QuestionQ14

Foundation Model Integration, Data Management, and Compliance

A company is developing a legal-research AI assistant that uses Amazon Bedrock with an Anthropic Claude foundation model (FM). The AI assistant must retrieve highly relevant case-law documents to augment the FM’s responses. It must recognize semantic relationships among legal concepts, specific legal terminology, and citations. The AI assistant must operate quickly and return precise results.

Which solution meets these requirements?

Explanation

Amazon OpenSearch Service hybrid search combines vector-based semantic retrieval with keyword search, enabling retrieval based on both conceptual legal relationships and exact legal terminology or citations. An Amazon Bedrock reranker evaluates and reorders the retrieved documents by query relevance, improving precision and allowing fewer, more relevant results to be passed to the foundation model, which can also reduce latency.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!