doc provider budget routing

This commit is contained in:
Ishaan Jaff 2024-11-19 17:28:52 -08:00
parent 7ceee027c8
commit 98a7a37c86
2 changed files with 76 additions and 1 deletions

View file

@ -0,0 +1,75 @@
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
# Provider Budget Routing
Use this to set budgets for LLM Providers - example $100/day for OpenAI, $100/day for Azure.
<Tabs>
<TabItem value="proxy-config" label="LiteLLM Proxy Config.yaml">
```yaml
model_list:
- model_name: gpt-3.5-turbo
litellm_params:
model: openai/gpt-3.5-turbo
api_key: os.environ/OPENAI_API_KEY
- model_name: gpt-3.5-turbo
litellm_params:
model: azure/chatgpt-functioncalling
api_key: os.environ/AZURE_API_KEY
api_version: os.environ/AZURE_API_VERSION
api_base: os.environ/AZURE_API_BASE
router_settings:
routing_strategy: provider-budget-routing
redis_host: <your-redis-host>
redis_password: <your-redis-password>
redis_port: <your-redis-port>
routing_strategy_args:
openai:
budget_limit: 0.000000000001 # float of $ value budget for time period
time_period: 1d # can be 1d, 2d, 30d
azure:
budget_limit: 100
time_period: 1d
anthropic:
budget_limit: 100
time_period: 10d
vertexai:
budget_limit: 100
time_period: 12d
gemini:
budget_limit: 100
time_period: 12d
general_settings:
master_key: sk-1234
```
</TabItem>
<TabItem value="python-sdk" label="Python SDK">
</TabItem>
</Tabs>
#### How provider-budget-routing works
1. **Budget Tracking**:
- Uses Redis to track spend for each provider
- Tracks spend over specified time periods (e.g., "1d", "30d")
- Automatically resets spend after time period expires
2. **Routing Logic**:
- Routes requests to providers under their budget limits
- Skips providers that have exceeded their budget
- If all providers exceed budget, raises an error
3. **Supported Time Periods**:
- Format: "Xd" where X is number of days
- Examples: "1d" (1 day), "30d" (30 days)
4. **Requirements**:
- Redis required for tracking spend across instances
- Provider names must be litellm provider names. See [Supported Providers](https://docs.litellm.ai/docs/providers)

View file

@ -100,7 +100,7 @@ const sidebars = {
{
type: "category",
label: "Routing",
items: ["proxy/load_balancing", "proxy/tag_routing", "proxy/team_based_routing", "proxy/customer_routing",],
items: ["proxy/load_balancing", "proxy/tag_routing", "proxy/provider_budget_routing", "proxy/team_based_routing", "proxy/customer_routing",],
},
{
type: "category",