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

Project

Topics

Tasks

Select...Code GenerationCoreference ResolutionDependency ParsingDistillationEmbeddings & VectorsEntity LinkingEvaluationImage ClassificationImage SegmentationLayout AnalysisLemmatizationNamed Entity RecognitionObject DetectionOptical Character Recognition (OCR)Part-of-Speech TaggingPII AnonymizationQuestion AnsweringRelation ExtractionRetrieval-Augmented Generation (RAG)Rule-Based MatchingSpan CategorizationText ClassificationText GenerationTokenizationWeak Supervision

Authors

Select...Adriane BoydÁkos KádárBasile DuraChung-Fan TsaiDamian RomeroDaniël de KokDuygu AltinokEdward SchmuhlHelena SteckmeisterIndia KerleInes MontaniKabir KhanLj MirandaMadeesh KannanMagdalena AniołMatthew HonnibalPaul O’Leary McCannPeter BaumgartnerPhilip VolletRaphael MitschRehan AhmedRichard HudsonRyan WesslenSofie Van LandeghemVictoria SlocumVincent D. WarmerdamVinit RavishankarWalter Henry

Vibe NLP for Applied NLP

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.

Sovereign AI systems instead of black box solutions

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

Conquering PDFs: document understanding beyond plain text

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.

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.

Reality is not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI

In this talk, Ines shows some practical solutions for using the latest state-of-the-art models in real-world applications and distilling their knowledge into smaller and faster components.

How S&P Global is making markets more transparent with NLP, spaCy and Prodigy

A case study on S&P Global’s efficient information extraction pipelines for real-time commodities trading insights in a high-security environment.

spaCy meets LLMs: Using Generative AI for Structured Data

This talk dives deeper into spaCy’s LLM integration, which provides a robust framework for extracting structured information from text, distilling large models into smaller components, and closing the gap between prototype and production.

Economies of Scale Can’t Monopolise the AI Revolution

During her presentation at QCon London, Ines Montani stated that economies of scale are not enough to create monopolies in the AI space and that open-source techniques and models will allow everybody to keep up with the “Gen AI revolution”.

Designing for tomorrow’s programming workflows

Modern editors and AI-powered tools like GitHub Copilot and ChatGPT are changing how people program and are transforming our workflows and developer productivity. But what does this mean for how we should be writing and designing our APIs and libraries?

Herding LLMs Towards Structured NLP

This talk shows how we integrate LLMs into spaCy, leveraging its modular and customizable framework. This allows for cheaper, faster and more robust NLP - driven by cutting-edge LLMs, without compromising on having structured, validated data.

Identifying Signs and Symptoms of Urinary Tract Infection from Emergency Department Clinical Notes Using Large Language Models

For annotation we employed Prodigy, a scriptable annotation tool designed to maximize efficiency, enabling data scientists to perform the annotation tasks themselves and facilitating rapid iterative development in natural language processing (NLP) projects.

Large Language Models: From Prototype to Production

In this talk, Ines presents visions for NLP in the age of LLMs and a pragmatic, practical approach for how to use Large Language Models to ship more successful NLP projects from prototype to production today.

Against LLM maximalism

LLMs are not a direct solution to most of the NLP use-cases companies have been working on. They are extremely useful, but if you want to deliver reliable software you can improve over time, you can't just write a prompt and call it a day. Once you're past prototyping and want to deliver the best system you can, supervised learning will often give you better efficiency, accuracy and reliability.

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.

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?

Getting Started with NLP and spaCy

There is a lot of text data out there and maybe you're interested in getting structured data out of it. There are a lot of options out there and this course will introduce you to the field by focussing on spaCy while also exploring other tools.

How to Host Your Own API of Open Language Models For Free

Powered by Explosion’s curated-transformers, FastAPI and ngrok.

How many Labelled Examples do you need for a BERT-sized Model to Beat GPT-4 on Predictive Tasks?

How does in-context learning compare to supervised approaches on predictive tasks? How many labelled examples do you need on different problems before a BERT-sized model can beat GPT-4 in accuracy? The answer might surprise you: models with fewer than 1b parameters are actually very good at classic predictive NLP, while in-context learning struggles on many problem shapes.

A practical guide to human-in-the-loop distillation

This blog post presents practical solutions for using the latest state-of-the-art models in real-world applications and distilling their knowledge into smaller and faster components that you can run and maintain in-house.

Towards Structured Data: LLMs from Prototype to Production

This talk presents pragmatic and practical approaches for how to use LLMs beyond just chat bots, how to ship more successful NLP projects from prototype to production and how to use the latest state-of-the-art models in real-world applications.

Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation

LLMs have enormous potential, but also challenge existing workflows in industry that require modularity, transparency and data privacy. In this talk, Ines shows some practical solutions for using the latest models in real-world applications and distilling their knowledge into smaller and faster components that you can run and maintain in-house.

Mastering spaCy

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.

ZenML v0.58.0

New out-of-the-box Prodigy integration in ZenML for LLMs and beyond, to make data development and annotation a core part of your MLOps lifecycle.