AWS, Document and K-nearest Neighbors

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

AWS Machine Learning Blog

NOVEMBER 13, 2024

Prerequisites To implement the proposed solution, make sure that you have the following: An AWS account and a working knowledge of FMs, Amazon Bedrock , Amazon SageMaker , Amazon OpenSearch Service , Amazon S3 , and AWS Identity and Access Management (IAM). Amazon Titan Multimodal Embeddings model access in Amazon Bedrock.

AWS

AWS Database K-nearest Neighbors AI

Build a Search Engine: Setting Up AWS OpenSearch

Flipboard

MAY 5, 2025

Home Table of Contents Build a Search Engine: Setting Up AWS OpenSearch Introduction What Is AWS OpenSearch? What AWS OpenSearch Is Commonly Used For Key Features of AWS OpenSearch How Does AWS OpenSearch Work? Why Use AWS OpenSearch for Semantic Search? Looking for the source code to this post?

AWS

AWS Clustering Deep Learning Deep Learning

Build a Search Engine: Semantic Search System Using OpenSearch

PyImageSearch

MAY 19, 2025

In this tutorial, well explore how OpenSearch performs k-NN (k-Nearest Neighbor) search on embeddings. Beyond Keyword Matching) Traditional keyword-based search works by matching exact words in a query to those present in indexed documents. The search is based on vector distance (e.g.,

K-nearest Neighbors

K-nearest Neighbors AWS Deep Learning Deep Learning

Webinars

What’s New in Apache Airflow® 3.0—And How Will It Reshape Your Data Workflows?

MORE WEBINARS

Enhancing Search Relevancy with Cohere Rerank 3.5 and Amazon OpenSearch Service

Flipboard

DECEMBER 18, 2024

Amazon OpenSearch Service Amazon OpenSearch Service is a fully managed service that simplifies the deployment, operation, and scaling of OpenSearch in the AWS Cloud to provide powerful search and analytics capabilities. Lexical search relies on exact keyword matching between the query and documents.

K-nearest Neighbors

K-nearest Neighbors AWS ML ML

Build cost-effective RAG applications with Binary Embeddings in Amazon Titan Text Embeddings V2, Amazon OpenSearch Serverless, and Amazon Bedrock Knowledge Bases

AWS Machine Learning Blog

NOVEMBER 18, 2024

Amazon Titan Text Embeddings models generate meaningful semantic representations of documents, paragraphs, and sentences. It supports exact and approximate nearest-neighbor algorithms and multiple storage and matching engines. RAG helps FMs deliver more relevant, accurate, and customized responses.

K-nearest Neighbors

K-nearest Neighbors AWS ML ML

Build a Search Engine: Deploy Models and Index Data in AWS OpenSearch

PyImageSearch

MAY 12, 2025

Home Table of Contents Build a Search Engine: Deploy Models and Index Data in AWS OpenSearch Introduction What Will We Do in This Blog? However, we will also provide AWS OpenSearch instructions so you can apply the same setup in the cloud. Why Are We Using Vector Embeddings? What’s Coming Next? Why Are We Using Vector Embeddings?

AWS

AWS K-nearest Neighbors Deep Learning Deep Learning

Retrieval-Augmented Generation with LangChain, Amazon SageMaker JumpStart, and MongoDB Atlas semantic search

Flipboard

NOVEMBER 17, 2023

The Retrieval-Augmented Generation (RAG) framework augments prompts with external data from multiple sources, such as document repositories, databases, or APIs, to make foundation models effective for domain-specific tasks. MongoDB Atlas Vector Search uses a technique called k-nearest neighbors (k-NN) to search for similar vectors.

K-nearest Neighbors

K-nearest Neighbors AWS Clustering Database

Benchmarking Amazon Nova and GPT-4o models with FloTorch

AWS Machine Learning Blog

MARCH 11, 2025

OpenAI launched GPT-4o in May 2024, and Amazon introduced Amazon Nova models at AWS re:Invent in December 2024. One of the most critical applications for LLMs today is Retrieval Augmented Generation (RAG), which enables AI models to ground responses in enterprise knowledge bases such as PDFs, internal documents, and structured data.

K-nearest Neighbors

K-nearest Neighbors AWS Database AI

AWS empowers sales teams using generative AI solution built on Amazon Bedrock

AWS Machine Learning Blog

AUGUST 26, 2024

At AWS, we are transforming our seller and customer journeys by using generative artificial intelligence (AI) across the sales lifecycle. It will be able to answer questions, generate content, and facilitate bidirectional interactions, all while continuously using internal AWS and external data to deliver timely, personalized insights.

AWS

AWS AI AI K-nearest Neighbors

Boosting RAG-based intelligent document assistants using entity extraction, SQL querying, and agents with Amazon Bedrock

AWS Machine Learning Blog

DECEMBER 6, 2023

Such data often lacks the specialized knowledge contained in internal documents available in modern businesses, which is typically needed to get accurate answers in domains such as pharmaceutical research, financial investigation, and customer support. For example, imagine that you are planning next year’s strategy of an investment company.

