Ethan Steininger

Former lead of MongoDB's Search Team, Ethan noticed the most common problem customers faced was building indexing and search infrastructure on their S3 buckets. Mixpeek was born.

Recent Posts

I Benchmarked 5 Video Embedding Models So You Don't Have To

We tested Gemini, Twelve Labs Marengo, X-CLIP, SigLIP 2, and InternVideo2 on text-to-video retrieval with graded relevance. The results surprised us.

March 12, 20266 min read

Gemini Embedding 2 is Live: embed multiple files into one vector

Google's Gemini Embedding 2 embeds images, PDFs, and text together in a single API call. Here's how we integrated it into Mixpeek's feature extractor pipeline, the production numbers, and where multi-file embedding beats single-chunk approaches.

March 12, 202610 min read

Query Preprocessing: Semantic Search With Large Files

How we built query preprocessing into Mixpeek's feature_search stage — decompose a 500MB video into chunks, embed in parallel, fuse results. Zero API surface change for callers.

March 9, 20266 min read

AI Video Analysis for Sports: Build Automated Highlight Reels, Archive Search, and Performance Analytics

Sports broadcasters cut 4-8 hour editing sessions to 15 minutes using AI video analysis. Learn how to build automated highlight detection, archive search, and performance analytics pipelines for any sport.

March 9, 20266 min read

How Mixpeek runs distributed multimodal ML on Ray: architecture, patterns, and production lessons

We run 20+ ML models in parallel across video, image, and document pipelines. Here's the Ray architecture behind it -- custom resource isolation, flexible actor pools, distributed Qdrant writes, and the lessons we learned the hard way.

February 25, 20267 min read

Political Ad Disclaimers: How ZIP+4 Targeting Creates Jurisdiction Conflicts

6,000+ ZIP codes straddle congressional district lines. At ZIP+4 precision, federal, state, and local disclaimer requirements can all apply simultaneously. Here's how multimodal AI solves what static rules engines can't.

February 19, 20265 min read

IAB Contextual Classifier: Taxonomies for Videos and Images

Classify text, images, and video into 700+ IAB Content Taxonomy categories using multimodal AI. Learn how it works under the hood and how to extend it for your contextual targeting needs.

February 15, 20269 min read

Semantic Crons: Replace LLM Polling with Vector-Based Alerts

Instead of polling with an LLM on a cron schedule, Retriever Alerts evaluate semantic conditions at ingestion time. Vector math instead of inference calls. Event-driven instead of scheduled. Three API calls to set up.

February 12, 20266 min read

Why SNF Documentation Is a Multimodal AI Problem

Nurses spend 40% of their time on documentation. MDS coordinators abstract charts for 3-4 hours per assessment. PDPM revenue goes uncaptured. The root cause is that clinical documentation is inherently multimodal — and most tools only handle text.

February 11, 20265 min read

Semantic Chunking Strategies for Multimodal RAG

How semantic chunking improves RAG quality by splitting content at natural boundaries rather than fixed token counts. Covers text, documents, video, and audio.

February 10, 20263 min read

What is Agentic Retrieval? The Next Evolution of RAG

How agentic retrieval goes beyond traditional RAG by letting AI agents dynamically plan and execute multi-step search strategies with tool calling.

February 10, 20263 min read

Video Intelligence: From Raw Footage to Searchable Data

How AI-powered video intelligence extracts structured, searchable information from raw footage — covering scene detection, transcription, face recognition, and temporal indexing.

February 10, 20263 min read

Keyword Search vs Semantic Search vs Hybrid Search: A Developer's Guide

A clear comparison of keyword, semantic, and hybrid search with practical guidance on when to use each approach in production systems.

February 10, 20263 min read

How to Build a Multimodal Search Engine in 2025

A practical guide to building search that works across text, images, video, and audio using shared embedding spaces and retrieval pipelines.

February 10, 20263 min read

Building a Production-Ready VLM Inference Server in Rust

How we built a fast, efficient, and production-ready vision-language model server without Python

January 26, 20267 min read