EVA – AI-Relational Database System
Hi friends, We are building EVA, an AI-Relational database system with first-class support for deep learning models. Our goal with EVA is to create a platform that supports AI-powered multi-modal database applications operating on structured (tables, feature vectors, etc.) and unstructured data (videos, podcasts, pdf, etc.) with deep learning models. EVA comes with a wide range of models for analyzing unstructured data, including models for object detection, OCR, text summarization, audio speech recognition, and more. The key feature of EVA is its AI-centric query optimizer. This optimizer…
In plain words
EVA is an AI-Relational database system designed for developers building AI-powered applications that process both structured and unstructured data. It integrates deep learning models for tasks like object detection, OCR, text summarization, and speech recognition alongside traditional database functionality. EVA's distinguishing feature is its AI-centric query optimizer, which caches inference results and applies database-inspired optimizations to speed up AI applications and reduce redundant computation.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi friends, We are building EVA, an AI-Relational database system with first-class support for deep learning models. Our goal with EVA is to create a platform that supports AI-powered multi-modal database applications operating on structured (tables, feature vectors, etc.) and unstructured data (videos, podcasts, pdf, etc.) with deep learning models. EVA comes with a wide range of models for analyzing unstructured data, including models for object detection, OCR, text summarization, audio speech recognition, and more. The key feature of EVA is its AI-centric query optimizer. This optimizer is designed to speed up AI-powered applications using a collection of optimizations inspired by relational database systems. Two of the most important optimizations are: + Caching: EVA automatically reuses previous query results (e.g., inference results), eliminating redundant computation and saving you money on inference. + Predicate Reordering: EVA optimizes the order in which query predicates are evaluated (e.g., running faster, more selective deep learning models first), leading to faster queries. Besides saving money spent on inference, EVA also makes it easier to write SQL queries to set up multi-modal AI pipelines. With EVA, you can quickly integrate your AI models into the database system and seamlessly query structured and unstructured data. We are constantly working on improving EVA and would love to hear your feedback!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
