AI-200: Developing AI Cloud Solutions on AzureDemo

By Microsoft · Question Mode

QuestionQ20

Develop AI solutions by using Azure data management services

You are developing a Retrieval-Augmented Generation (RAG) solution for a company. AI responses and embedding vectors are cached in Redis. Configure Redis to meet these requirements:

  • AI responses must expire exactly 24 hours after they are cached.
  • Cached embeddings must always reflect the current source data.
Select
AI responses must expire exactly 24 hours after they are cached.
Cached embeddings must always reflect the current source data.
Explanation

A Redis TTL automatically removes a key after its configured timeout, so a 24-hour TTL enforces the response cache lifetime. Embeddings are derived from document content; invalidating the related keys when that document changes prevents stale vectors from being served and causes refreshed embeddings to be generated. LRU eviction is memory-pressure based and cannot guarantee freshness or a fixed expiration time.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!