config/llm.yaml

@@ -30,7 +30,7 @@ backends:
     api_key: ollama
     base_url: http://host.docker.internal:11434/v1
     enabled: true
-    model: llama3.2:3b
+    model: llama3.1:8b
     supports_images: false
     type: openai_compat
   vision_service:
@@ -45,6 +45,12 @@ backends:
     model: __auto__
     supports_images: false
     type: openai_compat
+    cf_orch:
+      service: vllm
+      model_candidates:
+        - Ouro-2.6B-Thinking
+        - Ouro-1.4B
+      ttl_s: 300
   vllm_research:
     api_key: ''
     base_url: http://host.docker.internal:8000/v1