Controlling output with top_p and max_tokens
The marketing team now wants two versions of a story about ChefBot, the flagship cooking robot: a concise briefing for investors and a more creative “behind-the-scenes” blog post.
In this exercise, the boto3
and json
libraries, and the bedrock
client, have been pre-imported.
This exercise is part of the course
Introduction to Amazon Bedrock
Exercise instructions
- Generate a concise story using a low
top_p
and lowmax_tokens
and a more creative story using a hightop_p
and highmax_tokens
, keepingmax_tokens
to a maximum of 200.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
def generate_story_with_params(bedrock, top_p, max_tokens):
messages = [{"role": "user",
"content": "Write a story about ChefBot writing a bestselling AI-powered cookbook memoir."}]
request_body=json.dumps({"anthropic_version": "bedrock-2023-05-31", "max_tokens": max_tokens,
"top_p": top_p, "messages": messages})
response = bedrock.invoke_model(body=request_body, modelId='anthropic.claude-3-5-sonnet-20240620-v1:0')
response_body = json.loads(response.get('body').read().decode())
return response_body["content"][0]["text"]
# Modify the parameters to create the two stories
short_focused = generate_story_with_params(bedrock, ____, ____)
long_diverse = generate_story_with_params(bedrock, ____, ____)
print("More focused: ", short_focused, "More creative: ", long_diverse)