article thumbnail

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

AWS Machine Learning Blog

We tried different methods, including k-nearest neighbor (k-NN) search of vector embeddings, BM25 with synonyms , and a hybrid of both across fields including API routes, descriptions, and hypothetical questions. Having similar names and synonyms in API routes make this retrieval problem more complex.

Python 112
article thumbnail

Build a Search Engine: Setting Up AWS OpenSearch

Flipboard

Vector and Semantic Search: Leverages machine learning-powered search techniques, including k-NN (k-nearest neighbors) and dense vector embeddings, for applications like AI-driven search, recommendation systems, and similarity search.

AWS 118
professionals

Sign Up for our Newsletter

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

article thumbnail

Practical Tips and Tricks for Developers Building RAG Applications

Towards AI

To demonstrate this concept, I wrote a short demo in just ten lines of Python code using the k-nearest neighbors algorithm (KNN). argsort()] # Get the top k closest indices closest_k_indices = sorted_distances[:k, 1].astype(int)

article thumbnail

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

AWS Machine Learning Blog

For demo purposes, we use approximately 1,600 products. We use the first metadata file in this demo. We use a pretrained ResNet-50 (RN50) model in this demo. We only use the item images and item names in US English. For more details about this dataset, refer to the README. The dataset is hosted in a public S3 bucket.

ML 115
article thumbnail

Build a multimodal social media content generator using Amazon Bedrock

AWS Machine Learning Blog

Testing the Streamlit app in a SageMaker environment is intended for a temporary demo. find_similar_items performs semantic search using the k-nearest neighbors (kNN) algorithm on the input image prompt. In the demo, we use the luxury brand and the fast fashion brand, each with its own preferences and guidelines.

AWS 95
article thumbnail

[Latest] 20+ Top Machine Learning Projects for final year

Mlearning.ai

How to perform Face Recognition using KNN So in this blog, we will see how we can perform Face Recognition using KNN (K-Nearest Neighbors Algorithm) and Haar cascades. Check out the demo here… [link] 21. Check out the demo here… [link] 24. Check out the demo here… [link] 25. This is a simple project.

article thumbnail

[Latest] 20+ Top Machine Learning Projects with Source Code

Mlearning.ai

How to perform Face Recognition using KNN So in this blog, we will see how we can perform Face Recognition using KNN (K-Nearest Neighbors Algorithm) and Haar cascades. Check out the demo here… [link] 21. Check out the demo here… [link] 24. Check out the demo here… [link] 25. This is a simple project.