Daniel Madalitso Phiri

Vision for Websites: Training Your Frontend to See

Build web apps that see. Learn how to implement powerful visual search with vector embeddings in just a few lines of code.

Vision for Websites: Training Your Frontend to See
#1about 1 minute

Defining vision as the ability to deduce and understand

The concept of vision for websites is redefined from simply seeing to the ability to deduce, understand, and act on information.

#2about 4 minutes

Demo of a multimodal e-commerce search application

A live demonstration showcases an e-commerce store where users can search for products using both text queries and by uploading images.

#3about 2 minutes

What is multimodality in artificial intelligence?

Multimodality enables search queries to use multiple media types like text, images, and audio to capture more context and improve user interaction.

#4about 2 minutes

Why multimodal AI creates richer user experiences

Multimodal interfaces provide more natural and context-aware interactions, moving beyond simple keyword searches to a more intuitive experience.

#5about 4 minutes

Differentiating generative AI from embedding models

Embedding models encapsulate information into numerical representations (vectors), unlike generative models which create new data.

#6about 4 minutes

How vector search works by measuring distance

Vector search operates by converting a query into an embedding and finding the closest, most semantically similar items in a multidimensional space.

#7about 2 minutes

Creating a unified space for multimodal search

Different data types like text, images, and audio are processed by specific encoders and plotted into a single, unified vector space for cross-modal queries.

#8about 9 minutes

Implementing text-based image search with Weaviate

A code walkthrough demonstrates how to build a text-to-image search feature using a Next.js frontend and a Weaviate backend with a `nearText` query.

#9about 4 minutes

Implementing visual search with an image query

The code for an image-to-image search is explained, showing how a base64 image is sent to the backend to perform a `nearImage` vector search.

#10about 2 minutes

Expanding vision to other creative applications

Beyond e-commerce, multimodal vision can be applied to creative use cases like movie recommenders, educational tools, and map navigation.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Articles

View all articles
DC
Daniel Cranney
The State of WebDev AI 2025 Results: What Can We Learn?
Introduction The 2025 edition of The State of WebDev AI offers a detailed snapshot of how developers are using AI today, which tools have gained the most traction over the past year, and what these trends suggest about the future of the industry. In...
The State of WebDev AI 2025 Results: What Can We Learn?
CH
Chris Heilmann
Dev Digest 151: SEO in an AI world, security fixes and Doomed PDFs
Inside last week’s Dev Digest 151 . 🔎 How ChatGPT compares to search and what that means for SEO ✂️ Job cuts across the board as companies curb DEI programs 🟨 @Microsoft releases 161 Windows security updates ⚠️ @Google’s OAuth bug endangers million...
Dev Digest 151: SEO in an AI world, security fixes and Doomed PDFs
DC
Daniel Cranney
Security Basics for Vibe Coders
Vibe coding has become a popular trend in the tech world. With so many tools now available for both developers and non-developers, it’s easier than ever to build projects using natural language, in some cases without touching a line of code along the...
Security Basics for Vibe Coders
CH
Chris Heilmann
With AIs wide open - WeAreDevelopers at All Things Open 2025
Last week our VP of Developer Relations, Chris Heilmann, flew to Raleigh, North Carolina to present at All Things Open . An excellent event he had spoken at a few times in the past and this being the “Lucky 13” edition, he didn’t hesitate to come and...
With AIs wide open - WeAreDevelopers at All Things Open 2025

From learning to earning

Jobs that call for the skills explored in this talk.