> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langtrace.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS Bedrock

> Langtrace and AWS Bedrock Integration Guide

AWS Bedrock provides access to high-performance foundation models through a unified API. Langtrace integration with AWS Bedrock allows you to capture and analyze interactions with various foundation models, helping you optimize and monitor your AI applications.

<Callout type="warning">
  Langtrace currently only captures traces for requests sent using the converse API.
</Callout>

## Available Models

Before getting started, you'll need to request access to the specific foundation models you plan to use through the AWS Console. Visit [Supported Models](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html) for a list of models available to use with the converse API.

## Setup

### Install Langtrace SDK

Install and [initialize](/quickstart) the SDK in your code.

### Install AWS SDK

Install the AWS SDK for Python/Typescript:

<CodeGroup>
  ```python Python theme={null}
  pip install boto3
  ```

  ```javascript Typescript theme={null}
  npm install @aws-sdk/client-bedrock-runtime
  ```
</CodeGroup>

## Usage Example

<CodeGroup>
  ```python Python theme={null}
  import boto3
  from langtrace_python_sdk import langtrace

  # Initialize Langtrace
  langtrace = Langtrace(
      api_key="LANGTRACE_API_KEY",
  )

  # Initialize Bedrock client
  client = boto3.client(
      service_name='bedrock-runtime',
      region_name='us-east-1',
      aws_access_key_id=<AWS_ACCESS_KEY_ID>,
      aws_secret_access_key=<AWS_SECRET_ACCESS_KEY>,
  )

  # Example usage
  conversation = [
      {
          "role": "user",
          "content": [{"text": "Write a story about a magic backpack."}],
      }
  ]
  response = client.converse(
      modelId=model_id,
      messages=conversation,
      inferenceConfig={"maxTokens":4096,"temperature":0},
      additionalModelRequestFields={"top_k":250}
  )
  response_text = response["output"]["message"]["content"][0]["text"]
  print(response_text)
  ```

  ```javascript Typescript theme={null}
  import * as Langtrace from '@langtrase/typescript-sdk'
  import {
    BedrockRuntimeClient,
    ConverseCommand,
    Message
  } from '@aws-sdk/client-bedrock-runtime'

  // Initialize Langtrace
  Langtrace.init({
    api_key: "LANGTRACE_API_KEY"
  })

  // Initialize Bedrock client
  const bedrock = new BedrockRuntimeClient({ region: "us-east-1" });

  // Example usage
  const userMessage = 'Describe the purpose of a hello world program in one line.'
  const conversation: Message[] = [
    {
      role: 'user',
      content: [{ text: userMessage }]
    }
  ]

  const modelId = 'mistral.mistral-large-2402-v1:0'

  const command = new ConverseCommand({
      modelId,
      messages: conversation,
      inferenceConfig: { maxTokens: 512, temperature: 0.5, topP: 0.9 }
  })


  const response = await client.send(command)
  const responseText = ((response.output?.message?.content?.length) != null) && response.output.message.content[0].text
  console.log(responseText)
  ```
</CodeGroup>

## Troubleshooting

### Common Issues

1. **Model Access**: If you receive a "ResourceNotFoundException", ensure you've requested and been granted access to the model.
2. **Trace Capture**: If traces aren't appearing, verify you're using the converse API and the Langtrace SDK is properly initialized.
3. **Region Availability**: Some models may not be available in all AWS regions. Check the AWS Bedrock documentation for region availability.

### Support

For additional help:

* Visit the [AWS Bedrock documentation](https://docs.aws.amazon.com/bedrock)
* Check the [Langtrace documentation](/docs)
* Contact Langtrace support at [support@langtrace.com](mailto:support@langtrace.com) or [https://discord.langtrace.ai/](https://discord.langtrace.ai/)