You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/en/latest/plugins/ai-aws-content-moderation.md
+27-33
Original file line number
Diff line number
Diff line change
@@ -1,11 +1,11 @@
1
1
---
2
-
title: ai-content-moderation
2
+
title: ai-aws-content-moderation
3
3
keywords:
4
4
- Apache APISIX
5
5
- API Gateway
6
6
- Plugin
7
-
- ai-content-moderation
8
-
description: This document contains information about the Apache APISIX ai-content-moderation Plugin.
7
+
- ai-aws-content-moderation
8
+
description: This document contains information about the Apache APISIX ai-aws-content-moderation Plugin.
9
9
---
10
10
11
11
<!--
@@ -29,23 +29,23 @@ description: This document contains information about the Apache APISIX ai-conte
29
29
30
30
## Description
31
31
32
-
The `ai-content-moderation` plugin processes the request body to check for toxicity and rejects the request if it exceeds the configured threshold.
32
+
The `ai-aws-content-moderation` plugin processes the request body to check for toxicity and rejects the request if it exceeds the configured threshold.
33
33
34
34
**_This plugin must be used in routes that proxy requests to LLMs only._**
35
35
36
36
**_As of now, the plugin only supports the integration with [AWS Comprehend](https://aws.amazon.com/comprehend/) for content moderation. PRs for introducing support for other service providers are welcomed._**
|provider.aws_comprehend.region | Yes | String | AWS region |
45
-
|provider.aws_comprehend.endpoint | No | String | AWS Comprehend service endpoint. Must match the pattern `^https?://`|
46
-
|moderation_categories| No | Object| Key-value pairs of moderation category and their score. In each pair, the key should be one of the `PROFANITY`, `HATE_SPEECH`, `INSULT`, `HARASSMENT_OR_ABUSE`, `SEXUAL`, or `VIOLENCE_OR_THREAT`; and the value should be between 0 and 1 (inclusive).|
47
-
|moderation_threshold| No | Number | The degree to which content is harmful, offensive, or inappropriate. A higher value indicates more toxic content allowed. Range: 0 - 1. Default: 0.5 |
48
-
|llm_provider| Yes| String | Name of the LLM provider that this route will proxy requests to. |
|moderation_categories| No| Object| Key-value pairs of moderation category and their score. In each pair, the key should be one of the `PROFANITY`, `HATE_SPEECH`, `INSULT`, `HARASSMENT_OR_ABUSE`, `SEXUAL`, or `VIOLENCE_OR_THREAT`; and the value should be between 0 and 1 (inclusive).|
48
+
|moderation_threshold| No| Number| The degree to which content is harmful, offensive, or inappropriate. A higher value indicates more toxic content allowed. Range: 0 - 1. Default: 0.5|
0 commit comments