more updates

demos/samples_java/weather_forcecast_service/.vscode/launch.json

@@ -0,0 +1,15 @@
+{
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "type": "java",
+      "name": "WeatherForecastApplication",
+      "request": "launch",
+      "mainClass": "weather.WeatherForecastApplication",
+      "projectName": "weather-forecast-service"
+    }
+  ]
+}

demos/use_cases/ollama/arch_config.yaml

@@ -10,7 +10,7 @@ listeners:
 llm_providers:
 
   - model: openai/llama3.2
-    endpoint: host.docker.internal:11434
+    base_url: http://host.docker.internal:11434
     default: true
 
 system_prompt: |

demos/use_cases/preference_based_routing/arch_config.yaml

@@ -9,22 +9,21 @@ listeners:
 
 llm_providers:
 
-  - access_key: $OPENAI_API_KEY
-    model: openai/gpt-4o-mini
-
-  - access_key: $OPENAI_API_KEY
-    model: openai/gpt-4.1
+  - model: openai/gpt-4o-mini
+    access_key: $OPENAI_API_KEY
     default: true
 
-  - name: code_generation
+  - model: openai/gpt-4o
     access_key: $OPENAI_API_KEY
-    model: openai/gpt-4.1
-    usage: generating new code snippets, functions, or boilerplate based on user prompts or requirements
+    routing_preferences:
+      - name: code understanding
+        description: understand and explain existing code snippets, functions, or libraries
 
-  - name: code_understanding
+  - model: openai/gpt-4.1
     access_key: $OPENAI_API_KEY
-    model: openai/gpt-4o-mini
-    usage: understand and explain existing code snippets, functions, or libraries
+    routing_preferences:
+      - name: code generation
+        description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
 
 tracing:
   random_sampling: 100

demos/use_cases/preference_based_routing/arch_config_local.yaml

@@ -1,45 +0,0 @@
-version: v0.1.0
-
-routing:
-  model: Arch-Router
-  llm_provider: arch-router
-
-listeners:
-  egress_traffic:
-    address: 0.0.0.0
-    port: 12000
-    message_format: openai
-    timeout: 30s
-
-llm_providers:
-
-  - name: arch-router
-    provider_interface: arch
-    model: hf.co/katanemo/Arch-Router-1.5B.gguf:Q4_K_M
-    endpoint: host.docker.internal:11434
-
-  - name: gpt-4o-mini
-    provider_interface: openai
-    access_key: $OPENAI_API_KEY
-    model: gpt-4o-mini
-
-  - name: gpt-4.1
-    provider_interface: openai
-    access_key: $OPENAI_API_KEY
-    model: gpt-4.1
-    default: true
-
-  - name: code_generation
-    access_key: $OPENAI_API_KEY
-    provider_interface: openai
-    model: gpt-4.1
-    usage: generating new code snippets, functions, or boilerplate based on user prompts or requirements
-
-  - name: code_understanding
-    provider_interface: openai
-    access_key: $OPENAI_API_KEY
-    model: gpt-4.1
-    usage: understand and explain existing code snippets, functions, or libraries
-
-tracing:
-  random_sampling: 100

demos/use_cases/preference_based_routing/arch_config_rendered.yaml

@@ -0,0 +1,29 @@
+listeners:
+  egress_traffic:
+    address: 0.0.0.0
+    message_format: openai
+    port: 12000
+    timeout: 30s
+llm_providers:
+- access_key: $OPENAI_API_KEY
+  default: true
+  model: gpt-4o-mini
+  name: openai/gpt-4o-mini
+  provider_interface: openai
+- access_key: $OPENAI_API_KEY
+  model: gpt-4o
+  name: openai/gpt-4o
+  provider_interface: openai
+  routing_preferences:
+  - description: b
+    name: code understanding
+- access_key: $OPENAI_API_KEY
+  model: gpt-4.1
+  name: openai/gpt-4.1
+  provider_interface: openai
+  routing_preferences:
+  - description: a
+    name: code understanding
+tracing:
+  random_sampling: 100
+version: v0.1.0

demos/use_cases/preference_based_routing/hurl_tests/simple.hurl

@@ -2,18 +2,18 @@ POST http://localhost:12000/v1/chat/completions
 Content-Type: application/json
 
 {
+  "model": "openai/gpt-4.1",
   "messages": [
     {
       "role": "user",
       "content": "hi"
     }
-  ],
-  "model": "none"
+  ]
 }
 HTTP 200
 [Asserts]
 header "content-type" == "application/json"
-jsonpath "$.model" matches /^gpt-4.1/
+jsonpath "$.model" matches /^gpt-4o-mini/
 jsonpath "$.usage" != null
 jsonpath "$.choices[0].message.content" != null
 jsonpath "$.choices[0].message.role" == "assistant"