Update config.yaml

config.yaml

@@ -1,17 +1,44 @@
-general_settings:
-    master_key: sk-1234567890
-
-litellm_settings:
-    drop_params: True
-    set_verbose: True
-
 model_list:
- 
+  - model_name: gpt-3.5-turbo ### RECEIVED MODEL NAME ###
+    litellm_params: # all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input
+      model: azure/gpt-turbo-small-eu ### MODEL NAME sent to `litellm.completion()` ###
+      api_base: https://my-endpoint-europe-berri-992.openai.azure.com/
+      api_key: "os.environ/AZURE_API_KEY_EU" # does os.getenv("AZURE_API_KEY_EU")
+      rpm: 6      # [OPTIONAL] Rate limit for this deployment: in requests per minute (rpm)
+  - model_name: bedrock-claude-v1 
+    litellm_params:
+      model: bedrock/anthropic.claude-instant-v1
+  - model_name: gpt-3.5-turbo
+    litellm_params:
+      model: azure/gpt-turbo-small-ca
+      api_base: https://my-endpoint-canada-berri992.openai.azure.com/
+      api_key: "os.environ/AZURE_API_KEY_CA"
+      rpm: 6
+  - model_name: anthropic-claude
+    litellm_params: 
+      model: bedrock/anthropic.claude-instant-v1
+      ### [OPTIONAL] SET AWS REGION ###
+      aws_region_name: us-east-1
+  - model_name: vllm-models
+    litellm_params:
+      model: openai/facebook/opt-125m # the `openai/` prefix tells litellm it's openai compatible
+      api_base: http://0.0.0.0:4000/v1
+      api_key: none
+      rpm: 1440
+    model_info: 
+      version: 2
+  
+  # Use this if you want to make requests to `claude-3-haiku-20240307`,`claude-3-opus-20240229`,`claude-2.1` without defining them on the config.yaml
+  # Default models
+  # Works for ALL Providers and needs the default provider credentials in .env
+  - model_name: "*" 
+    litellm_params:
+      model: "*"
 
+litellm_settings: # module level litellm settings - https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py
+  drop_params: True
+  success_callback: ["langfuse"] # OPTIONAL - if you want to start sending LLM Logs to Langfuse. Make sure to set `LANGFUSE_PUBLIC_KEY` and `LANGFUSE_SECRET_KEY` in your env
 
-  - model_name: nousresearch/hermes-3-llama-3.1-405b:free
-    litellm_params: # all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input
-      model: nousresearch/hermes-3-llama-3.1-405b:free ### MODEL NAME sent to `litellm.completion()` ###
-      api_base: https://openrouter.ai/api/v1
-      api_key: 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 # does os.getenv("AZURE_API_KEY_EU")
-      rpm: 60      # [OPTIONAL] Rate limit for this deployment: in requests per minute (rpm)
+general_settings: 
+  master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234)
+  alerting: ["slack"] # [OPTIONAL] If you want Slack Alerts for Hanging LLM requests, Slow llm responses, Budget Alerts. Make sure to set `SLACK_WEBHOOK_URL` in your env