Explosion 💥

@explosion.ai

We specialize in developer tools & tailored solutions for AI & NLP. Makers of spacy.io, prodi.gy and beta.ellf.ai. 🌎 explosion.ai 💼 linkedin.com/company/explosion-ai 🐘 sigmoid.social/@explosion 📺 youtube.com/c/ExplosionAI

At PyCon Armenia I finally got to meet Anna Vissens, Head of Data Science at @theguardian.com, in person! In her talk, she shared her team's in-depth analysis of sentiment towards immigration in parliament – using Prodigy for data annotation by humans and LLMs and spaCy for training classifiers.

BildBild

I gave a talk on "Build-to-own AI: Agentic Development for Humans" at PyCon Armenia: how coding agents change the way we build ML systems and why code and programmable interfaces matter more than ever, not less. Here's the whole thing as a thread 🧵 (1/18)

Bild

In Yerevan, Armenia, for PyCon Armenia & PyData Yerevan! I'm giving the opening keynote on Friday (tomorrow) and will be talking about "build-to-own AI", agentic development for humans, and how to use AI to build better AI. Looking forward to seeing everyone and exploring Yerevan on my day off ✨

BildBild

Just published a new blog post ✨ Our recent work got me thinking about Atomic Design by @bradfrost.com, a methodology for building web interfaces & how neatly it maps to how we've been approaching applied NLP: atoms (components) → molecules (pipelines) → organisms (applications) → pages (products)

Bild

“The shortest distance is not necessarily the best one, if you want to go to London you do not start walking there, you go on your computer do buy the tickets; same with llm, ask them to write code to do the thing”

Bild

Want to be a beta partner of our upcoming product for agentic NLP? We're looking for teams who need help with their NLP projects, especially around tasks like information extraction. Ellf is a virtual assistant for NLP projects – think Claude Code, but with NLP superpowers, or "Vibe NLP" ✨

Super-experimental at this point—but I am now embedding a local LLM inside Prodigy to assist with NER annotations... 1. Using `correct` recipe, LatinCy model tags likely entities 2. Optional "Ask LLM" button queries Mistral based on text/tags 3. Add'l RAG runs over the project's NER guidelines

Prodigy interface for LatinCy NER annotations... here Ov. Met. 2.5 and a PERSON label assigned to MulciberProdigy interface for LatinCy NER annotations... here Ov. Met. 2.5 and a PERSON label assigned to Mulciber; "Ask LLM" button queries an "NER Assistant" and provides more context

I've been getting a lot of questions recently about optimizing annotation workflows – many new NLP projects are starting atm! ✨ To share some of our tips, I put together a blog post featuring examples inspired by real use cases and a checklist to help you get started. explosion.ai/blog/optimiz...

The ultimate guide to optimizing annotation workflows · Explosion

This blog post collects tips and advice for how to build efficient human-in-the-loop data development workflows, break down business problems into actionable annotation steps and make the most of auto...

explosion.ai

In town for PyData Amsterdam! Who will be there? 🙋‍♀️ Looking forward to chatting about NLP and more, some cool Feminist AI hacking and catching up with everyone. I also have some brand new and exciting dev tooling to demo for those interested ✨

BildBild