GeezerVison — Explosion · Developer tools and consulting for AI, Machine Learning and NLP

Home|About|Gaming cabinet|Archives|How it works|Starter sites

GeezerVison is showing explosion.ai — Explosion · Developer tools and consulting for AI, Machine Learning and NLP

Explosion builds developer tools for AI, Machine Learning and Natural Language Processing. →
Consulting

Project

Topics

Category

Tasks

Authors

Newsletter

Join our mailing list to receive updates about new blog posts and projects!

💌

View past issues

Introducing the free Solo plan for Ellf

Introducing the free Solo plan for Ellf

You can now use Ellf for free! The plan is designed for solo developers and includes all features and coding agent integration, with a data-private cluster running on your local machine.

🪎 ellf-templatesOct 29, 2026

Project templates for end-to-end NLP workflows, set up and adapted to your use case by your coding agent

Ellf: our new tool for agentic NLP development

Ellf: our new tool for agentic NLP development

Ellf gives your coding assistant like Claude Code superpowers for solving NLP problems and a platform to execute data-centric projects, automated annotation and more.

Build-to-own AI: Agentic Development for Humans

Build-to-own AI: Agentic Development for Humans PyData PyCon Yerevan Keynote

Instead of using LLM APIs, we can take back control and build our own systems, bootstrapped by agents. In this talk, Ines shows you these new agentic workflows, what they mean for developer tools and why code and open-source are more important than ever.

Show Us Your (Agent) Skills

Show Us Your (Agent) Skills PyMC Labs × Vanishing Gradients

What are people at the top of the game building with AI agents and how are they doing it? In this episode, 6 developers are sharing their workflows.

How rightwing rhetoric has risen sharply in the UK parliament

How rightwing rhetoric has risen sharply in the UK parliament The Guardian

In-depth analysis by the Guardian in collaboration with University College London, powered by Prodigy for semi-automated data annotation and spaCy for classification model training and prediction.

Engineering a human-aligned LLM evaluation workflow with Prodigy and DSPy

Engineering a human-aligned LLM evaluation workflow with Prodigy and DSPy

This post demonstrates a human-in-the-loop workflow for developing and evaluating LLMs, using Prodigy and DSPy to create task-specific, human-aligned metrics that guide model optimization beyond generic evaluation measures.

Conquering PDFs: document understanding beyond plain text

Conquering PDFs: document understanding beyond plain text PyData London

In this talk, Ines presents a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem.

AI in Reality Fireside Chat: Enterprise AI & Open-Source Innovation

AI in Reality Fireside Chat: Enterprise AI & Open-Source Innovation PyCon DE & PyData

Panel discussion with Alexander CS Hendorf, Dr. Alexander Beck, Walid Mehanna and Ines.

KI ohne Ketten: Warum Open Source gegen Big Tech gewinnen kann

KI ohne Ketten: Warum Open Source gegen Big Tech gewinnen kann UNMUTE IT Podcast (German)

Interview with Ines on open source, LLMs, ethics and sustainable AI development.

Künstliche Intelligenz: Technologie der Zukunft – und warum Open Source die Karten neu mischt

Künstliche Intelligenz: Technologie der Zukunft – und warum Open Source die Karten neu mischt Heise KI-Woche 2025 (German)

German talk on the future of Artificial Intelligence and the impact of open-source software and models.

What the history of the web can teach us about the future of AI

What the history of the web can teach us about the future of AI PyCon+Web Keynote

In this talk, Ines takes a look at what the history of the web can teach us about the future of AI, and what this means for developers, models, open source and regulation.

Prodigy Dashboard Plugin

Prodigy Dashboard Plugin

The new dashboard plugin adds a web application for managing annotations, data analytics and annotation progress, and is now available for early beta testing.

Recognising non-named spatial entities in literary texts: a novel spatial entities classifier

Recognising non-named spatial entities in literary texts: a novel spatial entities classifier Kababgi, Grisot, Pennino, Herrmann (2024)

In this paper, we present a case study on the prediction of what we call ‘non-named spatial entities’ (NNSE) in a historical corpus of Swiss-German novels using a deep learning model in conjunction with BERT and Prodigy.

