scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

docs(call_hooks.md): add async_moderation_hook to docs

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-17 09:40:34 -08:00 • committed by ishaan-jaff
parent 7248b8373a
commit f35c340462
1 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
docs/my-website/docs/proxy/call_hooks.md
View file

@ -78,7 +78,7 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
```
## *NEW* async_moderation_hook
## [BETA] *NEW* async_moderation_hook
Run a moderation check in parallel to the actual LLM API call.
@ -89,6 +89,12 @@ In your Custom Handler add a new `async_moderation_hook` function
- If your `async_moderation_hook` raises an Exception, we will return that to the user.
:::info
We might need to update the function schema in the future, to support multiple endpoints (e.g. accept a call_type). Please keep that in mind, while trying this feature
:::
See a complete example with our [Llama Guard content moderation hook](https://github.com/BerriAI/litellm/blob/main/enterprise/hooks/llama_guard.py)
```python