Cost-effective document classification using the Amazon Titan Multimodal Embeddings Model

Favorite Organizations across industries want to categorize and extract insights from high volumes of documents of different formats. Manually processing these documents to classify and extract information remains expensive, error prone, and difficult to scale. Advances in generative artificial intelligence (AI) have given rise to intelligent document processing (IDP) solutions

Read More
Shared by AWS Machine Learning April 12, 2024

Knowledge Bases for Amazon Bedrock now supports custom prompts for the RetrieveAndGenerate API and configuration of the maximum number of retrieved results

Favorite With Knowledge Bases for Amazon Bedrock, you can securely connect foundation models (FMs) in Amazon Bedrock to your company data for Retrieval Augmented Generation (RAG). Access to additional data helps the model generate more relevant, context-specific, and accurate responses without retraining the FMs. In this post, we discuss two

Read More
Shared by AWS Machine Learning April 10, 2024

Compelling responses to NTIA’s AI Open Model Weights RFC

Favorite The National Telecommunications and Information Administration (NTIA) posted a request for comments on Dual Use Foundation Artificial Intelligence Models with Widely Available Model Weights, and it has received 362 comments. In addition to the Open Source Initiative’s (OSI) joint letter drafted by Mozilla and the Center for Democracy and

Read More
Shared by voicesofopensource April 9, 2024

Boost inference performance for Mixtral and Llama 2 models with new Amazon SageMaker containers

Favorite In January 2024, Amazon SageMaker launched a new version (0.26.0) of Large Model Inference (LMI) Deep Learning Containers (DLCs). This version offers support for new models (including Mixture of Experts), performance and usability improvements across inference backends, as well as new generation details for increased control and prediction explainability

Read More
Shared by AWS Machine Learning April 9, 2024

Use everyday language to search and retrieve data with Mixtral 8x7B on Amazon SageMaker JumpStart

Favorite With the widespread adoption of generative artificial intelligence (AI) solutions, organizations are trying to use these technologies to make their teams more productive. One exciting use case is enabling natural language interactions with relational databases. Rather than writing complex SQL queries, you can describe in plain language what data

Read More
Shared by AWS Machine Learning April 9, 2024