Video Learning Hub
Master multimodal AI concepts through comprehensive tutorials, guides, and best practices from our expert team.
Trusted by engineers at
Mixpeek Taxonomies Guide
Learn how to organize and classify your multimodal content using Mixpeek's new Taxonomies feature. This guide walks you through creating hierarchical classifications that understand both visual and textual content using powerful embedding models. What you'll learn: ⚡ Creating custom taxonomies ⚡ Implementing multimodal embeddings ⚡ Automatic content classification ⚡ Hierarchical search capabilities ⚡ Best practices for video taxonomies
Mixpeek Namespaces Guide
Learn how to create and manage isolated environments for your search applications using Mixpeek's Namespaces feature. This guide covers organizing use cases, applications, or environments with independent configurations and security controls. What you'll learn: ⚡ Logical separation for different applications ⚡ Configuring vector and payload indexes ⚡ Best practices for organizing namespaces ⚡ Implementing environment and client isolation ⚡ Naming conventions for efficient management
Mixpeek Collections Guide
Learn how to effectively organize your multimodal content using Mixpeek Collections! This guide covers everything you need to know about creating and managing content groups for optimized search and retrieval. What you'll learn: ⚡ Collection creation and management ⚡ Content organization strategies ⚡ Namespace isolation ⚡ Access patterns and permissions ⚡ Performance optimization tips Key highlights: Create logical content groupings Scale to millions of assets Optimize search configurations Manage access controls
Multimodal Monday #2 — From Tiny VLMs to 10M‑Token Titans
This week in multimodal AI was wild — we're talking: Meta's Llama 4 with 10M-token context windows Microsoft's Phi-4-Multimodal outperforming much larger models Hugging Face's SmolVLM that runs on less than 1GB RAM Poisoned image attacks on retrieval-augmented generation (!) We'll break down the latest research, tools, real-world use cases, and what it all means for developers, founders, and builders in the AI space. ⏱ Timestamps: 00:00 – Welcome 00:25 – Quick Take 01:05 – Research Highlights 02:10 – Tools & Techniques 03:00 – Real-World Applications 03:40 – Trends & Predictions 04:30 – Community & Shoutouts 04:55 – Wrap-up
Introduction to Multimodal University
Join Ethan, former MongoDB Search Engineer and CEO of Mixpeek, as he introduces you to the world of multimodal AI development. Learn what you'll master in this comprehensive course and why multimodal understanding is crucial for modern applications.
What is Multimodal Understanding?
Discover how computers can understand multiple types of data simultaneously. This lesson breaks down the core concepts of multimodal systems and their real-world applications. Learn how text, images, audio, and video work together in modern AI systems.
Fundamental Multimodal Concepts
Dive into the building blocks of multimodal systems. Learn about data representation, feature extraction, neural networks, and information retrieval. Essential concepts for anyone looking to build sophisticated AI applications.
Text Understanding Fundamentals
Master the basics of natural language processing. From tokenization to word embeddings, learn how machines understand and process text data. Includes practical examples and real-world applications.
Audio Understanding Fundamentals
Explore how machines process and understand audio signals. Learn about waveforms, feature extraction, and common audio processing tasks. Essential knowledge for speech recognition and audio analysis.
Visual Understanding Fundamentals
Learn the foundations of computer vision. From image preprocessing to object detection, understand how machines interpret visual information. Includes practical examples of feature extraction and real-world applications.