amazonBedrock

Connect the call to an Amazon Bedrock AI agent. Similar to ai() but uses Amazon Bedrock as the LLM backend.

Parameters

prompt

unknown | undefined

The prompt configuration for the Bedrock agent.

SWAIG

Record<string, unknown> | undefined

SWAIG configuration for tool/function definitions.

aiParams

Record<string, unknown> | undefined

AI parameters for the Bedrock session.

globalData

Record<string, unknown> | undefined

Data accessible to the AI and SWAIG functions.

postPrompt

Record<string, unknown> | undefined

Post-prompt configuration.

postPromptUrl

string | undefined

URL to receive the post-prompt result.

Returns

Promise<Record<string, unknown>> — Server response confirming the Bedrock session.

Example

1 import { RelayClient } from '@signalwire/sdk';
2 
3 const client = new RelayClient({
4   project: process.env.SIGNALWIRE_PROJECT_ID!,
5   token: process.env.SIGNALWIRE_API_TOKEN!,
6   contexts: ['default']
7 });
8 
9 client.onCall(async (call) => {
10   await call.answer();
11 
12   // Start an Amazon Bedrock AI agent
13   const result = await call.amazonBedrock({
14     prompt: { text: 'You are a helpful assistant.' },
15     aiParams: { barge_confidence: 0.02 },
16   });
17 });
18 
19 await client.run();

1	import { RelayClient } from '@signalwire/sdk';
2
3	const client = new RelayClient({
4	project: process.env.SIGNALWIRE_PROJECT_ID!,
5	token: process.env.SIGNALWIRE_API_TOKEN!,
6	contexts: ['default']
7	});
8
9	client.onCall(async (call) => {
10	await call.answer();
11
12	// Start an Amazon Bedrock AI agent
13	const result = await call.amazonBedrock({
14	prompt: { text: 'You are a helpful assistant.' },
15	aiParams: { barge_confidence: 0.02 },
16	});
17	});
18
19	await client.run();