Topic 1 Question 140
A company is using a large language model (LLM) on Amazon Bedrock to build a chatbot. The chatbot processes customer support requests. To resolve a request, the customer and the chatbot must interact a few times.
Which solution gives the LLM the ability to use content from previous customer messages?
Turn on model invocation logging to collect messages.
Add messages to the model prompt.
Use Amazon Personalize to save conversation history.
Use Provisioned Throughput for the LLM.
ユーザの投票
コメント(4)
- 正解だと思う選択肢: B
Answer: B. Add messages to the model prompt
Large language models (LLMs) typically rely on the context that is provided directly in the input prompt when generating a response. To give the model the ability to use content from previous customer messages, you need to include those past messages in the prompt for each new inference call. This approach ensures that the model has the necessary context to respond accurately based on prior interactions.
👍 1jerry002182025/02/04 - 正解だと思う選択肢: B
Add messages to the model prompt.
By including the conversation history in the model's prompt, the LLM can maintain context and reference previous interactions to provide coherent and relevant responses. This approach ensures that the chatbot can understand and respond to the customer's requests based on the entire conversation history.
👍 1Jessiii2025/02/11 - 正解だと思う選択肢: B
B is the correct answer. Here's why:
Adding previous messages to the prompt allows the LLM to maintain context across multiple interactions.
👍 1kopper20192025/02/12
シャッフルモード