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
- set INFERNECE_MODEL to OLLAMA_INFERENCE_MODEL
- set images to use "latest" tag than 0.2.15

Signed-off-by: Wen Zhou <wenzhou@redhat.com>

Author: zdtsw

README.md

@@ -80,11 +80,10 @@ spec:
   replicas: 1
   server:
     distribution:
-      name: ollama
+      name: starter
     containerSpec:
-      port: 8321
       env:
-      - name: INFERENCE_MODEL
+      - name: OLLAMA_INFERENCE_MODEL
         value: "llama3.2:1b"
       - name: OLLAMA_URL
         value: "http://ollama-server-service.ollama-dist.svc.cluster.local:11434"

config/samples/_v1alpha1_llamastackdistribution.yaml

@@ -7,7 +7,7 @@ spec:
   server:
     containerSpec:
       env:
-        - name: INFERENCE_MODEL
+        - name: OLLAMA_INFERENCE_MODEL
           value: 'llama3.2:1b'
         - name: OLLAMA_URL
           value: 'http://ollama-server-service.ollama-dist.svc.cluster.local:11434'

config/samples/example-with-configmap.yaml

@@ -48,7 +48,7 @@ data:
 apiVersion: llamastack.io/v1alpha1
 kind: LlamaStackDistribution
 metadata:
-  name: llamastack-with-config
+  name: llamastack-with-userconfig
 spec:
   replicas: 1
   server:
@@ -57,10 +57,8 @@ spec:
     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: OLLAMA_EMBEDDING_MODEL
+        value: all-minilm:l6-v2
     userConfig:
       configMapName: llama-stack-config
       # configMapNamespace: ""  # Optional - defaults to the same namespace as the CR

config/samples/example-withoutconfigmap.yaml

@@ -0,0 +1,19 @@
+---
+apiVersion: llamastack.io/v1alpha1
+kind: LlamaStackDistribution
+metadata:
+  name: llamastack-without-userconfig
+spec:
+  replicas: 1
+  server:
+    distribution:
+      name: starter
+    containerSpec:
+      env:
+      - name: OLLAMA_INFERENCE_MODEL
+        value: "llama3.2:1b"
+      - name: OLLAMA_URL
+        value: "http://ollama-server-service.ollama-dist.svc.cluster.local:11434"
+    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: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"
 }