Finished deployment of llama and lightspeed stack

are-ces · are-ces · commit 06f7cbf1dd81 · 2025-10-21T17:42:35.000+02:00
diff --git a/tests/e2e-prow/rhoai/config/lightspeed-stack.yaml b/tests/e2e-prow/rhoai/config/lightspeed-stack.yaml
@@ -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://llama-stack:8321
+  url: http://${env.LLAMA_IP}:8321
   api_key: xyzzy
 user_data_collection:
   feedback_enabled: true
diff --git a/tests/e2e-prow/rhoai/config/lightspeed/lightspeed-stack.yaml b/tests/e2e-prow/rhoai/config/lightspeed/lightspeed-stack.yaml
@@ -0,0 +1,25 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: lightspeed-stack-service
+  namespace: e2e-rhoai-dsc
+spec:
+  containers:
+    - name: lightspeed-stack-container
+      env:
+        - name: LLAMA_IP
+          valueFrom:
+            secretKeyRef:
+              name: llama-stack-ip-secret
+              key: key
+      image: quay.io/lightspeed-core/lightspeed-stack:dev-latest
+      ports:
+        - containerPort: 8080
+      volumeMounts:
+        - name: config
+          mountPath: /app-root/lightspeed-stack.yaml
+          subPath: lightspeed-stack.yaml
+  volumes:
+    - name: config
+      configMap:
+        name: lightspeed-stack-config
diff --git a/tests/e2e-prow/rhoai/config/lightspeed/llama-stack.yaml b/tests/e2e-prow/rhoai/config/lightspeed/llama-stack.yaml
@@ -0,0 +1,30 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: llama-stack-service
+  namespace: e2e-rhoai-dsc
+spec:
+  containers:
+    - name: llama-stack-container
+      env:
+        - name: KSVC_URL
+          valueFrom:
+            secretKeyRef:
+              name: api-url-secret
+              key: key
+        - name: VLLM_API_KEY
+          valueFrom:
+            secretKeyRef:
+              name: vllm-api-key-secret
+              key: key
+      image: quay.io/opendatahub/llama-stack:rhoai-v2.25-latest
+      ports:
+        - containerPort: 8321
+      volumeMounts:
+        - name: config
+          mountPath: /opt/app-root/run.yaml
+          subPath: run.yaml
+  volumes:
+    - name: config
+      configMap:
+        name: llama-stack-config
diff --git a/tests/e2e-prow/rhoai/config/run.yaml b/tests/e2e-prow/rhoai/config/run.yaml
@@ -1,62 +1,120 @@
-version: 2
-image_name: rag-configuration-demo3
+version: '2'
+image_name: minimal-viable-llama-stack-configuration
 
 apis:
-- agents
-- inference
-- vector_io
-- tool_runtime
-- safety
-
-models:
-- model_id: meta-llama/Llama-3.2-1B-Instruct
-  provider_id: vllm
-  model_type: llm
-  provider_model_id: null
-- model_id: sentence-transformers/all-mpnet-base-v2
-  metadata:
-      embedding_dimension: 768
-  model_type: embedding
-  provider_id: sentence-transformers
-  provider_model_id: /Users/cpompeia/Documents/Dev/lightspeed-rag-content/embeddings_model
-  
+  - 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: sentence-transformers
-    provider_type: inline::sentence-transformers
-    config: {}
   - provider_id: vllm
     provider_type: remote::vllm
     config:
       url: ${env.KSVC_URL}/v1/
       api_token: ${env.VLLM_API_KEY}
       tls_verify: false
       max_tokens: 1024
-
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        type: sqlite
-        db_path: .llama/distributions/ollama/agents_store.db
-      responses_store:
-        type: sqlite
-        db_path: .llama/distributions/ollama/responses_store.db
-
+  post_training:
+  - config:
+      checkpoint_format: huggingface
+      device: cpu
+      distributed_backend: null
+      dpo_output_dir: "."
+    provider_id: huggingface
+    provider_type: inline::huggingface-gpu
   safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
+  - 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: []
+  vector_io: []
+scoring_fns: []
+server:
+  auth: null
+  host: null
+  port: 8321
+  quota: null
+  tls_cafile: null
+  tls_certfile: null
+  tls_keyfile: null
+shields: []
+vector_dbs: []
 
-  tool_runtime:
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
-    config: {}
+models:
+- model_id: meta-llama/Llama-3.2-1B-Instruct
+  provider_id: vllm
+  model_type: llm
+  provider_model_id: null
 
-tool_groups:
-- provider_id: rag-runtime
-  toolgroup_id: builtin::rag
-  args: null
-  mcp_endpoint: null
diff --git a/tests/e2e-prow/rhoai/scripts/deploy-services.sh b/tests/e2e-prow/rhoai/scripts/deploy-services.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+
+BASE_DIR="$1"
+
+oc apply -f "$BASE_DIR/config/lightspeed/llama-stack.yaml"
+
+# Get IP address of llama-stack pod
+LLAMA_IP=$(oc get pod llama-stack-service -n e2e-rhoai-dsc -o jsonpath='{.status.podIP}')
+oc create secret generic llama-stack-ip-secret \
+    --from-literal=key="$LLAMA_IP" \
+    -n e2e-rhoai-dsc || echo "Secret exists"
+
+oc apply -f "$BASE_DIR/config/lightspeed/lightspeed-stack.yaml"
diff --git a/tests/e2e-prow/rhoai/scripts/deploy-vllm.sh b/tests/e2e-prow/rhoai/scripts/deploy-vllm.sh
diff --git a/tests/e2e-prow/rhoai/scripts/get-pod-info.sh b/tests/e2e-prow/rhoai/scripts/get-pod-info.sh
@@ -22,13 +22,6 @@ until [ -n "$POD_NAME" ] || [ $ELAPSED -ge $TIMEOUT ]; do
     -l "serving.kserve.io/inferenceservice=$ISVC_NAME" \
     -o jsonpath="{.items[?(@.status.phase=='Running')].metadata.name}" 2>/dev/null)
   echo "Waiting for pod $POD_NAME in namespace $NAMESPACE"
-  
-  echo "GET PODS"
-  oc get pods -n $NAMESPACE || true
-
-  echo "END GET PODS"
-  oc describe pod $POD_NAME -n $NAMESPACE || true
-  oc logs $POD_NAME -n $NAMESPACE || true
 
   if [ -z "$POD_NAME" ]; then
     echo "  -> Pod not running yet, waiting $INTERVAL seconds..."
@@ -37,6 +30,9 @@ until [ -n "$POD_NAME" ] || [ $ELAPSED -ge $TIMEOUT ]; do
   fi
 done
 
+oc describe pod $POD_NAME -n $NAMESPACE || true
+oc logs $POD_NAME -n $NAMESPACE || true
+
 POD_NAME=$(oc get pods -n $NAMESPACE -o jsonpath='{.items[0].metadata.name}')
 
 if [ -z "$POD_NAME" ]; then
