aws-samples/Reducing-Hallucinations-in-LLM-Agents-with-a-Verified-Semantic-Cache
This repository contains sample code demonstrating how to implement a verified semantic cache using Amazon Bedrock Knowledge Bases to prevent hallucinations in Large Language Model (LLM) responses while improving latency and reducing costs.
This solution helps developers who are building applications powered by Large Language Models (LLMs) to ensure those applications provide accurate and consistent information. It takes user queries as input and, by intelligently reusing previously verified answers, delivers more reliable LLM responses while also speeding up the application and reducing operational costs. Developers implementing LLM-based chatbots, virtual assistants, or Q&A systems will find this valuable.
No commits in the last 6 months.
Use this if you are developing an LLM-powered application and need to prevent your AI from generating incorrect or 'hallucinated' information, while also improving response times and managing costs.
Not ideal if you are looking for a plug-and-play end-user application or do not have experience with AWS and deploying cloud infrastructure.
Stars
12
Forks
—
Language
Jupyter Notebook
License
MIT-0
Category
Last pushed
Apr 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/aws-samples/Reducing-Hallucinations-in-LLM-Agents-with-a-Verified-Semantic-Cache"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aws-samples/generative-ai-use-cases
Application implementation with business use cases for safely utilizing generative AI in...
aws-samples/serverless-rag-demo
Amazon Bedrock Foundation models with Amazon Opensearch Serverless as a Vector DB
aws-samples/amazon-bedrock-rag
Fully managed RAG solution implemented using Knowledge Bases for Amazon Bedrock
IBM/granite-workshop
Source code for the IBM Granite AI Model Workshop
aws-samples/rag-with-amazon-bedrock-and-opensearch
Opinionated sample on how to build and deploy a RAG application with Amazon Bedrock and OpenSearch