LCORE-431: how to build the lightspeed core image

Containerfile

@@ -62,4 +62,4 @@ ENTRYPOINT ["python3.12", "src/lightspeed_stack.py"]
 LABEL vendor="Red Hat, Inc."
 
 # no-root user is checked in Konflux
-USER 1001
+USER 1001

README.md

@@ -506,6 +506,80 @@ Container images are built for the following platforms:
 1. `linux/amd64` - main platform for deployment
 1. `linux/arm64`- Mac users with M1/M2/M3 CPUs
 
+## Building Container Images
+
+The repository includes production-ready container configurations that support two deployment modes:
+
+1. **Server Mode**: lightspeed-core connects to llama-stack as a separate service
+2. **Library Mode**: llama-stack runs as a library within lightspeed-core
+
+### Llama-Stack as Separate Service (Server Mode)
+
+When using llama-stack as a separate service, the existing `docker-compose.yaml` provides the complete setup. This builds two containers for lightspeed core and llama stack.
+
+**Configuration** (`lightspeed-stack.yaml`):
+```yaml
+llama_stack:
+  use_as_library_client: false
+  url: http://llama-stack:8321  # container name from docker-compose.yaml
+  api_key: xyzzy
+```
+
+In the root of this project simply run:
+
+```bash
+# Set your OpenAI API key
+export OPENAI_API_KEY="your-api-key-here"
+
+# Start both services
+podman compose up --build
+
+# Access lightspeed-core at http://localhost:8080
+# Access llama-stack at http://localhost:8321
+```
+
+### Llama-Stack as Library (Library Mode)
+
+When embedding llama-stack directly in the container, use the existing `Containerfile` directly (this will not build the llama stack service in a separate container). First modify the `lightspeed-stack.yaml` config to use llama stack in library mode.
+
+**Configuration** (`lightspeed-stack.yaml`):
+```yaml
+llama_stack:
+  use_as_library_client: true
+  library_client_config_path: /app-root/run.yaml
+```
+
+**Build and run**:
+```bash
+# Build lightspeed-core with embedded llama-stack
+podman build -f Containerfile -t my-lightspeed-core:latest .
+
+# Run with embedded llama-stack
+podman run \
+  -p 8080:8080 \
+  -v ./lightspeed-stack.yaml:/app-root/lightspeed-stack.yaml:Z \
+  -v ./run.yaml:/app-root/run.yaml:Z \
+  -e OPENAI_API_KEY=your-api-key \
+  my-lightspeed-core:latest
+```
+
+For macosx users:
+```bash
+podman run \
+  -p 8080:8080 \
+  -v ./lightspeed-stack.yaml:/app-root/lightspeed-stack.yaml:ro \
+  -v ./run.yaml:/app-root/run.yaml:ro \
+  -e OPENAI_API_KEY=your-api-key \
+  my-lightspeed-core:latest
+```
+
+### Verify it's running properly
+
+A simple sanity check:
+
+```bash
+curl -H "Accept: application/json" http://localhost:8080/v1/models
+```
 
 
 # Endpoints

lightspeed-stack.yaml

@@ -1,6 +1,6 @@
 name: Lightspeed Core Service (LCS)
 service:
-  host: localhost
+  host: 0.0.0.0
   port: 8080
   auth_enabled: false
   workers: 1
@@ -13,7 +13,7 @@ llama_stack:
   # Alternative for "as library use"
   # use_as_library_client: true
   # library_client_config_path: <path-to-llama-stack-run.yaml-file>
-  url: http://localhost:8321
+  url: http://llama-stack:8321
   api_key: xyzzy
 user_data_collection:
   feedback_enabled: true