🔌 prodigy-pdf v0.4.0Nov 25, 2024

Add text-based span annotation for PDFs

Serverless custom NLP with LLMs, Modal and Prodigy

Serverless custom NLP with LLMs, Modal and Prodigy

In this blog post, we’ll show you how you can go from an idea and little data to a fully custom information extraction model using Prodigy and Modal, no infrastructure or GPU setup required.

✨ prodigy v1.16.0Oct 22, 2024

Modal plugin for on-demand deployment, cross-platform wheels and UI fixes

Agent UX: Building developer tools for humans and their coding agents

Agent UX: Building developer tools for humans and their coding agents

For a long time, visual SaaS apps have been the go-to for professional tools. With coding agents, this is changing – and the apps we build now need to work just as well for the agents operating them.

Happy 10th Anniversary!

Happy 10th Anniversary!

Exactly 10 years ago today, we officially founded Explosion. So much has happened since and we got to witness the field evolve, “AI” become mainstream, and hypes come and go. Thanks to all of you for your support over the past 10 years and beyond!

Atomic NLP

Atomic NLP

An applied NLP methodology inspired by Atomic Design: building reliable language understanding systems out of small, composable components instead of one big model and a prompt.

Building Multimodal Corpora Using Microtask Pipelines and Local Annotators

Building Multimodal Corpora Using Microtask Pipelines and Local Annotators Hotti, Vázquez, Jokipohja, Kalliokoski, Paakki, Suviranta, Hiippala (2026)

To create the infrastructure needed for supporting this effort, we repurpose an existing commercial annotation tool, Prodigy, which we then enhance with additional components for combining the annotation tasks into pipelines, cross-validating the annotations and supporting annotator access to tasks.

The ultimate guide to optimizing annotation workflows

The ultimate guide to optimizing annotation workflows

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 automation and model assistance.

Building AI with AI

Building AI with AI PyCon Ireland Keynote

AI-powered coding assistants have transformed the way we build software, and AI itself. In this talk, Ines shows why we should use LLMs to build systems instead of as systems, and why code is more important than ever, not less.

Applied NLP in the Age of Generative AI: Future-Proof Strategies for Banking and Finance

Applied NLP in the Age of Generative AI: Future-Proof Strategies for Banking and Finance ECONDAT Keynote

A modern approach and mindset for building future-proof NLP pipelines in-house, focusing on use cases from banking, finance and economics.

Feminist AI LAN Party

Feminist AI LAN Party PyCon DE & PyData

Three days of workshops, hacking, creating, publishing and connecting locally, featuring a data development workshop with Prodigy and a session on hacking LLMs.

KI zwischen Freiheit und Kontrolle: The AI Revolution Will Not Be Monopolized

KI zwischen Freiheit und Kontrolle: The AI Revolution Will Not Be Monopolized data:unplugged (German)

How should we envision the use of AI in practice? And are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies?

📚 spacy-layout v0.0.12Mar 8, 2025

Support processing PDFs with context, add document index tables and more docs

Mastering spaCy

Mastering spaCy Déborah Mesquita, Duygu Altinok (Packt Publishing, 2025)

Build structured NLP solutions with custom components and models powered by LLMs. By end of the book you will be empowered to build robust NLP pipelines and integrate them with web applications to build end-to-end solutions.

Using natural language processing to identify emergency department patients with incidental lung nodules requiring follow-up

Using natural language processing to identify emergency department patients with incidental lung nodules requiring follow-up Moore, Socrates, Hesami, Denkewicz, Cavallo, Venkatesh, Taylor (2025)

CT reports were annotated by MD raters using Prodigy software to develop a stepwise NLP “pipeline” that first excluded prior or known malignancy, determined the presence of a lung nodule, and then categorized any recommended follow-up. NLP was developed using a RoBERTa large language model on the spaCy platform.

Cracking the Code: How to Start a Career in AI

Cracking the Code: How to Start a Career in AI Welcome to the Jungle

Short video interview with Ines about the 4 skills job hunters can cultivate for a career in artificial intelligence.

