article thumbnail

Build a reverse image search engine with Amazon Titan Multimodal Embeddings in Amazon Bedrock and AWS managed services

AWS Machine Learning Blog

It works by analyzing the visual content to find similar images in its database. Store embeddings : Ingest the generated embeddings into an OpenSearch Serverless vector index, which serves as the vector database for the solution. To do so, you can use a vector database. Retrieve images stored in S3 bucket response = s3.list_objects_v2(Bucket=BUCKET_NAME)

AWS 115
article thumbnail

Combine keyword and semantic search for text and images using Amazon Bedrock and Amazon OpenSearch Service

Flipboard

OpenSearch Service is the AWS recommended vector database for Amazon Bedrock. OpenSearch is a distributed open-source search and analytics engine composed of a search engine and vector database. To learn more, see Improve search results for AI using Amazon OpenSearch Service as a vector database with Amazon Bedrock.

AWS 151
professionals

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Implement user-level access control for multi-tenant ML platforms on Amazon SageMaker AI

AWS Machine Learning Blog

Prerequisites Before implementing this solution, make sure your SageMaker Studio domain meets the following criteria: Roles used with SageMaker AI (both SageMaker Studio and roles passed to SageMaker pipelines or processing jobs) have the sts:SetSourceIdentity permission in their trust policy.

ML 62
article thumbnail

Agents as escalators: Real-time AI video monitoring with Amazon Bedrock Agents and video streams

Flipboard

As demonstrated in the following example, the system translates natural language queries about vehicles into SQL, returning structured information from the database. The database connection is configured through a SQL Alchemy engine. Daytime conditions, clear visibility. No suspicious behavior or safety concerns observed.

AWS 142
article thumbnail

Transforming financial analysis with CreditAI on Amazon Bedrock: Octus’s journey with AWS

AWS Machine Learning Blog

It was built using a combination of in-house and external cloud services on Microsoft Azure for large language models (LLMs), Pinecone for vectorized databases, and Amazon Elastic Compute Cloud (Amazon EC2) for embeddings. Opportunities for innovation CreditAI by Octus version 1.x x uses Retrieval Augmented Generation (RAG).

AWS 112
article thumbnail

Enrich your AWS Glue Data Catalog with generative AI metadata using Amazon Bedrock

Flipboard

When you run the crawler, it creates metadata tables that are added to a database you specify or the default database. This approach is ideal for AWS Glue databases with a small number of tables. Fetch information for the database tables from the Data Catalog. Each table represents a single data store. Build the prompt.

AWS 147
article thumbnail

Adobe enhances developer productivity using Amazon Bedrock Knowledge Bases

AWS Machine Learning Blog

This involved creating a pipeline for data ingestion, preprocessing, metadata extraction, and indexing in a vector database. Similarity search and retrieval – The system retrieves the most relevant chunks in the vector database based on similarity scores to the query.

AWS 71