Explosion 💥

Prodigy interface for LatinCy NER annotations... here Ov. Met. 2.5 and a PERSON label assigned to Mulciber

Prodigy 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

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

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...

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...

Back from a great PyCon Ireland #PyConIE in Dublin! 💚 As always, some of my personal highlights:

www.linkedin.com/posts/inesmo...

Great wisdom by @inesmontani.bsky.social at #PyConIE

Back from a few days in Amsterdam for PyData! Here are some of my highlights:

www.linkedin.com/feed/update/...

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 ✨

I was interviewed for a German article on it-daily about efficient AI development in industry, the role of open source, and using Generative AI to create systems and data for smaller models. Thanks Silvia for the feature!

www.it-daily.net/it-managemen...

What a great meetup! Thanks to everyone who came by yesterday for an evening of real-world AI and bullshit-free strategies for building LLM applications.

Recap and highlights: www.linkedin.com/feed/update/...

I'm back from a busy four days in London! 💜 I had a great time at @pydatalondon.bsky.social‬ and you can read my recap and highlights here: www.linkedin.com/feed/update/...

At #PyData London @inesmontani.bsky.social confirms our suspicions that we should try not to work with PDFs directly. Do the expensive extraction upfront into a unified structured format and build all your analysis and #NLP components yourself so you can better modularise
@pydatalondon.bsky.social

Hi Berlin people! @hugobowne.bsky.social is in town & we're celebrating by hosting a meetup together 🎉 This one is all about building with AI & we'll also open the floor for lightning talks. If you're around, come hang out with us!

📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u

Streaming spaCy (May 19, 2025): Working on Python 3.13 compatibility YouTube video by Explosion

Back to streaming spaCy! Working on Python 3.13 compatibility today: www.youtube.com/watch?v=wgjQ...

Developer Trends in 2025 What trends and technologies should you be paying attention to today? Are there hot new database servers you should check out? Or will that just be a flash in the pan? I love these forward looking epi...

Awesome new episode with a bunch of fun and smart people:

Episode #504: Developer Trends in 2025

Featuring @foosel.net, @richcampbell.bsky.social, @calvinhp.com, @inesmontani.bsky.social, and @mkennedy.codes #python

talkpython.fm/episodes/sho...

Conquering PDFs: document understanding beyond plain text NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documen…

Here are the slides for my talk "Conquering PDFs: document understanding beyond plain text": speakerdeck.com/inesmontani/...

Another great @pyconde.bsky.social is over and I'm exhausted but happy, and feel very inspired! ⚡

Here are my personal highlights: www.linkedin.com/feed/update/...

In Darmstadt for @pyconde.bsky.social 🐍✨

Tomorrow I'll be speaking about conquering PDFs and document understanding, and Thursday I'm joining the fireside chat panel on enterprise AI & open source. And I'll be around for the @feminist-ai.bsky.social LAN Party open hours to hack LLMs. See you there!

Feminist AI is coming to @pyconde.bsky.social! If you're around, drop by at any time during the open hours and join us for workshops on hacking LLMs and data development, or contribute to our DIY PyCon zine ⚡

Follow for updates: @feminist-ai.bsky.social
Details: feministai.party/events/2025-...

How to advocate for modular NLP in the age of Generative AI · Explosion With all the hype around Generative AI, many are led to believe it’s the solution to everything. So how can you, as a developer, communicate the nuances and advocate for new and modular solutions that...

This is another great and short read from @inesmontani.bsky.social at spaCy. It has a lot of implications for those who work in the humanities and industry.

explosion.ai/blog/modular...

#MachineLearning

The episode is now out on youtube, coming to podcast channels in a few weeks. Great show, thanks Ines!

Enjoying my train ride to Münster for data:unplugged!

Tomorrow I'll be speaking about real-world use cases of AI, how to navigate black-box models and why open source means that nobody can monopolize AI (unless we let them) ✊

I will be around all day, so if you're attending, come and say hi!

My friend @hugobowne.bsky.social launched new course on Building LLM Applications for Data Scientists and Software Engineers! I'll be joining for a guest lecture on human-in-the-loop development and distillation workflows.

You can get 10% off with my code + lots of perks: maven.com/hugo-stefan/...

Announcing a new event initiative: Feminist AI LAN Party! Katharine and I did a pilot event last year and we're now taking it to @pyconde.bsky.social.

We've also open-sourced event kits to make it easy to host your own, including:

💣 hacking LLMs
📑 data development
✂️ zine making

feministai.party

I don't normally write advice columns but this question I got deserved its own post: With all the hype around Generative AI, how can you, as a developer, communicate the nuances and advocate for new and modular solutions that are better, easier and cheaper?

explosion.ai/blog/modular...

So many good events coming up this season. Here's my schedule – hope to see you there!

Apr 10: data:unplugged (Münster)
Apr 23: @pyconde.bsky.social (Darmstadt)
May 31: @pyconit.bsky.social (Bologna)
Jun 5: ECONDAT (London)
Jun 7-8: @pydatalondon.bsky.social (London)

📆 Details: explosion.ai/events

@explosion-ai.bsky.social

Only the best companies will send you stickers if you are a fan and beg for them!

Thank you so much, Ines and Matt!!!!

TIL: Incorrect music metadata is a huge problem and is causing artists to lose millions in royalties. This disproportionaly affects independent musicians. But structured NLP can help!

explosion.ai/blog/love-wi...

New case study: How Love Without Sound built innovative AI-powered tools for the music industry and law firms, and helped publishers recover hundreds of millions of dollars in lost revenue for artists.

explosion.ai/blog/love-wi...

Out now: Prodigy v1.18! New features include:

✍️ edit text during span annotation
💬 fully custom UI translations
🎛️ new JavaScript events and functions
✅ various small fixes and docs

More details: prodi.gy/docs/changelog

These are the kinds of NLP stories I love! TFW you "accidentally" train a great 2 MB (!) task-specific model 🤯 @strickvl.bsky.social