Reducing hallucinations in LLM agents with a verified semantic cache using Amazon Bedrock Knowledge Bases
AWS Machine Learning
FEBRUARY 21, 2025
Solution overview Our solution implements a verified semantic cache using the Amazon Bedrock Knowledge Bases Retrieve API to reduce hallucinations in LLM responses while simultaneously improving latency and reducing costs. The function checks the semantic cache (Amazon Bedrock Knowledge Bases) using the Retrieve API.
Let's personalize your content