config/llm.yaml

@@ -28,9 +28,9 @@ backends:
     type: openai_compat
   ollama_research:
     api_key: ollama
-    base_url: http://ollama_research:11434/v1
+    base_url: http://host.docker.internal:11434/v1
     enabled: true
-    model: llama3.1:8b
+    model: llama3.2:3b
     supports_images: false
     type: openai_compat
   vision_service:
@@ -40,20 +40,14 @@ backends:
     type: vision_service
   vllm:
     api_key: ''
-    base_url: http://vllm:8000/v1
+    base_url: http://host.docker.internal:8000/v1
     enabled: true
     model: __auto__
     supports_images: false
     type: openai_compat
-    cf_orch:
-      service: vllm
-      model_candidates:
-      - Qwen2.5-3B-Instruct
-      - Phi-4-mini-instruct
-      ttl_s: 300
   vllm_research:
     api_key: ''
-    base_url: http://vllm:8000/v1
+    base_url: http://host.docker.internal:8000/v1
     enabled: true
     model: __auto__
     supports_images: false