39 lines
2.4 KiB
YAML
39 lines
2.4 KiB
YAML
general_settings:
|
|
# completion_model: string
|
|
store_prompts_in_spend_logs: true
|
|
forward_client_headers_to_llm_api: true
|
|
disable_spend_logs: false # turn off writing each transaction to the db
|
|
disable_master_key_return: false # turn off returning master key on UI (checked on '/user/info' endpoint)
|
|
disable_retry_on_max_parallel_request_limit_error: false # turn off retries when max parallel request limit is reached
|
|
disable_reset_budget: false # turn off reset budget scheduled task
|
|
disable_adding_master_key_hash_to_db: false # turn off storing master key hash in db, for spend tracking
|
|
disable_responses_id_security: false # turn off response ID security checks that prevent users from accessing other users' responses
|
|
enable_jwt_auth: false # allow proxy admin to auth in via jwt tokens with 'litellm_proxy_admin' in claims
|
|
enforce_user_param: false # requires all openai endpoint requests to have a 'user' param
|
|
reject_clientside_metadata_tags: false # if true, rejects requests with client-side 'metadata.tags' to prevent users from influencing budgets
|
|
# allowed_routes: ["route1", "route2"] # list of allowed proxy API routes - a user can access. (currently JWT-Auth only)
|
|
# key_management_system: google_kms # either google_kms or azure_kms
|
|
default_team_disabled: true
|
|
# master_key: string
|
|
maximum_spend_logs_retention_period: 30d # The maximum time to retain spend logs before deletion.
|
|
maximum_spend_logs_retention_interval: 1d # interval in which the spend log cleanup task should run in.
|
|
|
|
# Database Settings
|
|
# database_url: string
|
|
database_connection_pool_limit: 10 # default 10
|
|
database_connection_timeout: 60 # default 60s
|
|
allow_requests_on_db_unavailable: true # if true, will allow requests that can not connect to the DB to verify Virtual Key to still work
|
|
|
|
# custom_auth: string
|
|
max_parallel_requests: 10 # the max parallel requests allowed per deployment
|
|
global_max_parallel_requests: 100 # the max parallel requests allowed on the proxy all up
|
|
infer_model_from_keys: true
|
|
background_health_checks: false
|
|
health_check_interval: 300
|
|
# alerting: ["slack", "email"]
|
|
# alerting_threshold: 0
|
|
use_client_credentials_pass_through_routes: true # use client credentials for all pass through routes like "/vertex-ai", /bedrock/. When this is True Virtual Key auth will not be applied on these endpoints
|
|
|
|
callback_settings:
|
|
otel:
|
|
message_logging: true # OTEL logging callback specific settings |