SQL

SQL AWS Analytics Analytics

How Druva used Amazon Bedrock to address foundation model complexity when building Dru, Druva’s backup AI copilot

AWS Machine Learning Blog

NOVEMBER 1, 2024

Intelligent responses and a direct conduit to Druva’s documentation – Users can gain in-depth knowledge about product features and functionalities without manual searches or watching training videos. The FM resides in a separate AWS account and virtual private cloud (VPC) from the backend services.

Python

Python AI AI K-nearest Neighbors

From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 1

AWS Machine Learning Blog

OCTOBER 24, 2024

The AWS Generative AI Innovation Center (GenAIIC) is a team of AWS science and strategy experts who have deep knowledge of generative AI. They help AWS customers jumpstart their generative AI journey by building proofs of concept that use generative AI to bring business value.

AWS

AWS K-nearest Neighbors Database AI

Build a secure enterprise application with Generative AI and RAG using Amazon SageMaker JumpStart

AWS Machine Learning Blog

SEPTEMBER 6, 2023

With generative AI on AWS, you can reinvent your applications, create entirely new customer experiences, and improve overall productivity. You can use this post as a reference to build secure enterprise applications in the Generative AI domain using AWS services. An Amazon Simple Storage Service (Amazon S3) bucket.

AWS

AWS K-nearest Neighbors AI AI

Semantic image search for articles using Amazon Rekognition, Amazon SageMaker foundation models, and Amazon OpenSearch Service

AWS Machine Learning Blog

SEPTEMBER 8, 2023

It also relies on the images in the repository being tagged correctly, which can also be automated (for a customer success story, refer to Aller Media Finds Success with KeyCore and AWS ). In this post, we demonstrate how to use Amazon Rekognition , Amazon SageMaker JumpStart , and Amazon OpenSearch Service to solve this business problem.

K-nearest Neighbors

K-nearest Neighbors AWS ML ML

Talk to your slide deck using multimodal foundation models on Amazon Bedrock – Part 3

AWS Machine Learning Blog

DECEMBER 10, 2024

Part 1 uses AWS services including Amazon Bedrock , Amazon SageMaker , and Amazon OpenSearch Serverless. We performed a k-nearest neighbor (k-NN) search to retrieve the most relevant embedding matching the question. You can do this by deleting the stacks using the AWS CloudFormation console. 13636-13645.

AWS

AWS K-nearest Neighbors Database ML

From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 2

AWS Machine Learning Blog

NOVEMBER 15, 2024

This centralized system consolidates a wide range of data sources, including detailed reports, FAQs, and technical documents. The system integrates structured data, such as tables containing product properties and specifications, with unstructured text documents that provide in-depth product descriptions and usage guidelines.

Database

Database SQL Data Analysis Data Analysis

How IDIADA optimized its intelligent chatbot with Amazon Bedrock

AWS Machine Learning Blog

FEBRUARY 25, 2025

These included document translations, inquiries about IDIADAs internal services, file uploads, and other specialized requests. This approach allows for tailored responses and processes for different types of user needs, whether its a simple question, a document translation, or a complex inquiry about IDIADAs services.

Algorithm

Algorithm Machine Learning Machine Learning K-nearest Neighbors

Talk to your slide deck using multimodal foundation models hosted on Amazon Bedrock and Amazon SageMaker – Part 1

AWS Machine Learning Blog

JANUARY 30, 2024

and AWS services including Amazon Bedrock and Amazon SageMaker to perform similar generative tasks on multimodal data. In this post, we use the slide deck titled Train and deploy Stable Diffusion using AWS Trainium & AWS Inferentia from the AWS Summit in Toronto, June 2023, to demonstrate the solution.

AWS

AWS ML ML K-nearest Neighbors

Implement serverless semantic search of image and live video with Amazon Titan Multimodal Embeddings

AWS Machine Learning Blog

JUNE 3, 2024

Kinesis Video Streams makes it straightforward to securely stream video from connected devices to AWS for analytics, machine learning (ML), playback, and other processing. This solution was created with AWS Amplify. It enables real-time video ingestion, storage, encoding, and streaming across devices.

AWS

AWS K-nearest Neighbors ML ML

Talk to your slide deck using multimodal foundation models hosted on Amazon Bedrock and Amazon SageMaker – Part 2

AWS Machine Learning Blog

APRIL 19, 2024

We used AWS services including Amazon Bedrock , Amazon SageMaker , and Amazon OpenSearch Serverless in this solution. In this series, we use the slide deck Train and deploy Stable Diffusion using AWS Trainium & AWS Inferentia from the AWS Summit in Toronto, June 2023 to demonstrate the solution.

