LCORE-334: Lightspeed core needs to fully support RHOAI LLM provider (prow)

README.md

@@ -124,6 +124,7 @@ Lightspeed Core Stack (LCS) supports the large language models from the provider
 | -------- | ---------------------------------------------- | ------------ | -------------- | -------------------------------------------------------------------------- |
 | OpenAI   | gpt-5, gpt-4o, gpt4-turbo, gpt-4.1, o1, o3, o4 | Yes          | remote::openai | [1](examples/openai-faiss-run.yaml) [2](examples/openai-pgvector-run.yaml) |
 | OpenAI   | gpt-3.5-turbo, gpt-4                           | No           | remote::openai |                                                                            |
+| RHOAI (vLLM)| meta-llama/Llama-3.2-1B-Instruct           | Yes          | remote::vllm   | [1](tests/e2e-prow/rhoai/configs/run.yaml)                                     |
 | RHAIIS (vLLM)| meta-llama/Llama-3.1-8B-Instruct           | Yes          | remote::vllm   | [1](tests/e2e/configs/run-rhaiis.yaml)                                     |
 | Azure    | gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o3-mini, o4-mini | Yes          | remote::azure  | [1](examples/azure-run.yaml)                                               |
 | Azure    |  o1, o1-mini | No          | remote::azure  |  |

docs/providers.md

@@ -61,6 +61,7 @@ Red Hat providers:
 
 | Name | Version Tested | Type | Pip Dependencies | Supported in LCS |
 |---|---|---|---|:---:|
+| RHOAI (vllm) | latest operator | remote | `openai` | ✅ |
 | RHAIIS (vllm) | 3.2.3 (on RHEL 9.20250429.0.4) | remote | `openai` | ✅ |
 
 

tests/e2e-prow/rhoai/configs/lightspeed-stack.yaml

@@ -0,0 +1,25 @@
+name: Lightspeed Core Service (LCS)
+service:
+  host: 0.0.0.0
+  port: 8080
+  auth_enabled: false
+  workers: 1
+  color_log: true
+  access_log: true
+llama_stack:
+  # Uses a remote llama-stack service
+  # The instance would have already been started with a llama-stack-run.yaml file
+  use_as_library_client: false
+  # Alternative for "as library use"
+  # use_as_library_client: true
+  # library_client_config_path: <path-to-llama-stack-run.yaml-file>
+  url: http://${env.E2E_LLAMA_HOSTNAME}:8321
+  api_key: xyzzy
+user_data_collection:
+  feedback_enabled: true
+  feedback_storage: "/tmp/data/feedback"
+  transcripts_enabled: true
+  transcripts_storage: "/tmp/data/transcripts"
+
+authentication:
+  module: "noop"

tests/e2e-prow/rhoai/configs/run.yaml

@@ -0,0 +1,120 @@
+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: vllm
+    provider_type: remote::vllm
+    config:
+      url: ${env.KSVC_URL}/v1/
+      api_token: ${env.VLLM_API_KEY}
+      tls_verify: false
+      max_tokens: 1024
+  post_training:
+  - config:
+      checkpoint_format: huggingface
+      device: cpu
+      distributed_backend: null
+      dpo_output_dir: "."
+    provider_id: huggingface
+    provider_type: inline::huggingface-gpu
+  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: []
+  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: []
+
+models:
+- model_id: meta-llama/Llama-3.2-1B-Instruct
+  provider_id: vllm
+  model_type: llm
+  provider_model_id: null
+

tests/e2e-prow/rhoai/manifests/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: E2E_LLAMA_HOSTNAME
+          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

tests/e2e-prow/rhoai/manifests/lightspeed/llama-stack.yaml

@@ -0,0 +1,34 @@
+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: app-root
+          mountPath: /opt/app-root/src/.llama
+        - name: config
+          mountPath: /opt/app-root/run.yaml
+          subPath: run.yaml
+  volumes:
+    - name: app-root
+      emptyDir: {}
+    - name: config
+      configMap:
+        name: llama-stack-config

tests/e2e-prow/rhoai/manifests/operators/ds-cluster.yaml

@@ -0,0 +1,17 @@
+apiVersion: datasciencecluster.opendatahub.io/v1
+kind: DataScienceCluster
+metadata:
+  name: default-dsc
+  namespace: e2e-rhoai-dsc
+spec:
+  serviceMesh:
+    managementState: Managed
+  components:
+    kserve:
+      managementState: Managed
+    workbenches:
+      managementState: Removed
+    dashboard:
+      managementState: Removed
+    dataSciencePipelines:
+      managementState: Removed

tests/e2e-prow/rhoai/manifests/operators/operatorgroup.yaml

@@ -0,0 +1,6 @@
+apiVersion: operators.coreos.com/v1
+kind: OperatorGroup
+metadata:
+  name: global-operators
+  namespace: openshift-operators
+spec: 

tests/e2e-prow/rhoai/manifests/operators/operators.yaml

@@ -0,0 +1,35 @@
+# Service Mesh Operator Subscription
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: servicemeshoperator
+  namespace: openshift-operators
+spec:
+  channel: "stable"
+  name: "servicemeshoperator"
+  source: "redhat-operators"
+  sourceNamespace: "openshift-marketplace"
+---
+# Serverless Operator Subscription
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: serverless-operator
+  namespace: openshift-operators
+spec:
+  channel: "stable"
+  name: "serverless-operator"
+  source: "redhat-operators"
+  sourceNamespace: "openshift-marketplace"
+---
+# RHODS Operator Subscription
+apiVersion: operators.coreos.com/v1alpha1
+kind: Subscription
+metadata:
+  name: rhods-operator
+  namespace: openshift-operators
+spec:
+  channel: stable
+  name: rhods-operator
+  source: redhat-operators
+  sourceNamespace: openshift-marketplace

tests/e2e-prow/rhoai/manifests/test-pod/spin-up.yaml

@@ -0,0 +1,30 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: test-pod
+  namespace: e2e-rhoai-dsc
+spec:
+  containers:
+  - name: test-container
+    env:
+      - name: E2E_LSC_HOSTNAME
+        valueFrom:
+          secretKeyRef:
+            name: lcs-ip-secret
+            key: key
+      - name: E2E_LLAMA_HOSTNAME
+        valueFrom:
+          secretKeyRef:
+            name: llama-stack-ip-secret
+            key: key
+    image: registry.access.redhat.com/ubi9/python-312
+    command: ["/bin/sh", "/scripts/run-tests.sh"] 
+    volumeMounts:
+    - name: script-volume
+      mountPath: /scripts
+  volumes:
+  - name: script-volume
+    configMap:
+      name: test-script-cm
+      defaultMode: 0755 # Make the script executable
+  restartPolicy: Never

tests/e2e-prow/rhoai/manifests/vllm/inference-service.yaml

@@ -0,0 +1,13 @@
+apiVersion: serving.kserve.io/v1beta1
+kind: InferenceService
+metadata:
+  name: vllm-model
+  namespace: e2e-rhoai-dsc
+spec:
+  predictor:
+    model:
+      modelFormat:
+        name: pytorch
+      runtime: vllm
+      storage:
+        key: localModel