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

docs - alerting test /health/services

Browse source
This commit is contained in:
Ishaan Jaff 2024-05-14 07:47:33 -07:00
parent 901254d31e
commit c4dab4e735
1 changed files with 15 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

24
docs/my-website/docs/proxy/alerting.md
View file

@ -3,19 +3,16 @@
Get alerts for: Get alerts for:
- Hanging LLM api calls - Hanging LLM api calls
- Failed LLM api calls
- Slow LLM api calls - Slow LLM api calls
- Budget Tracking per key/user: - Failed LLM api calls
- When a User/Key crosses their Budget - Budget Tracking per key/user
- When a User/Key is 15% away from crossing their Budget
- Spend Reports - Weekly & Monthly spend per Team, Tag - Spend Reports - Weekly & Monthly spend per Team, Tag
- Failed db read/writes - Failed db read/writes
- Daily Reports:
- **LLM** Top 5 slowest deployments
- **LLM** Top 5 deployments with most failed requests
- **Spend** Weekly & Monthly spend per Team, Tag
As a bonus, you can also get "daily reports" posted to your slack channel.
These reports contain key metrics like:
- Top 5 deployments with most failed requests
- Top 5 slowest deployments
## Quick Start ## Quick Start
@ -52,4 +49,13 @@ environment_variables:
```bash ```bash
$ litellm --config /path/to/config.yaml $ litellm --config /path/to/config.yaml
```
## Testing Alerting is Setup Correctly
Make a GET request to `/health/services`, expect to see a test slack alert in your provided webhook slack channel
```shell
curl -X GET 'http://localhost:4000/health/services?service=slack' \
-H 'Authorization: Bearer sk-1234'
``` ```