x

config/general_settings.yaml

@@ -28,7 +28,7 @@ general_settings:
   max_parallel_requests: 10  # the max parallel requests allowed per deployment 
   global_max_parallel_requests: 100  # the max parallel requests allowed on the proxy all up 
   infer_model_from_keys: true
-  background_health_checks: true
+  background_health_checks: false
   health_check_interval: 300
   # alerting: ["slack", "email"]
   # alerting_threshold: 0

config/model_config.yaml

@@ -2,30 +2,30 @@ model_list:
   - model_name: "*" 
     litellm_params:
       model: "*"
-#   - model_name: "openai/*"
-#     litellm_params:
-#       model: "openai/*"
-#       api_key: os.environ/OPENAI_API_KEY
-#     litellm_settings:
-#       check_provider_endpoint: true
+  - model_name: "openai/*"
+    litellm_params:
+      model: "openai/*"
+      api_key: os.environ/OPENAI_API_KEY
+    litellm_settings:
+      check_provider_endpoint: true
 
-#   - model_name: "anthropic/*"
-#     litellm_params:
-#       model: "anthropic/*"
-#       api_key: os.environ/ANTHROPIC_API_KEY
-#     litellm_settings:
-#       check_provider_endpoint: true
+  - model_name: "anthropic/*"
+    litellm_params:
+      model: "anthropic/*"
+      api_key: os.environ/ANTHROPIC_API_KEY
+    litellm_settings:
+      check_provider_endpoint: true
 
-#   - model_name: "gemini/*"
-#     litellm_params:
-#       model: "gemini/*"
-#       api_key: os.environ/GEMINI_API_KEY
-#     litellm_settings:
-#       check_provider_endpoint: true
+  - model_name: "gemini/*"
+    litellm_params:
+      model: "gemini/*"
+      api_key: os.environ/GEMINI_API_KEY
+    litellm_settings:
+      check_provider_endpoint: true
   
-#   - model_name: nova-2
-#     litellm_params:
-#       model: deepgram/nova-2
-#       api_key: os.environ/DEEPGRAM_API_KEY
-#     model_info:
-#       mode: audio_transcription
+  - model_name: nova-2
+    litellm_params:
+      model: deepgram/nova-2
+      api_key: os.environ/DEEPGRAM_API_KEY
+    model_info:
+      mode: audio_transcription