Amazon Bedrock Knowledge Bases now enables developers to build generative AI applications that can analyze and leverage insights from both textual and visual data, such as images, charts, diagrams, and tables. Bedrock Knowledge Bases offers end-to-end managed Retrieval-Augmented Generation (RAG) workflow that enables customers to create highly accurate, low-latency, secure, and custom generative AI applications by incorporating contextual information from their own data sources. With this launch, Bedrock Knowledge Bases extracts content from both text and visual data, generates semantic embeddings using the selected embedding model, and stores them in the chosen vector store. This enables users to retrieve and generate answers to questions derived not only from text but also from visual data. Additionally, retrieved results now include source attribution for visual data, enhancing transparency and building trust in the generated outputs.
To get started, customers can choose between: Amazon Bedrock Data Automation, a managed service that automatically extracts content from multimodal data (currently in Preview), or FMs such as Claude 3.5 Sonnet or Claude 3 Haiku, with the flexibility to customize the default prompt.
Multimodal data processing with Bedrock Data Automation is available in the US West (Oregon) region in preview. FM-based parsing is supported in all regions where Bedrock Knowledge Bases is available. For details on pricing for using Bedrock Data Automation or FM as a parser, please refer to the pricing page.
To learn more, visit Amazon Bedrock Knowledge Bases product documentation.
Source:: Amazon AWS