fix(main.py): fix ahealth_check to infer mode when custom_llm_provider/model_name used

litellm/main.py

@@ -4333,6 +4333,10 @@ async def ahealth_check(
             mode = litellm.model_cost[model]["mode"]
 
         model, custom_llm_provider, _, _ = get_llm_provider(model=model)
+
+        if model in litellm.model_cost and mode is None:
+            mode = litellm.model_cost[model]["mode"]
+
         mode = mode or "chat"  # default to chat completion calls
 
         if custom_llm_provider == "azure":

litellm/proxy/_super_secret_config.yaml

@@ -34,6 +34,11 @@ model_list:
     api_base: https://openai-france-1234.openai.azure.com
     api_key: os.environ/AZURE_FRANCE_API_KEY
     model: azure/gpt-turbo
+- model_name: text-embedding
+  litellm_params:
+    model: textembedding-gecko-multilingual@001
+    vertex_project: my-project-9d5c
+    vertex_location: us-central1
 
 router_settings:
   enable_pre_call_checks: true