From f683acda61883c8b3f08e8bff69bd0fe63b18d19 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Mon, 11 Mar 2024 13:56:10 -0700 Subject: [PATCH] build: fix default config --- proxy_server_config.yaml | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/proxy_server_config.yaml b/proxy_server_config.yaml index 0976103ef..83bcc0626 100644 --- a/proxy_server_config.yaml +++ b/proxy_server_config.yaml @@ -1,18 +1,16 @@ model_list: - # NOTE: This is the default config users use with Dockerfile. - # DO not expect users to pass os.environ/<> vars here, this will lead to proxy startup failing for them if they don't have the expected env vars - model_name: gpt-3.5-turbo 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: os.environ/AZURE_API_KEY # use `os.environ/AZURE_API_KEY` for production. The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault + api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault - 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: os.environ/AZURE_API_KEY # use `os.environ/AZURE_API_KEY` for production. The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault + api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault - model_name: sagemaker-completion-model litellm_params: model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4 @@ -20,7 +18,7 @@ model_list: - model_name: text-embedding-ada-002 litellm_params: model: azure/azure-embedding-model - api_key: os.environ/AZURE_API_KEY # use `os.environ/AZURE_API_KEY` for production. The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault + api_key: os.environ/AZURE_API_KEY api_base: https://openai-gpt-4-test-v-1.openai.azure.com/ api_version: "2023-05-15" model_info: @@ -28,10 +26,13 @@ model_list: base_model: text-embedding-ada-002 - model_name: dall-e-2 litellm_params: - model: azure/dall-e-2 + model: azure/ api_version: 2023-06-01-preview api_base: https://openai-gpt-4-test-v-1.openai.azure.com/ - api_key: os.environ/AZURE_API_KEY # use `os.environ/AZURE_API_KEY` for production. The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault + api_key: os.environ/AZURE_API_KEY + - model_name: openai-dall-e-3 + litellm_params: + model: dall-e-3 litellm_settings: drop_params: True @@ -39,7 +40,7 @@ litellm_settings: budget_duration: 30d num_retries: 5 request_timeout: 600 -general_settings: +general_settings: master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234) proxy_budget_rescheduler_min_time: 60 proxy_budget_rescheduler_max_time: 64