Making a conversation memory-aware
Continuing work on ChargeBot at ChargeNet, you’ll store each turn of the dialogue and send only the most recent messages to Claude, to maintain conversation context with Amazon Bedrock's Claude model. The bot will manage message history and format the conversation in a way Claude can understand, using only the most recent context.
The boto3 and json libraries, and the ConversationManager class you defined in the previous exercise, have been preloaded.
This exercise is part of the course
Introduction to Amazon Bedrock
Exercise instructions
- Use the
add_message()method to store the user's input. - Send only the last two messages from the history to Claude using the correct message format.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
conversation = ConversationManager()
user_input = "What is the charging speed of your Highway Max station?"
# Add the user input
conversation.____
# Send only the last two messages from conversation history
messages = ____
request_body = json.dumps({"anthropic_version": "bedrock-2023-05-31", "max_tokens": 200, "temperature": 0.2, "messages": messages})
response = conversation.bedrock.invoke_model(modelId="anthropic.claude-3-5-sonnet-20240620-v1:0", body=request_body)
completion = json.loads(response['body'].read().decode())["content"][0]["text"]
conversation.add_message("assistant", completion)
print(completion)