(dos) config.yaml

litellm/proxy/config.yaml

@@ -1,15 +1,22 @@
 model_list:
-  - model_name: zephyr-alpha
+  - model_name: gpt-4
-    litellm_params: # params for litellm.completion() - https://docs.litellm.ai/docs/completion/input#input---request-body
-      model: huggingface/HuggingFaceH4/zephyr-7b-alpha
-      api_base: http://0.0.0.0:8001
-  - model_name: zephyr-beta
     litellm_params:
-      model: huggingface/HuggingFaceH4/zephyr-7b-beta
+      model: azure/chatgpt-v-2
-      api_base: https://<my-hosted-endpoint>
+      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
-  - model_name: deepseek-coder:latest
+      api_version: "2023-05-15"
+      api_key: 
+  - model_name: gpt-4
     litellm_params:
-      model: ollama/deepseek-coder:latest
+      model: azure/gpt-4
+      api_key: 
+      api_base: https://openai-gpt-4-test-v-2.openai.azure.com/
+  - model_name: gpt-4
+    litellm_params:
+      model: azure/gpt-4
+      api_key: 
+      api_base: https://openai-gpt-4-test-v-2.openai.azure.com/
+
+
 
 litellm_settings:
   drop_params: True

proxy_server_config.yaml

@@ -0,0 +1,34 @@
+model_list:
+  - model_name: gpt-4
+    litellm_params:
+      model: azure/chatgpt-v-2
+      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
+      api_version: "2023-05-15"
+      api_key: 
+      rpm: 200
+  - model_name: gpt-4
+    litellm_params:
+      model: azure/gpt-4
+      api_key: 
+      api_base: https://openai-gpt-4-test-v-2.openai.azure.com/
+      rpm: 100
+  - model_name: gpt-4
+    litellm_params:
+      model: azure/gpt-4
+      api_key: 
+      api_base: https://openai-gpt-4-test-v-2.openai.azure.com/
+      rpm: 10
+
+litellm_settings:
+  drop_params: True
+  set_verbose: True
+
+general_settings: 
+  # master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234)
+  # database_url: "postgresql://<user>:<password>@<host>:<port>/<dbname>" # [OPTIONAL] use for token-based auth to proxy
+
+environment_variables:
+  # settings for using redis caching
+  # REDIS_HOST: redis-16337.c322.us-east-1-2.ec2.cloud.redislabs.com
+  # REDIS_PORT: "16337"
+  # REDIS_PASSWORD: 

router_config_template.yaml

@@ -1,30 +0,0 @@
-# Global settings for the litellm module
-litellm_settings:
-  drop_params: True
-  # failure_callbacks: ["sentry"]
-
-# Model-specific settings
-model_list: # refer to https://docs.litellm.ai/docs/routing
-  - model_name: gpt-3.5-turbo
-    litellm_params:  # parameters for litellm.completion() 
-      model: azure/chatgpt-v-2 # azure/<your-deployment-name>
-      api_key: your_azure_api_key
-      api_version: your_azure_api_version
-      api_base: your_azure_api_base
-    tpm: 240000 # [OPTIONAL] To load balance between multiple deployments
-    rpm: 1800 # [OPTIONAL] To load balance between multiple deployments
-  - model_name: mistral
-    litellm_params:
-      model: ollama/mistral
-      api_base: my_ollama_api_base
-  - model_name: gpt-3.5-turbo
-    litellm_params:
-      model: gpt-3.5-turbo
-      api_key: your_openai_api_key
-    tpm: 1000000 # [OPTIONAL] REPLACE with your openai tpm
-    rpm: 9000 # [OPTIONAL] REPLACE with your openai rpm
-
-environment_variables:
-  REDIS_HOST: your_redis_host
-  REDIS_PASSWORD: your_redis_password
-  REDIS_PORT: your_redis_port