Foundation Model Integration, Data Management, and Compliance IV
Explore methods to implement hybrid search combining keyword and vector similarity in OpenSearch. Learn how to select embedding models for multi-document synthesis using Amazon Bedrock. Understand model evaluation and deployment strategies to ensure accuracy and compliance in GenAI applications, and design modular prompt workflows for complex analysis.
We'll cover the following...
Question 16
A GenAI team is implementing a hybrid search for a technical documentation portal. Users often search using exact error codes as well as natural language questions. The system uses Amazon OpenSearch Service as the vector store.
Which approaches should the team implement to support effective hybrid search? (Select any two options.)
A. Combine keyword-based search with vector similarity search in OpenSearch.
B. Use Amazon Bedrock Knowledge Bases without keyword indexing.
C. Store documents in DynamoDB and perform post-retrieval filtering.
D. Apply weighted scoring to merge ...