phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix(proxy_server.py): actual implementation of slack soft budget alerting

Browse source
This commit is contained in:
Krrish Dholakia 2024-03-02 18:34:18 -08:00
parent b30cbd0d55
commit ac085a4643
5 changed files with 142 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

3
schema.prisma
View file

@ -23,6 +23,7 @@ model LiteLLM_BudgetTable {
updated_at DateTime @default(now()) @updatedAt @map("updated_at")
updated_by String
organization LiteLLM_OrganizationTable[] // multiple orgs can have the same budget
keys LiteLLM_VerificationToken[] // multiple keys can have the same budget
}
model LiteLLM_OrganizationTable {
@ -90,6 +91,7 @@ model LiteLLM_VerificationToken {
token String @id
key_name String?
key_alias String?
soft_budget_cooldown Boolean @default(false) // key-level state on if budget alerts need to be cooled down
spend Float @default(0.0)
expires DateTime?
models String[]
@ -109,6 +111,7 @@ model LiteLLM_VerificationToken {
model_spend Json @default("{}")
model_max_budget Json @default("{}")
budget_id String?
litellm_budget_table LiteLLM_BudgetTable? @relation(fields: [budget_id], references: [budget_id])
}
// store proxy config.yaml