Styled content generation with Bedrock
StellarStack’s developer-relations team is writing blog content. You’ll build a system prompt that tells Claude to use a professional-yet-friendly voice when explaining cloud best practices to StellarStack users.
The json and boto3 libraries, as well as the bedrock client, are preloaded.
This exercise is part of the course
Introduction to Amazon Bedrock
Exercise instructions
- Use values from the
prompt_templatedictionary to build the final prompt.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
prompt_template = {
"tone": "Write in a professional but friendly tone.",
"task": "Write a blog post about",
"topic": "multi-cloud best practices for StellarStack users"
}
# Use the dictionary values to build the prompt
prompt = f"{prompt_template['____']}\n{prompt_template['____']} {prompt_template['____']}"
response = bedrock.invoke_model(modelId="anthropic.claude-3-5-sonnet-20240620-v1:0",
body=json.dumps({"anthropic_version": "bedrock-2023-05-31", "max_tokens": 100,
"messages": [{"role": "user", "content": [{"type": "text", "text": prompt}]}]}))
print(json.loads(response["body"].read().decode())["content"][0]["text"])