Building Applications with Vector Databases

Tim Tully

Vector databases use embeddings to capture the meaning of data, gauge the similarity between different pairs of vectors, and navigate large datasets to identify the most similar vectors. In the context of large language models, the primary use of vector databases is retrieval augmented generation (RAG), where text embeddings are stored and retrieved for specific queries.

However, the versatility of vector databases extends beyond RAG and makes it possible to build a wide range of applications quickly with minimal coding.

What's inside

Syllabus

Project Overview

Vector databases use embeddings to capture the meaning of data, gauge the similarity between different pairs of vectors, and navigate large datasets to identify the most similar vectors. In the context of large language models, the primary use of vector databases is retrieval augmented generation (RAG), where text embeddings are stored and retrieved for specific queries. However, the versatility of vector databases extends beyond RAG and makes it possible to build a wide range of applications quickly with minimal coding.In this course, you’ll explore the implementation of six applications using vector databases: (1) Semantic Search: Create a search tool that goes beyond keyword matching, focusing on the meaning of content for efficient text-based searches on a user Q/A dataset. (2) RAG: Enhance your LLM applications by incorporating content from sources the model wasn’t trained on, like answering questions using the Wikipedia dataset. (3) Recommender System: Develop a system that combines semantic search and RAG to recommend topics, and demonstrate it with a news article dataset. (4) Hybrid Search: Build an application that finds items using both images and descriptive text, using an eCommerce dataset as an example. (5) Facial Similarity: Create an app to compare facial features, using a database of public figures to determine the likeness between them.(6) Anomaly Detection: Learn how to build an anomaly detection app that identifies unusual patterns in network communication logs.After taking this course, you’ll be equipped with new ideas for building applications with any vector database.

Save this course

Save Building Applications with Vector Databases to your list so you can find it easily later:

Save

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Building Applications with Vector Databases with these activities:

Review Linear Algebra

Show steps

Strengthen your mathematical foundation by reviewing the fundamentals of linear algebra, providing you with a stronger understanding of the concepts behind vector databases.

Browse courses on Linear Algebra

Show steps

Review the concepts of vector spaces and subspaces.
Practice operations on matrices and vectors.

Compile a List of Vector Database Resources

Show steps

Expand your knowledge by compiling a comprehensive list of vector database resources, including tutorials, documentation, and open-source projects.

Browse courses on Vector Databases

Show steps

Search for vector database resources online.
Review and evaluate the resources.
Organize the resources into a structured format.

Practice Retrieval Augmented Generation

Show steps

Build proficiency in RAG by practicing retrieval techniques, helping you create more effective applications that leverage external knowledge.

Browse courses on Retrieval Augmented Generation (RAG)

Show steps

Identify queries and gather relevant documents.
Implement a retrieval algorithm using a vector database.
Evaluate the performance of your retrieval model.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Practice Semantic Search

Show steps

Reinforce your understanding of semantic search by completing practice exercises aimed at testing your ability to create efficient search tools.

Browse courses on Semantic Search

Show steps

Create a dataset of questions and answers.
Implement a semantic search algorithm using a vector database.
Evaluate the performance of your search tool.

Build an Anomaly Detection App

Show steps

Solidify your understanding of anomaly detection by building an app, allowing you to identify unusual patterns and potential threats in network communication logs.

Browse courses on Anomaly Detection

Show steps

Collect network communication logs.
Extract features from the logs.
Train an anomaly detection model using a vector database.
Develop a user interface for your app.

Build a RAG Application

Show steps

Deepen your understanding of RAG by implementing your own RAG application, enhancing your LLM applications with external knowledge.

Browse courses on Retrieval Augmented Generation (RAG)

Show steps

Choose a topic and gather relevant text data.
Train a text embedding model on the data.
Create a RAG index using the trained model.
Develop a user interface for your RAG application.

Build a Facial Similarity App

Show steps

Enhance your understanding of computer vision by building a facial similarity app, allowing you to compare facial features and determine the likeness between individuals.

Show steps

Gather a dataset of facial images.
Extract facial features using a pre-trained model.
Create a vector database to store the extracted features.
Develop a user interface for your app.

Develop a Hybrid Search System

Show steps

Integrate your knowledge of vector databases and text-based search by creating a hybrid search system, enabling users to search for items using both images and descriptive text.

Browse courses on Hybrid Search

Show steps