Distill Your LLMs and Surpass Their PerformanceInfoQ MagazineIn 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.
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillationInfoQ Dev SummitLLMs 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.
The NLP and AI Revolution with the spaCy CreatorsVanishing GradientsIn this interview with Hugo Bowne-Anderson, we delve into the forefront of NLP and the future of AI development, covering topics like human-in-the-loop distillation, open-source AI and Explosion’s journey.
A practical guide to human-in-the-loop distillationThis 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.
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillationPyData LondonLLMs 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.
The AI Revolution Won’t Be MonopolizedTalkPython PodcastThere hasn’t been a boom like the AI boom since the .com days. And it may look like a space destined to be controlled by a couple of tech giants. But Ines Montani thinks open source will play an important role in the future of AI.
Economies of Scale Can’t Monopolise the AI RevolutionInfoQ MagazineDuring 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”.
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMsPyCon Lithuania KeynoteWith the latest advancements in NLP and LLMs, and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies?
T-RAG: Lessons from the LLM TrenchesFatehkia, Lucas, Chawla (2024)An important application area is question answering over private enterprise documents where the main considerations are data security, which necessitates applications that can be deployed on-prem, [and] limited computational resources. [...] In addition to retrieving contextual documents, we use the spaCy library with custom rules to detect named entities from the organization.
State-of-the-Art Transformer Pipelines in spaCyaiGrunnIn this talk, we will show you how you can use transformer models (from pretrained models such as XLM-RoBERTa to large language models like Llama2) to create state-of-the-art annotation pipelines for text annotation tasks such as named entity recognition.
Newsletter September 2023The latest edition of our newsletter, featuring our plans for premium models, LLMs, chain-of-thought prompting, upcoming events and talks, and exciting new Prodigy features. Plus exclusive discounts!
How to Host Your Own API of Open Language Models For FreePowered by Explosion’s curated-transformers, FastAPI and ngrok.
✨ prodigy v1.12.0Jul 5, 2023LLM-assisted workflows for annotation and prompt engineering, task routing for multi-annotator setups
Serverless custom NLP with LLMs, Modal and ProdigyIn 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.
Newsletter September 2024The latest edition of our newsletter features recent talks, blog posts and interviews, plus real-world examples of practical, applied NLP with LLMs and Generative AI.
Practical Tips for Bootstrapping Information Extraction PipelinesDataHack SummitThis talk presents approaches for bootstrapping NLP pipelines and retrieval via information extraction, including tips for training, modelling and data annotation.
Newsletter June 2024The latest edition of our newsletter, featuring real-world examples of NLP, how to distill LLMs into smaller & faster components and why there’s no need to compromise on best practices and privacy.
Simply Simplify LanguageInteractive app by the Canton of Zurich, Switzerland, using LLMs and spaCy to analyze and simplify institutional communication and make bureaucratic German more inclusive.
KI – Die künstlerische Intelligenz?Immergut Festival (German)Panelists are discussing the latest developments in Generative AI, hype vs. reality and what those new technologies mean for people, businesses, art, creativity and the music industry.
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMsPyCon DE & PyData BerlinWith the latest advancements in NLP and LLMs, and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies?
Designing for tomorrow’s programming workflowsPyCon LithuaniaModern 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?
spacy-llm: From quick prototyping with LLMs to more reliable and efficient NLP solutionsAstraZeneca NLP Community of PracticeLLMs are paving the way for fast prototyping of NLP applications. Here, Sofie showcases how to build a structured NLP pipeline to mine clinical trials, using spaCy and spacy-llm. Moving beyond a fast prototype, she offers pragmatic solutions to make the pipeline more reliable and cost efficient.
Half hour of labeling power: Can we beat GPT?PyData NYCLarge Language Models (LLMs) offer a lot of value for modern NLP and can typically achieve surprisingly good accuracy on predictive NLP tasks. But can we do even better than that? In this workshop we show how to use LLMs at development time to create high-quality datasets and train specific, smaller, private and more accurate models for your business problems.
MP Interests Tracker: Utilising GenAI to uncover insights in the UK Register of Financial InterestJournalismAI BlogProject from teams at The Times and BBC using spacy-llm to make complex financial interests data more accessible.