From PDFs to AI-ready structured data: a deep dive

From PDFs to AI-ready structured data: a deep dive

This blog post presents a new modular workflow for converting PDFs and similar documents to structured data and shows you how to build end-to-end document understanding and information extraction pipelines for industry use cases.

✨ prodigy v1.17.0Nov 18, 2024

Pages UI for multi-page tasks like longer documents, PDFs or collections of images

Accelerate your Career with Open-Source AI

Accelerate your Career with Open-Source AI dotAI

Panel discussion about making a career out of open-source software, featuring Gael Varoquaux (scikit-learn), Steeve Morin (ZML) and Ines.

Introducing Ellf: The missing piece for building NLP with coding assistants

Introducing Ellf: The missing piece for building NLP with coding assistants

Ellf is our new tool that plugs into the coding assistant you already use, like Claude Code, Codex or GitHub Copilot, and gives it the missing pieces to develop custom AI systems.

Vibe NLP for Applied NLP

Vibe NLP for Applied NLP Build with AI

What if we could take learnings from AI-powered coding agents and apply them to solving real-world NLP problems? In this talk, Ines shows you these new agentic workflows and how we’ve built a powerful virtual assistant to create practical solutions that are small, fast and data-private.

A quick chat with Ines & Matt

A quick chat with Ines & Matt Py4AI

Impromptu video interview on what inspired our talk and the conference vibes in sunny Pavia.

Vibe NLP for Applied NLP

Vibe NLP for Applied NLP PyCon DE & PyData

What if we could take learnings from AI-powered coding agents and apply them to solving real-world NLP problems? In this talk, I’ll show how we’ve built a powerful virtual NLP assistant to help developers create practical and modular solutions that are small, fast and fully data-private.

Style tips for less experienced developers coding with AI

Getting good performance out of LLM coding is less about prompts or agents, and more about the code you steer the model towards. Matt shares some lessons software engineers have learned over the years about building bigger things.

How AI is reshaping IT skills

How AI is reshaping IT skills connect professional

German article featuring Ines’ take on the impact of AI on future-proof skills for IT professionals.

E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness

E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness Zhao, Zhu, Guo, He, Li (2025)

Instead of using LLMs for entity extraction, we employ the traditional NLP tool spaCy to extract entities, and use their co-occurrence in a chunk as relations.

Conquering PDFs: document understanding beyond plain text

Conquering PDFs: document understanding beyond plain text PyCon DE & PyData

In this talk, Ines presents a new and modular approach for building robust document understanding systems, using state-of-the-art models and the awesome Python ecosystem.

How to advocate for modular NLP in the age of Generative AI

How to advocate for modular NLP in the age of Generative AI

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 are better, easier and cheaper?

✨ prodigy v1.18.0Feb 24, 2025

Text editing during NER and span annotation, custom translations and more JavaScript features

Prozessvisualisierung mit generativer KI im Praxistest

Prozessvisualisierung mit generativer KI im Praxistest iX Magazin / Heise

German article by Nils Durner on visualizing technical processes with Generative AI, featuring spaCy and Presidio for PII anonymization.

Best Way to OCR a PDF in Python

Best Way to OCR a PDF in Python Python Tutorials for Digital Humanities

Tutorial by WJB Mattingly on how to use the new spaCy Layout package and Docling to convert PDFs to text.

spaCy Natural Language Processing: From Beginner to Advanced

spaCy Natural Language Processing: From Beginner to Advanced Guan Wang, Xiaoquan Kong (2024)

The first Chinese-language book on spaCy for beginners and experienced practitioners, covering traditional NLP techniques and how to leverage LLMs for various NLP tasks.

🔌 prodigy-pdf v0.3.0Nov 18, 2024

Support multi-page PDFs in a single view

uOttawa at LegalLens-2024: Transformer-based Classification Experiments

uOttawa at LegalLens-2024: Transformer-based Classification Experiments Meghdadi, Inkpen (2024)

Our training utilizes the spaCy pipeline configured with a transformer model and a transition-based parser for NER tasks. The deberta-v3-base model has been selected for the main transformer architecture.

