mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
104 lines
3.7 KiB
YAML
104 lines
3.7 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
|
|
input_cost_per_token: 0.0.00006
|
|
output_cost_per_token: 0.00003
|
|
max_tokens: 4096
|
|
base_model: gpt-3.5-turbo
|
|
- 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_name: gpt-vision
|
|
litellm_params:
|
|
model: azure/gpt-4-vision
|
|
base_url: https://gpt-4-vision-resource.openai.azure.com/openai/deployments/gpt-4-vision/extensions
|
|
api_key: os.environ/AZURE_VISION_API_KEY
|
|
api_version: "2023-09-01-preview"
|
|
dataSources:
|
|
- type: AzureComputerVision
|
|
parameters:
|
|
endpoint: os.environ/AZURE_VISION_ENHANCE_ENDPOINT
|
|
key: os.environ/AZURE_VISION_ENHANCE_KEY
|
|
- model_name: BEDROCK_GROUP
|
|
litellm_params:
|
|
model: bedrock/cohere.command-text-v14
|
|
- model_name: tg-ai
|
|
litellm_params:
|
|
model: together_ai/mistralai/Mistral-7B-Instruct-v0.1
|
|
- model_name: sagemaker
|
|
litellm_params:
|
|
model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4
|
|
- model_name: openai-gpt-3.5
|
|
litellm_params:
|
|
model: gpt-3.5-turbo
|
|
api_key: os.environ/OPENAI_API_KEY
|
|
model_info:
|
|
mode: chat
|
|
- model_name: azure-cloudflare
|
|
litellm_params:
|
|
model: azure/chatgpt-v-2
|
|
api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1
|
|
api_key: os.environ/AZURE_API_KEY
|
|
api_version: "2023-07-01-preview"
|
|
- model_name: azure-embedding-model
|
|
litellm_params:
|
|
model: azure/azure-embedding-model
|
|
api_base: os.environ/AZURE_API_BASE
|
|
api_key: os.environ/AZURE_API_KEY
|
|
api_version: "2023-07-01-preview"
|
|
model_info:
|
|
mode: embedding
|
|
base_model: text-embedding-ada-002
|
|
- model_name: text-embedding-ada-002
|
|
litellm_params:
|
|
model: text-embedding-ada-002
|
|
api_key: os.environ/OPENAI_API_KEY
|
|
model_info:
|
|
mode: embedding
|
|
litellm_settings:
|
|
fallbacks: [{"openai-gpt-3.5": ["azure-gpt-3.5"]}]
|
|
success_callback: ['langfuse']
|
|
max_budget: 10 # global budget for proxy
|
|
max_user_budget: 0.0001
|
|
budget_duration: 30d # global budget duration, will reset after 30d
|
|
default_key_generate_params:
|
|
max_budget: 1.5000
|
|
models: ["azure-gpt-3.5"]
|
|
duration: None
|
|
cache: True # set cache responses to True
|
|
cache_params:
|
|
type: "redis-semantic"
|
|
similarity_threshold: 0.8
|
|
redis_semantic_cache_embedding_model: azure-embedding-model
|
|
upperbound_key_generate_params:
|
|
max_budget: 100
|
|
duration: "30d"
|
|
# 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)
|