docs: update using "starter" distro than "ollama"

- update example and create one without using userconfigmap
- set new env to enable ollama
- use the same llama model as in llama-stack
- remove deprecated distro images from distribution.json

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

Author: zdtsw

README.md

@@ -80,21 +80,22 @@ spec:
   replicas: 1
   server:
     distribution:
-      name: ollama
+      name: starter
     containerSpec:
-      port: 8321
       env:
       - name: INFERENCE_MODEL
-        value: "llama3.2:1b"
+        value: "llama3.2:3b"
       - 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 for run.yaml configuration
+### Using a ConfigMap to override default run.yaml configuration from distribution
 
 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

@@ -8,12 +8,14 @@ spec:
     containerSpec:
       env:
         - name: INFERENCE_MODEL
-          value: 'llama3.2:1b'
+          value: 'llama3.2:3b'
         - name: OLLAMA_URL
           value: 'http://ollama-server-service.ollama-dist.svc.cluster.local:11434'
+        - name: ENABLE_OLLAMA
+          value: ollama
       name: llama-stack
     distribution:
-      name: ollama
+      name: starter
     # Uncomment the storage section to use persistent storage
     # storage: {}  # Will use default size of 10Gi and default mount path of /.llama
     # Or specify custom values:

config/samples/example-with-configmap.yaml

@@ -6,38 +6,44 @@ data:
   run.yaml: |
     # Llama Stack Configuration
     version: '2'
-    image_name: ollama
+    image_name: starter
     apis:
     - inference
     providers:
       inference:
-      - provider_id: ollama
+      - provider_id: ${env.ENABLE_OLLAMA:=__disabled__}
         provider_type: "remote::ollama"
         config:
           url: "http://ollama-server-service.ollama-dist.svc.cluster.local:11434"
     models:
-      - model_id: "llama3.2:1b"
+      - model_id: "ollama/llama3.2:3b"
         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
     server:
       port: 8321
 ---
 apiVersion: llamastack.io/v1alpha1
 kind: LlamaStackDistribution
 metadata:
-  name: llamastack-with-config
+  name: llamastack-with-userconfig
 spec:
   replicas: 1
   server:
     distribution:
-      name: ollama
+      name: starter
     containerSpec:
       port: 8321
       env:
-      - name: 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: OLLAMA_EMBEDDING_MODEL
+        value: all-minilm:l6-v2
     userConfig:
-      configMapName: llama-stack-config
+      configMapName: llama-stack-config  # use ConfigMap's data.run.yaml
       # configMapNamespace: ""  # Optional - defaults to the same namespace as the CR

config/samples/example-withoutconfigmpa.yaml

@@ -0,0 +1,22 @@
+---
+apiVersion: llamastack.io/v1alpha1
+kind: LlamaStackDistribution
+metadata:
+  name: llamastack-without-userconfig
+spec:
+  replicas: 1
+  server:
+    distribution:
+      name: starter
+    containerSpec:
+      port: 8321
+      env:
+      - name: OLLAMA_INFERENCE_MODEL
+        value: "llama3.2:3b"
+      - 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

@@ -1,9 +1,6 @@
 {
-"starter": "docker.io/llamastack/distribution-starter:latest",
-"ollama": "docker.io/llamastack/distribution-ollama:latest",
-"bedrock": "docker.io/llamastack/distribution-bedrock:latest",
-"remote-vllm": "docker.io/llamastack/distribution-remote-vllm:latest",
-"tgi": "docker.io/llamastack/distribution-tgi:latest",
-"together": "docker.io/llamastack/distribution-together:latest",
-"vllm-gpu": "docker.io/llamastack/distribution-vllm-gpu:latest"
+  "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"
 }