tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-21 04:19:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(azure_content_guardrails.md): add doc on azure content guardrails

Browse Source
This commit is contained in:
Krrish Dholakia
2025-07-06 21:42:58 -07:00
parent 55ecb543f2
commit 4d718f97ef
1 changed files with 29 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/proxy/guardrails/azure_content_guardrail.md
+29
View File
@@ -71,6 +71,35 @@ curl -i http://localhost:4000/v1/chat/completions \
}'
```
## Supported Params
### Common Params
- `api_key` - str - Azure Content Safety API key
- `api_base` - str - Azure Content Safety API base URL
- `default_on` - bool - Whether to run the guardrail by default. Default is `false`.
- `mode` - Union[str, list[str]] - Mode to run the guardrail. Either `pre_call` or `post_call`. Default is `pre_call`.
### Azure Text Moderation
- `severity_threshold` - int - Severity threshold for the Azure Content Safety Text Moderation guardrail across all categories
- `severity_threshold_by_category` - Dict[AzureHarmCategories, int] - Severity threshold by category for the Azure Content Safety Text Moderation guardrail. See list of categories - https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/harm-categories?tabs=warning
- `categories` - List[AzureHarmCategories] - Categories to scan for the Azure Content Safety Text Moderation guardrail. See list of categories - https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/harm-categories?tabs=warning
- `blocklistNames` - List[str] - Blocklist names to scan for the Azure Content Safety Text Moderation guardrail. Learn more - https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-text
- `haltOnBlocklistHit` - bool - Whether to halt the request if a blocklist hit is detected
- `outputType` - Literal["FourSeverityLevels", "EightSeverityLevels"] - Output type for the Azure Content Safety Text Moderation guardrail. Learn more - https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-text
AzureHarmCategories:
- Hate
- SelfHarm
- Sexual
- Violence
### Azure Prompt Shield Only
n/a
## Further Reading