run.yaml

@@ -0,0 +1,125 @@
+version: '2'
+image_name: minimal-viable-llama-stack-configuration
+
+apis:
+  - agents
+  - datasetio
+  - eval
+  - inference
+  - post_training
+  - safety
+  - scoring
+  - telemetry
+  - tool_runtime
+  - vector_io
+benchmarks: []
+container_image: null
+datasets: []
+external_providers_dir: null
+inference_store:
+  db_path: .llama/distributions/ollama/inference_store.db
+  type: sqlite
+logging: null
+metadata_store:
+  db_path: .llama/distributions/ollama/registry.db
+  namespace: null
+  type: sqlite
+providers:
+  agents:
+  - config:
+      persistence_store:
+        db_path: .llama/distributions/ollama/agents_store.db
+        namespace: null
+        type: sqlite
+      responses_store:
+        db_path: .llama/distributions/ollama/responses_store.db
+        type: sqlite
+    provider_id: meta-reference
+    provider_type: inline::meta-reference
+  datasetio:
+  - config:
+      kvstore:
+        db_path: .llama/distributions/ollama/huggingface_datasetio.db
+        namespace: null
+        type: sqlite
+    provider_id: huggingface
+    provider_type: remote::huggingface
+  - config:
+      kvstore:
+        db_path: .llama/distributions/ollama/localfs_datasetio.db
+        namespace: null
+        type: sqlite
+    provider_id: localfs
+    provider_type: inline::localfs
+  eval:
+  - config:
+      kvstore:
+        db_path: .llama/distributions/ollama/meta_reference_eval.db
+        namespace: null
+        type: sqlite
+    provider_id: meta-reference
+    provider_type: inline::meta-reference
+  inference:
+    - provider_id: openai
+      provider_type: remote::openai
+      config:
+        api_key: ${env.OPENAI_API_KEY}
+  post_training:
+  - config:
+      checkpoint_format: huggingface
+      device: cpu
+      distributed_backend: null
+    provider_id: huggingface
+    provider_type: inline::huggingface
+  safety:
+  - config:
+      excluded_categories: []
+    provider_id: llama-guard
+    provider_type: inline::llama-guard
+  scoring:
+  - config: {}
+    provider_id: basic
+    provider_type: inline::basic
+  - config: {}
+    provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+  - config:
+      openai_api_key: '********'
+    provider_id: braintrust
+    provider_type: inline::braintrust
+  telemetry:
+  - config:
+      service_name: 'lightspeed-stack-telemetry'
+      sinks: sqlite
+      sqlite_db_path: .llama/distributions/ollama/trace_store.db
+    provider_id: meta-reference
+    provider_type: inline::meta-reference
+  tool_runtime:
+    - provider_id: model-context-protocol
+      provider_type: remote::model-context-protocol
+      config: {}
+  vector_io:
+  - config:
+      kvstore:
+        db_path: .llama/distributions/ollama/faiss_store.db
+        namespace: null
+        type: sqlite
+    provider_id: faiss
+    provider_type: inline::faiss
+scoring_fns: []
+server:
+  auth: null
+  host: null
+  port: 8321
+  quota: null
+  tls_cafile: null
+  tls_certfile: null
+  tls_keyfile: null
+shields: []
+vector_dbs: []
+
+models:
+  - model_id: gpt-4-turbo
+    provider_id: openai
+    model_type: llm
+    provider_model_id: gpt-4-turbo

test.containerfile

@@ -14,7 +14,7 @@ COPY README.md ./
 COPY src/ ./src/
 
 RUN microdnf install -y --nodocs --setopt=keepcache=0 --setopt=tsflags=nodocs \
-    python3.12 python3.12-devel python3.12-pip git tar
+    python3.12 python3.12-devel python3.12-pip git tar gcc gcc-c++ make
 
 RUN curl -LsSf https://astral.sh/uv/install.sh | sh
 
@@ -25,4 +25,4 @@ RUN uv -h
 # Include dev deps for testing (pytest, behave, etc.)
 RUN uv sync --locked --no-install-project --group dev --group llslibdev
 
-CMD ["uv", "run", "llama", "stack", "run", "run.yaml"]
+CMD ["uv", "run", "llama", "stack", "run", "run.yaml"]