AWS

AWS ML ML Database

Customizing coding companions for organizations

AWS Machine Learning Blog

NOVEMBER 9, 2023

This benefits enterprise software development and helps overcome the following challenges: Sparse documentation or information for internal libraries and APIs that forces developers to spend time examining previously written code to replicate usage. Xiaofei Ma is an Applied Science Manager in AWS AI Labs.

AWS

AWS Natural Language Processing K-nearest Neighbors Computer Science

Power recommendations and search using an IMDb knowledge graph – Part 3

AWS Machine Learning Blog

JANUARY 6, 2023

Many AWS media and entertainment customers license IMDb data through AWS Data Exchange to improve content discovery and increase customer engagement and retention. We downloaded the data from AWS Data Exchange and processed it in AWS Glue to generate KG files. Background. Solution overview. Launch solution resources.

AWS

AWS ML ML Machine Learning

Use DeepSeek with Amazon OpenSearch Service vector database and Amazon SageMaker

Flipboard

FEBRUARY 7, 2025

You will execute scripts to create an AWS Identity and Access Management (IAM) role for invoking SageMaker, and a role for your user to create a connector to SageMaker. You will create a connector to SageMaker with Amazon Titan Text Embeddings V2 to create embeddings for a set of documents with population statistics.

Database

Database AWS Python ML

Implement unified text and image search with a CLIP model using Amazon SageMaker and Amazon OpenSearch Service

AWS Machine Learning Blog

APRIL 5, 2023

Implementing this unified image and text search application consists of two phases: k-NN reference index – In this phase, you pass a set of corpus documents or product images through a CLIP model to encode them into embeddings. You save those embeddings into a k-NN index in OpenSearch Service. bin/bash MODEL_NAME=RN50.pt

ML

ML ML AWS K-nearest Neighbors

Build a crop segmentation machine learning model with Planet data and Amazon SageMaker geospatial capabilities

AWS Machine Learning Blog

SEPTEMBER 29, 2023

In late 2023, Planet announced a partnership with AWS to make its geospatial data available through Amazon SageMaker. In this analysis, we use a K-nearest neighbors (KNN) model to conduct crop segmentation, and we compare these results with ground truth imagery on an agricultural region.

Machine Learning

Machine Learning Machine Learning ML ML

Using Amazon OpenSearch ML connector APIs

Flipboard

MAY 30, 2025

In this post, we show you how to use this connector to invoke the LangDetect API to detect the languages of ingested documents. The second connector we demonstrate is the Amazon Bedrock connector to invoke the Amazon Titan Text Embeddings v2 model so that you can create embeddings from ingested documents and perform semantic search.

ML

ML ML AWS K-nearest Neighbors

Data Science Current

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

Build a Search Engine: Setting Up AWS OpenSearch

Webinars

Trending Sources

Build a Search Engine: Semantic Search System Using OpenSearch

Webinars

Enhancing Search Relevancy with Cohere Rerank 3.5 and Amazon OpenSearch Service

Build cost-effective RAG applications with Binary Embeddings in Amazon Titan Text Embeddings V2, Amazon OpenSearch Serverless, and Amazon Bedrock Knowledge Bases

Build a Search Engine: Deploy Models and Index Data in AWS OpenSearch

Retrieval-Augmented Generation with LangChain, Amazon SageMaker JumpStart, and MongoDB Atlas semantic search

Benchmarking Amazon Nova and GPT-4o models with FloTorch

AWS empowers sales teams using generative AI solution built on Amazon Bedrock

Boosting RAG-based intelligent document assistants using entity extraction, SQL querying, and agents with Amazon Bedrock

How Druva used Amazon Bedrock to address foundation model complexity when building Dru, Druva’s backup AI copilot

From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 1

Build a secure enterprise application with Generative AI and RAG using Amazon SageMaker JumpStart

Semantic image search for articles using Amazon Rekognition, Amazon SageMaker foundation models, and Amazon OpenSearch Service

Talk to your slide deck using multimodal foundation models on Amazon Bedrock – Part 3

From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 2

How IDIADA optimized its intelligent chatbot with Amazon Bedrock

Talk to your slide deck using multimodal foundation models hosted on Amazon Bedrock and Amazon SageMaker – Part 1

Implement serverless semantic search of image and live video with Amazon Titan Multimodal Embeddings

Talk to your slide deck using multimodal foundation models hosted on Amazon Bedrock and Amazon SageMaker – Part 2

Customizing coding companions for organizations

Power recommendations and search using an IMDb knowledge graph – Part 3

Use DeepSeek with Amazon OpenSearch Service vector database and Amazon SageMaker

Implement unified text and image search with a CLIP model using Amazon SageMaker and Amazon OpenSearch Service

Build a crop segmentation machine learning model with Planet data and Amazon SageMaker geospatial capabilities

Using Amazon OpenSearch ML connector APIs

Stay Connected