Configuring Amazon Bedrock services

Documentation Integrations
1

:bookmark: This guide explains how to configure API keys for Amazon Bedrock to enable Discourse AI features that require 3rd party LLM keys.

:person_raising_hand: Required user level: Administrator

In this example, we are using Amazon Bedrock to generate the keys.

Note: You will require a paid plan and configured api keys

Platforms will always change so this guide may not reflect 100% process.

Obtain API keys

Configuring keys on Amazon Bedrock is a somewhat more complicated than most other providers. You will likely need to be versed with concepts such as IAM roles and more. Instruction on how to obtain keys is at:

What bedrock models does Discourse AI support?

Discourse AI supports all Anthropic Claude models and all Nova language models (Micro / Lite and Pro)

These models are supported with images, videos and tool calling (xml and native).

Here are some key model ids:

Nova:

  • amazon.nova-pro-v1:0
  • amazon.nova-lite-v1:0
  • amazon.nova-micro-v1:0

Claude:

  • anthropic.claude-sonnet-4-6
  • anthropic.claude-opus-4-6-v1
  • anthropic.claude-haiku-4-5-20251001-v1:0
  • And many more

For the full and up-to-date list of supported Claude model IDs, see the bedrock_model_id method in the source code. Additionally, any model name not explicitly mapped will be passed through as-is, allowing you to use newer model IDs directly.

Keep in mind not all models are available in all regions, check your bedrock configuration page.

Using API keys for Discourse AI

  1. Go to Admin → Plugins → AI → LLMs tab
  2. Click on the Set up button on “Manual configuration”
  3. Enter all model settings:

The image displays a form for configuring a tool that involves settings for an Amazon Nova Pro model on AWS Bedrock, including model ID, provider, API key, access key ID, region, tokenizer, and other options. (Captioned by AI)
The image displays a form for configuring a tool that involves settings for an Amazon Nova Pro model on AWS Bedrock, including model ID, provider, API key, access key ID, region, tokenizer, and other options. (Captioned by AI)629×1127 64.5 KB

Discourse AI supports two authentication methods for Bedrock:

  • Static access keys: Provide an API key (secret access key), an access key ID, and a region.
  • IAM role-based auth: Provide a role ARN and a region. This uses AWS STS AssumeRole for automatic credential rotation.

You must configure either an access key ID or a role ARN (along with a region) for authentication.

As a tokenizer you can use the OpenAiTokenizer for Nova and the AnthropicTokenizer for Claude based models.

Should I disable native tool support or not?

Discourse ships with native tool and xml tool based configurations, in some cases XML tools outperform native tool implementation, you should experiment to find which configuration works best for you.

3 Likes
Amazon Nova support for Discourse AI
Discourse AI
Managing AI credentials