litellm-mirror/litellm/proxy/proxy_config.yaml
2024-02-14 17:23:25 -08:00

67 lines
2.3 KiB
YAML

model_list:
- model_name: azure-gpt-3.5
litellm_params:
model: azure/chatgpt-v-2
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY
api_version: "2023-07-01-preview"
model_info:
mode: chat
max_tokens: 4096
base_model: azure/gpt-4-1106-preview
access_groups: ["public"]
- model_name: openai-gpt-3.5
litellm_params:
model: gpt-3.5-turbo
api_key: os.environ/OPENAI_API_KEY
model_info:
access_groups: ["public"]
- model_name: anthropic-claude-v2.1
litellm_params:
model: bedrock/anthropic.claude-v2:1
timeout: 300 # sets a 5 minute timeout
model_info:
access_groups: ["private"]
- model_name: anthropic-claude-v2
litellm_params:
model: bedrock/anthropic.claude-v2
- model_name: bedrock-cohere
litellm_params:
model: bedrock/cohere.command-text-v14
timeout: 0.0001
- 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 # 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_info:
base_model: azure/gpt-4
- model_name: text-moderation-stable
litellm_params:
model: text-moderation-stable
api_key: os.environ/OPENAI_API_KEY
litellm_settings:
fallbacks: [{"openai-gpt-3.5": ["azure-gpt-3.5"]}]
success_callback: ['langfuse']
# setting callback class
# callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
general_settings:
master_key: sk-1234
alerting: ["slack"]
alerting_threshold: 10 # sends alerts if requests hang for 2 seconds
# database_type: "dynamo_db"
# database_args: { # 👈 all args - https://github.com/BerriAI/litellm/blob/befbcbb7ac8f59835ce47415c128decf37aac328/litellm/proxy/_types.py#L190
# "billing_mode": "PAY_PER_REQUEST",
# "region_name": "us-west-2",
# "ssl_verify": False
# }
environment_variables:
# otel: True # OpenTelemetry Logger
# master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234)