WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
WeAreDevelopers LIVE • Sep 18, 2024

Vision for Websites: Training Your Frontend to See

Daniel Madalitso Phiri

Ditch rigid keyword metadata and teach your frontend to see. Use multimodal AI and vector databases to build context-aware apps that intuitively understand images, text, and audio.

Pause
Mute Enter Fullscreen
#1 about 2 min

Defining machine vision for modern web frontends

Redefining digital vision as data deduction provides clear strategies for frontend data interpretation.

#2 about 5 min

Demonstrating multimodal search in an enterprise storefront

Retrieving catalog items without specific metadata requires multimodality to dynamically match text and visual queries.

#3 about 5 min

Improving user interactions via multimodal context gathering

Transitioning traditional keyword searches into natural multimodal queries significantly improves user interface interactions.

#4 about 4 min

Encapsulating complex frontend data using embedding models

Storing distinct multi-format data in multidimensional mathematical spaces enables the direct comparison of non-uniform assets.

#5 about 5 min

Executing vector search queries using spatial distance

Plotting queries and data into numbered vector coordinates measures physical distance to determine search relevance.

#6 about 3 min

Unifying distinct media formats across shared vector spaces

Processing varying media through specialized encoders deposits uniform embeddings into a shared retrieval environment.

#7 about 3 min

Architecting a multimodal storefront interface using Next.js

Wiring frontend UI components to remote API routes securely hands text and image queries off to backend machine learning tools.

#8 about 7 min

Filtering text search queries with TypeScript and Weaviate

Interrogating vector clusters with text values relies on dynamic API limits to trim results by statistical distance jumps.

#9 about 3 min

Processing base64 image queries against remote vector collections

Submitting user photos to backend machine learning functions requires encoding visuals into processable base64 strings.

#10 about 3 min

Expanding vision applications beyond standard ecommerce features

Deploying camera-based cross-referencing inside user applications bridges digital product catalogs with real-world physical objects.

Matching moments

5:20 min

Building neural search applications across diverse data modalities

Han Xiao · World Congress 2022

3:46 min

Substituting traditional classification models with search-based AI architecture

Erik Bamberg · LIVE

3:00 min

Introduction to generative AI and vector search

Mary Grygleski Mary Grygleski · LIVE

1:28 min

Implementing multimodal image processing and visual capabilities on the edge

Daniel Ostrovsky Daniel Ostrovsky · World Congress 2026 Europe

3:45 min

Demonstrating Viro React capabilities for interactive applications

Vladimir Novick · World Congress 2021

4:46 min

Visualizing semantic similarity within a multi-dimensional vector space

Erik Bamberg · LIVE

More from WeAreDevelopers LIVE

Fake or News - Claude's DNA Discovery, Quick Cloning & Crime on Insta thumbnail
6:07
2 days ago

Fake or News - Claude's DNA Discovery, Quick Cloning & Crime on Insta

Andrew MacLean, Daniel Cranney, Christian Heilmann

WeAreDevelopers LIVE - Playing in Production thumbnail
1:06:40
2 days ago

WeAreDevelopers LIVE - Playing in Production

Andrew MacLean, Daniel Cranney, Christian Heilmann

WeAreDevelopers LIVE - Is CSS Catching Up to Flash? thumbnail
1:03:33
16 days ago

WeAreDevelopers LIVE - Is CSS Catching Up to Flash?

Chris Heilmann, Daniel Cranney, Bramus Van Damme

WeAreDevelopers LIVE - Project Chopin: Make Your Team and Agents Play Along thumbnail
1:21:17
23 days ago

WeAreDevelopers LIVE - Project Chopin: Make Your Team and Agents Play Along

Chris Heilmann, Daniel Cranney, Krzysztof Cieślak

Fake or News - AI Toothbrushes, Carrier Pigeon Tech & Life on Mars - Krzysztof Cieślak thumbnail
4:23
25 days ago

Fake or News - AI Toothbrushes, Carrier Pigeon Tech & Life on Mars - Krzysztof Cieślak

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Open Source Agent Toolkits thumbnail
1:00:38
about 1 month ago

WeAreDevelopers LIVE - Open Source Agent Toolkits

Chris Heilmann, Daniel Cranney, Eddie Jaoude

Related videos

How to Decipher User Uncertainty with GenAI and Vector Search thumbnail
24:47
World Congress 2025 • about 1 year ago

How to Decipher User Uncertainty with GenAI and Vector Search

Ben Greenberg

Develop AI-powered Applications with OpenAI Embeddings and Azure Search thumbnail
57:52
LIVE • almost 3 years ago

Develop AI-powered Applications with OpenAI Embeddings and Azure Search

Rainer Stropek

WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more thumbnail
1:05:44
LIVE • about 1 year ago

WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more

Chris Heilmann, Daniel Cranney, Raphael De Lio, Advocate At Redis

What comes after ChatGPT? Vector Databases - the Simple and powerful future of ML? thumbnail
59:38
LIVE • almost 3 years ago

What comes after ChatGPT? Vector Databases - the Simple and powerful future of ML?

Erik Bamberg

Harry Potter and the Elastic Semantic Search thumbnail
57:52
LIVE • over 2 years ago

Harry Potter and the Elastic Semantic Search

Iulia Feroli

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka thumbnail
11:14
Coffee With Developers • about 1 month ago

AI Vector Search at Scale - Ewa Szyszka - Ewa Szyszka

Ewa Szyszka

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.