update: address review comments

- revert back to use llama3.2:1b
- remove unnecessary/unrelated comments/changes
- set INFERNECE_MODEL to OLLAMA_INFERENCE_MODEL
- remove ENALBE_OLLAMA
- set images to use "latest" tag than 0.2.15
-

Signed-off-by: Wen Zhou <[email protected]>

Author: zdtsw

README.md

@@ -84,18 +84,16 @@ spec:
     containerSpec:
       env:
       - name: INFERENCE_MODEL
-        value: "llama3.2:3b"
+        value: "llama3.2:1b"
       - name: OLLAMA_URL
         value: "http://ollama-server-service.ollama-dist.svc.cluster.local:11434"
-      - name: ENABLE_OLLAMA
-        value: ollama
     storage:
       size: "20Gi"
       mountPath: "/home/lls/.lls"
 ```
 3. Verify the server pod is running in the user defined namespace.
 
-### Using a ConfigMap to override default run.yaml configuration from distribution
+### Using a ConfigMap for run.yaml configuration
 
 A ConfigMap can be used to store run.yaml configuration for each LlamaStackDistribution.
 Updates to the ConfigMap will restart the Pod to load the new data.

config/manager/manager.yaml

@@ -48,7 +48,7 @@ spec:
           allowPrivilegeEscalation: false
           capabilities:
             drop:
-            - "ALL"
+              - "ALL"
         livenessProbe:
           httpGet:
             path: /healthz

config/samples/_v1alpha1_llamastackdistribution.yaml

@@ -7,12 +7,10 @@ spec:
   server:
     containerSpec:
       env:
-        - name: INFERENCE_MODEL
-          value: 'llama3.2:3b'
+        - name: OLLAMA_INFERENCE_MODEL
+          value: 'llama3.2:1b'
         - name: OLLAMA_URL
           value: 'http://ollama-server-service.ollama-dist.svc.cluster.local:11434'
-        - name: ENABLE_OLLAMA
-          value: ollama
       name: llama-stack
     distribution:
       name: starter

config/samples/example-with-configmap.yaml

@@ -11,20 +11,15 @@ data:
     - inference
     providers:
       inference:
-      - provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
+      - provider_id: ollama
         provider_type: "remote::ollama"
         config:
           url: "http://ollama-server-service.ollama-dist.svc.cluster.local:11434"
     models:
-      - model_id: "ollama/llama3.2:3b"
+      - model_id: "llama3.2:1b"
         provider_id: ollama
         model_type: llm
-        provider_model_id: llama3.2:3b
-      - embedding_dimension: 384
-        model_id: ${env.ENABLE_OLLAMA:=__disabled__}/${env.OLLAMA_EMBEDDING_MODEL:=__disabled__}
-        provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
-        provider_model_id: ${env.OLLAMA_EMBEDDING_MODEL:=__disabled__}
-        model_type: embedding
+        provider_model_id: llama3.2:1b
     server:
       port: 8321
 ---
@@ -40,10 +35,8 @@ spec:
     containerSpec:
       port: 8321
       env:
-      - name: ENABLE_OLLAMA
-        value: ollama
       - name: OLLAMA_EMBEDDING_MODEL
         value: all-minilm:l6-v2
     userConfig:
-      configMapName: llama-stack-config  # use ConfigMap's data.run.yaml
+      configMapName: llama-stack-config
       # configMapNamespace: ""  # Optional - defaults to the same namespace as the CR

config/samples/example-withoutconfigmpa.yaml

@@ -12,11 +12,9 @@ spec:
       port: 8321
       env:
       - name: OLLAMA_INFERENCE_MODEL
-        value: "llama3.2:3b"
+        value: "llama3.2:1b"
       - name: OLLAMA_URL
         value: "http://ollama-server-service.ollama-dist.svc.cluster.local:11434"
-      - name: ENABLE_OLLAMA
-        value: ollama
     storage:
       size: "10Gi"  # Optional - defaults to 10Gi
       mountPath: "/home/lls/.lls"  # Optional - defaults to /.llama

distributions.json

@@ -1,6 +1,6 @@
 {
-  "starter": "docker.io/llamastack/distribution-starter:0.2.15",
-  "remote-vllm": "docker.io/llamastack/distribution-remote-vllm:0.2.15",
-  "meta-reference-gpu": "docker.io/llamastack/distribution-meta-reference-gpu:0.2.15",
-  "postgres-demo": "docker.io/llamastack/distribution-postgres-demo:0.2.15"
+  "starter": "docker.io/llamastack/distribution-starter:latest",
+  "remote-vllm": "docker.io/llamastack/distribution-remote-vllm:latest",
+  "meta-reference-gpu": "docker.io/llamastack/distribution-meta-reference-gpu:latest",
+  "postgres-demo": "docker.io/llamastack/distribution-postgres-demo:latest"
 }