- Lab
-
Libraries: If you want this lab, consider one of these libraries.
- Cloud
- Data
Cache Bedrock Responses with DynamoDB
While inspecting your Bedrock invocation logs, it is revealed that many calls to your customer chatbot–Globomantics Ask–are identical or near-identical prompts. In this lab, you will add a semantic-similarity-based response cache to a Bedrock-backed FAQ assistant using Amazon DynamoDB's native vector search. You will store model responses alongside prompt embeddings, retrieve cached answers for semantically similar prompts, and validate that cache hits avoid repeated Amazon Bedrock model calls.
Lab Info
Table of Contents
-
Challenge
Inspect the Bedrock model invocation flow and storage resources
- Review the globomantics-ask function code, and locate the stubbed caching sections.
- Invoke the function twice from CloudShell with the same prompt, and observe that both invocations report a model call.
-
Challenge
Store model responses in a semantic cache
- Create a
globomantics-prompt-cacheDynamoDB table, and add a vector index on the prompt embedding attribute. - Complete the embedding and cache-write sections of the function code: In the globomantics-ask Lambda function, create a
CACHE_TABLE_NAMEenvironment variable with a value ofglobomantics-prompt-cache. - Confirm a cached item containing the embedding and response appears in the table.
- Create a
-
Challenge
Retrieve cached responses for semantically similar prompts
- Complete the cache-lookup section so the function searches the vector index before invoking the model.
- Invoke the function with a paraphrased prompt and confirm the response is served from the cache.
-
Challenge
Validate cache behavior by comparing uncached and cached request handling
- Compare the source, latency, and hit-count fields between uncached and cached invocations in CloudShell.
- Ensure your initial cached prompt is exactly
How do I reset my Globomantics account password? - Confirm an unrelated prompt misses the cache and triggers a model invocation.
Real skill practice before real-world application
Hands-on Labs are real environments created by industry experts to help you learn. These environments help you gain knowledge and experience, practice without compromising your system, test without risk, destroy without fear, and let you learn from your mistakes. Hands-on Labs: practice your skills before delivering in the real world.
Learn by doing
Engage hands-on with the tools and technologies you’re learning. You pick the skill, we provide the credentials and environment.
Follow your guide
All labs have detailed instructions and objectives, guiding you through the learning process and ensuring you understand every step.
Turn time into mastery
On average, you retain 75% more of your learning if you take time to practice. Hands-on labs set you up for success to make those skills stick.