Update routing references (#6758)

* Update routing references

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

* Update routing references

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

---------

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
This commit is contained in:
Emmanuel Ferdman 2024-11-16 18:28:44 +02:00 committed by GitHub
parent 73ccbc0f14
commit 9cf3dcbbf3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -281,7 +281,7 @@ Picks the deployment with the lowest response time.
It caches, and updates the response times for deployments based on when a request was sent and received from a deployment.
[**How to test**](https://github.com/BerriAI/litellm/blob/main/litellm/tests/test_lowest_latency_routing.py)
[**How to test**](https://github.com/BerriAI/litellm/blob/main/tests/local_testing/test_lowest_latency_routing.py)
```python
from litellm import Router
@ -567,7 +567,7 @@ print(response)
Picks a deployment with the least number of ongoing calls, it's handling.
[**How to test**](https://github.com/BerriAI/litellm/blob/main/litellm/tests/test_least_busy_routing.py)
[**How to test**](https://github.com/BerriAI/litellm/blob/main/tests/local_testing/test_least_busy_routing.py)
```python
from litellm import Router
@ -1035,7 +1035,7 @@ print(f"response: {response}")
### [Advanced]: Custom Retries, Cooldowns based on Error Type
- Use `RetryPolicy` if you want to set a `num_retries` based on the Exception receieved
- Use `RetryPolicy` if you want to set a `num_retries` based on the Exception received
- Use `AllowedFailsPolicy` to set a custom number of `allowed_fails`/minute before cooling down a deployment
[**See All Exception Types**](https://github.com/BerriAI/litellm/blob/ccda616f2f881375d4e8586c76fe4662909a7d22/litellm/types/router.py#L436)