Large Language Models: From Prototype to ProductionEuroPython KeynoteLarge Language Models (LLMs) have shown some impressive capabilities and their impact is the topic of the moment. 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.
🦙 spacy-llm v0.3.0Jun 14, 2023Cohere, Anthropic, OpenLLaMa, StableLM, logging, streamlit demo, lemmatization task
Large Disagreement Modelling“In this blogpost I’d like to talk about large language models. There’s a bunch of hype, sure, but there’s also an opportunity to revisit one of my favourite machine learning techniques: disagreement.”
Applied NLP in the Age of Generative AIPyData Amsterdam KeynoteIn this talk, Ines shares the most important lessons we’ve learned from solving real-world information extraction problems in industry, and shows you a new approach and mindset for designing robust and modular NLP pipelines in the age of Generative AI.
How S&P Global is making markets more transparent with NLP, spaCy and ProdigyA case study on S&P Global’s efficient information extraction pipelines for real-time commodities trading insights in a high-security environment.
Towards Structured Data: LLMs from Prototype to ProductionU.S. Census Bureau: Center for Optimization and Data Science SeminarThis 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.
ZenML v0.58.0New 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.
The AI Revolution Will Not Be Monopolized: Behind the scenesOpen Source ML MixerA more in-depth look at the concepts and ideas, academic literature, related experiments and preliminary results for distilled task-specific models.
Zero-Shot NER with GliNER and spaCy Python Tutorials for Digital HumanitiesTutorial by WJB Mattingly on how to integrate the generalist GLiNER model for Named Entity Recognition with spaCy's versatile NLP environment.
Herding LLMs Towards Structured NLPGlobal AI ConferenceThis 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.
How many Labelled Examples do you need for a BERT-sized Model to Beat GPT-4 on Predictive Tasks?Generative AI SummitHow 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.
Panel: Large Language ModelsBig PyData BBQwith Ines, Alejandro Saucedo (Zalando, Institute for Ethical AI & ML), Alina Lehnhard (Cerence), Michael Gerz (Heidelberg University), Alexander CS Hendorf (Königsweg)
Against LLM maximalismLLMs 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.
Applied NLP with LLMs: Beyond Black-Box MonolithsPyBerlinIn 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.
Combining the Best of Two Worlds: From TF-IDF to Llama LLMOpen Source Summit EuropeTalk by William Arias, Staff Developer Advocate at GitLab, on combining traditional NLP techniques and LLMs to solve hallucination issues and create robust spaCy applications.
The AI Revolution Will Not Be MonopolizedInfoQOpen-source initiatives are pivotal in democratizing AI technology, offering transparent, extensible tools that empower users. Daniel Dominguez summarizes the key takeaways from Ines’ recent talk for InfoQ.
Exploring the AI nexus with the mind behind spaCyLeading With Data PodcastIn this episode, Matt takes you on a deep dive into the future of data and the challenges facing current Large Language Models (LLMs).
spaCy meets LLMs: Using Generative AI for Structured DataData+ML Community MeetupThis 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.
Getting Started with NLP and spaCyTalkPython CourseThere 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.
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMsQCon London
Constructing a knowledge base with spaCy and spacy-llmMantisNLP BlogThis blog post shows how to use spaCy and LLMs to extract entities and relationships from text and quickly tackle the complex problem of constructing a knowledge base graph from a corpus.
Prodigy in 2023: LLMs, task routers, QA and pluginsWe have made a ton of new updates in Prodigy this year with v1.12, v1.13, and v1.14 releases. So we decided to write a post about them.
Identifying Signs and Symptoms of Urinary Tract Infection from Emergency Department Clinical Notes Using Large Language ModelsIscoe, Socrates, Gilson, Chi, Li, Huang, Kearns, Perkins, Khandjian, Taylor (2023)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.
🦙 spacy-llm v0.5.0Sep 8, 2023Improved user API and novel Chain-of-Thought prompting for more accurate NER
Models as annotators in ProdigyHow to use models and LLMs as annotators to find disagreements and prioritize examples to annotate first.
Newsletter May 2023We got so much amazing feedback from the spaCy user survey, thank you all for your contributions! The most requested feature was spaCy integration with LLMs, which is why we’re so excited to announce spacy-llm!
