This course will teach you how to generate embeddings and use vector databases for semantic search apps, recommendations, and multimodal solutions.

Vector Databases- from Embeddings to Applications.png

vdbstreamlitnew.tar.gz

jupyter-wordembeddings

jupyter-sentenceembeddings

jupyter-documentembeddings

jupyter-imageembeddings

jupyter-videoembeddings

jupyter-audioembeddings

jupyter-multimodalembeddings

jupyter-multimodalembeddingsSearchbyText

jupyter-multimodalembeddingsSearchbyImage

jupyter-FineTuningCLIPonCustomData

jupyter-ChromaDBMultimodalEmbeddings

jupyter-MultimodalEmbeddingsWithFineTunedModel

jupyter-appsearchbytextandsearchbyimage

streamlit-musicrecommendationsystem

liveApp-streamlit-musicrecommendationsystem-both

liveApp-streamlit-musicrecommendationsystem-metadata

liveApp-streamlit-musicrecommendationsystem-audio

In this course, you’ll learn to generate embeddings and utilize vector databases to build semantic search apps, enhance recommendation systems, and develop multimodal search solutions.

You’ll begin by understanding the concept of embeddings, vector databases, and their importance in modern world applications. You’ll learn to generate text embeddings with BERT, image and video embeddings with CNNs, audio embeddings with mel spectrogram, and multimodal embeddings with CLIP. You’ll explore the architecture, design choices, and key features of different open-source vector databases, focusing on using Chroma for storage and queries on multimodal data. You’ll learn performance optimization techniques, especially HNSW. You’ll also learn to develop applications, including similarity search applications for images, videos, and audio.

By the end of this course, you will have a solid foundation in vector databases and be able to apply your knowledge to small—and large-scale projects.

Vector Databases: From Embeddings to Applications

Faster retrieval times for structured data

Speed and accuracy in similarity matching

What is the key advantage of using vector databases for similarity search?

What is the key advantage of using vector databases for similarity search?

They cannot handle large volumes of data.

They are optimized for exact match and range queries, not similarity searches.

Why are traditional databases not well-suited for storing and querying vectorized data in modern AI-driven applications?

Why are traditional databases not well-suited for storing and querying vectorized data in modern AI-driven applications?

What indexing technique is commonly used by vector databases to optimize similarity search in high-dimensional spaces?

What indexing technique is commonly used by vector databases to optimize similarity search in high-dimensional spaces?

Which capability distinguishes vector databases from traditional databases in terms of querying?

Which capability distinguishes vector databases from traditional databases in terms of querying?

Which open-source vector database is designed for similarity search and integrates well with large language models (LLMs)?

Which open-source vector database is designed for similarity search and integrates well with large language models (LLMs)?

Which open-source vector database employs a multi-layered architecture and supports hybrid search capabilities combining vector similarity search with structured data filtering?



Which open-source vector database employs a multi-layered architecture and supports hybrid search capabilities combining vector similarity search with structured data filtering?

NSW graphs guarantee the shortest path in all searches.

NSW graphs provide faster query times by efficiently navigating through a small-world network structure.

NSW graphs are only effective for small datasets.

NSW graphs guarantee exact matches in similarity search.

What is the advantage of navigable small world (NSW) graphs in similarity search?

What is the advantage of navigable small world (NSW) graphs in similarity search?

How does the hierarchical navigable small world (HNSW) improve upon NSW graphs?

How does the hierarchical navigable small world (HNSW) improve upon NSW graphs?

**(True or False)** Product Quantization (PQ) is a technique to compress vectors into compact codes to speed up similarity searches in high-dimensional spaces.


(True or False) Product Quantization (PQ) is a technique to compress vectors into compact codes to speed up similarity searches in high-dimensional spaces.

Test your understanding of the open-source vector databases.

Before Getting Started

Getting Started with Vector Databases and Embeddings

Working with Vector Databases

Developing a Music Recommendation System

Wrapping Up

Quiz: Working with Vector Databases