AI-200: Developing AI Cloud Solutions on AzureDemo

Question

Embeddings are stored in Redis with keys formatted as doc:(id). Some embeddings are accessed frequently, while others are rarely used.

You need to implement a caching strategy that retains only frequently accessed embeddings in memory.

What should you use?

A volatile-ttl
B allkeys-lru
C EXPIRE command
D time-window expiration

Explanation

Redis’s allkeys-lru eviction policy applies to all keys and evicts the least recently used ones when the configured memory limit is reached. This keeps frequently accessed embeddings in memory while allowing rarely used embeddings to be removed.

Learn more

Redis key eviction documentation

AI-200: Developing AI Cloud Solutions on AzureDemo

AstroTutor

Notes

Readiness

QuestionQ16

Community Discussion