scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 85

docs fix

Browse source
This commit is contained in:
Ishaan Jaffer 2026-02-21 17:27:59 -08:00
parent efebd37183
commit 661c6faac6
1 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
docs/my-website/release_notes/v1.81.14.md
View file

@ -54,14 +54,12 @@ pip install litellm==1.81.14
Browse built-in and partner guardrails organized by use case — competitor blocking, topic filtering, keyword lists, GDPR/EU AI Act compliance, prompt injection detection, and more. Pick a template, customize the parameters (keyword lists, blocked topics, score thresholds), and attach it to a team or key.
![Guardrail Garden](../img/release_notes/guardrail_garden.png)
## 3 New Built-in Guardrails
A competitor name blocker, a topic blocker (keyword and embedding-based), and an insults/keyword filter. All run at the gateway level with no external API call. They're configurable per-team or per-key, and you can swap in AWS Bedrock Guardrails or Azure Content Safety on the same endpoint without changing your application code.
## Compliance Playground
Upload your own dataset or use a pre-built one to measure how a guardrail policy performs before it goes live. See precision, recall, and false positive rate on your actual traffic patterns — so you know how the policy will behave in production before you deploy it.
### Eval results
We benchmark every built-in guardrail against labeled datasets before shipping. Results for the two policies most relevant to topic and keyword blocking (207 investment-question cases, 299 insult cases):
@ -73,6 +71,14 @@ We benchmark every built-in guardrail against labeled datasets before shipping.
For reference, ONNX embedding approaches on the same eval set hit 95–98% precision at 2–20ms latency and require additional dependencies. The built-in content filter uses no ML model — just structured YAML rules with layered matching — so there's nothing to download, no API key needed, and latency is effectively zero.
## Compliance Playground
Upload your own dataset or use a pre-built one to measure how a guardrail policy performs before it goes live. See precision, recall, and false positive rate on your actual traffic patterns — so you know how the policy will behave in production before you deploy it.
![Compliance Playground](../img/release_notes/compliance_playground.png)
---
---