fix: update the command for Llama Stack server (#2097)

* Update the server run command

* testing foreground run

* testing foreground run

* Update yaml

* Update workflow

* Update workflow

* Update workflow

* Update tests

* Update toml

* Attempt another fix

* See what models are available

* Increase sleep time

* Pin the version

Author: Amnah199

.github/workflows/llama_stack.yml

@@ -31,7 +31,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]  # to test on other Operating Systems, we need to install Ollama differently
-        python-version: ["3.10", "3.13"]  
+        python-version: ["3.12", "3.13"]  
 
     steps:
       - uses: actions/checkout@v4
@@ -77,21 +77,25 @@ jobs:
           python-version: ${{ matrix.python-version }}
 
       - name: Test Llama Stack Server
+        shell: bash
         run: |
           pip install uv
-          INFERENCE_MODEL=llama3.2:3b uv run --with llama-stack llama stack build --template ollama --image-type venv --run &
-
+          INFERENCE_MODEL=llama3.2:3b uv run --with llama-stack llama stack build --template ollama --image-type venv --run < /dev/null > server.log 2>&1 &
+          sleep 120
+          # Verify it's running
+          curl -f http://localhost:8321/v1/models || { cat server.log; exit 1; }
+          
           echo "Llama Stack Server started successfully."
 
       - name: Install Hatch
         run: pip install --upgrade hatch
 
       - name: Lint
-        if: matrix.python-version == '3.10' && runner.os == 'Linux'
+        if: matrix.python-version == '3.12' && runner.os == 'Linux'
         run: hatch run fmt-check && hatch run test:types
 
       - name: Generate docs
-        if: matrix.python-version == '3.10' && runner.os == 'Linux'
+        if: matrix.python-version == '3.12' && runner.os == 'Linux'
         run: hatch run docs
 
       - name: Run tests

integrations/llama_stack/pyproject.toml

@@ -7,22 +7,20 @@ name = "llama-stack-haystack"
 dynamic = ["version"]
 description = 'Use Llama Stack framework for text generation'
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.12"
 license = "Apache-2.0"
 keywords = []
 authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
 classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.10", # python 3.9 is not supported by llama-stack
-  "Programming Language :: Python :: 3.11",
-  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.12", # minimum supported version by llama-stack
   "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.14", "llama-stack"]
+dependencies = ["haystack-ai>=2.14", "llama-stack==0.2.14"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/llama-stack#readme"