Ellf: Your virtual NLP engineer

Ellf: Your virtual NLP engineer

In this new video series, Ines gives you an overview of our new tool and platform Ellf, its philosophy and how to use it to build your own custom NLP pipelines with the help of agents.

Decoding the Evolution of Marine Plastic Litter Research with Large Language Models

Decoding the Evolution of Marine Plastic Litter Research with Large Language Models de Medeiros Back, Grelaud, Alarcon, Ziveri (2026)

Papers were classified into basins (as defined by the NOAA’s World Ocean Database) using an automatic Named Entity Recognition algorithm freely available at spaCy.

Taking back control of your AI development

Taking back control of your AI development Feminist AI (PyData London)

Short unconference presentation by Ines on the current focus of our work: empowering developers to build AI in-house again.

A Century of Immigration Rhetoric in the UK Parliament

A Century of Immigration Rhetoric in the UK Parliament Gennaro, Vissens, Thornewill von Essen, Ravalde, Egan, Dave, Dable, Facini (2026)

With all annotated snippets, we trained two transformer-based classifiers, each using a spaCy pipeline consisting of a RoBERTa base transformer model and spaCy’s textcat (text categorisation) component.

RiCoRecA: rich cooking recipe annotation schema

RiCoRecA: rich cooking recipe annotation schema Ventirozos, Jacob-Romero, Alrdahi, Clinch, Batista-Navarro (2026)

The annotation process consists of two sections. Firstly, the annotator utilized a customized Prodigy interface to complete the NER and RC annotation tasks.

Sovereign AI systems instead of black box solutions

Sovereign AI systems instead of black box solutions it-daily

German article featuring Ines’ take on AI in industry, the role of open source, and using Generative AI to create systems.

Developer Trends in 2025

Developer Trends in 2025 TalkPython Podcast

Discussion with Michael Kennedy, Calvin Hendryx-Parker, Gina Häußge, Richard Campbell and Ines.

Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content

Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content Rizvi, Navojith, Adhikari, Senevirathna, Kasthurirathna, Abeywardhana (2025)

Keyword extraction in English is performed with a hybrid approach comprising a fine-tuned spaCy NER model, FinBERT-based KeyBERT embeddings, YAKE, and EmbedRank, which results in a combined accuracy of 91.2%.

How Love Without Sound helps the music industry recover millions in revenue for artists with NLP, spaCy and Prodigy

How Love Without Sound helps the music industry recover millions in revenue for artists with NLP, spaCy and Prodigy

A case study on Love Without Sound’s innovative AI-powered tools for the music industry and law firms specializing in royalty negotiations.

What the history of the web can teach us about the future of AI

What the history of the web can teach us about the future of AI

How will AI development look in the future? There is a lot we can learn from another groundbreaking technology: the web. This blog post takes a look at what the history of the web can teach us, and what this means for developers, models, open source and regulation.

Streaming spaCy

Streaming spaCy

Join spaCy author and core developer Matt as he works on the library, develops features and fixes bugs, while chatting about all things NLP and open source. Every Thursday at 2pm CET and Friday at 11am CET.

PyLadies entrepreneurs and career development

PyLadies entrepreneurs and career development PyLadiesCon

Panel discussion about career challenges and starting your own business with Cheuk Ting Ho, Tereza Iofciu, Anwesha Das, Una Galyeva and Ines.

📚 spacy-layout v0.0.6Nov 24, 2024

Add support for tables and convert tabular data to pandas.DataFrame

📚 spacy-layout v0.0.1Nov 18, 2024

Process PDFs, Word documents and more with spaCy

Distill Your LLMs and Surpass Their Performance

Distill Your LLMs and Surpass Their Performance InfoQ Magazine

In her presentation at InfoQ Dev Summit, Ines Montani provided the audience with practical solutions for using the latest state-of-the-art models in real-world applications and distilling their knowledge into smaller and faster components.

Newsletter

Join our mailing list to receive updates about new blog posts and projects!

💌

View past issues