependency-groups]
@@ -62,7 +64,7 @@ package-dir = { "" = "src" }
 include-package-data = true
 
 [tool.setuptools.package-data]
-"ramalama_stack" = ["providers.d/**/*", "ramalama-run.yaml"]
+"ramalama_stack" = ["ramalama-run.yaml"]
 
 [tool.ruff]
 extend-exclude = ["*.ipynb"]