Improve contract search accuracy with auto-generated filters in Amazon Bedrock
In this post, we describe how AIDA works at a high level and how it helps address these challenges — grounding users in the right contracts, under the right legal context, and within the right access boundaries. Specifically, we explore how AIDA uses implicit and explicit filtering, along with metadata-enriched chunking in Amazon Bedrock Knowledge Bases, to dramatically improve contract search…
Amazon Bedrock's AIDA solution utilizes a Retrieval-Augmented Generation (RAG) architecture built on Amazon Bedrock Knowledge Bases to improve contract search accuracy. By leveraging implicit and explicit filtering techniques along with metadata-enriched chunking, the system can generate precise answers to natural language queries across large contract repositories.
The solution starts with document ingestion, where contracts are synced into Amazon Bedrock Knowledge Bases alongside structured metadata files containing key contract attributes such as parties, effective date, termination date, jurisdiction, and other relevant information. Next, a sophisticated chunking mechanism breaks contracts into semantically meaningful segments optimized for retrieval, ensuring each segment has sufficient context while remaining concise enough for efficient processing.
Finally, vector embeddings of the document chunks are stored in a vector database for querying. This architecture enables users to ask questions across large contract repositories while delivering accurate and relevant results grounded in the right contracts, legal context, and access boundaries.
Brief written by urgent.news from AWS Machine Learning's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
