The Curious Engineer

All blogs / AI / ML

Explosion · RSS Feed

explosion.ai

Explosion is a software company specializing in developer tools and tailored solutions for Artificial Intelligence and Natural Language Processing. We’re the makers of spaCy, one of the leading open-source libraries for advanced NLP.

AI / MLPythonDev tools / editors / IDEs

’15’20’25
Posts
384 from 18 Sep 2013 to 29 Oct 2026
Posting
monthly (23 in the last year)
Kind
company blog
Feed
https://explosion.ai/feed/

2026 20

  1. 🪎 ellf-templates
  2. Evaluate and optimize LLM pipelines with Ellf
  3. Agent UX: Building developer tools for humans and their coding agents
  4. Introducing Ellf: The missing piece for building NLP with coding assistants
  5. Ellf: Your virtual NLP engineer
  6. Ellf: our new tool for agentic NLP development
  7. Happy 10th Anniversary!
  8. Vibe NLP for Applied NLP
  9. Build-to-own AI: Agentic Development for Humans
  10. Atomic NLP
  11. A quick chat with Ines & Matt
  12. Taking back control of your AI development
  13. Show Us Your (Agent) Skills
  14. Building Multimodal Corpora Using Microtask Pipelines and Local Annotators
  15. Vibe NLP for Applied NLP
  16. A Century of Immigration Rhetoric in the UK Parliament
  17. How rightwing rhetoric has risen sharply in the UK parliament
  18. The ultimate guide to optimizing annotation workflows
  19. Style tips for less experienced developers coding with AI
  20. RiCoRecA: rich cooking recipe annotation schema

2025 25

  1. Engineering a human-aligned LLM evaluation workflow with Prodigy and DSPy
  2. Building AI with AI
  3. How AI is reshaping IT skills
  4. Sovereign AI systems instead of black box solutions
  5. Conquering PDFs: document understanding beyond plain text
  6. Applied NLP in the Age of Generative AI: Future-Proof Strategies for Banking and Finance
  7. E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
  8. Developer Trends in 2025
  9. AI in Reality Fireside Chat: Enterprise AI & Open-Source Innovation
  10. Feminist AI LAN Party
  11. Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content
  12. KI ohne Ketten: Warum Open Source gegen Big Tech gewinnen kann
  13. KI zwischen Freiheit und Kontrolle: The AI Revolution Will Not Be Monopolized
  14. How to advocate for modular NLP in the age of Generative AI
  15. How Love Without Sound helps the music industry recover millions in revenue for artists with NLP, spaCy and Prodigy
  16. 📚 spacy-layout v0.0.12
  17. Künstliche Intelligenz: Technologie der Zukunft – und warum Open Source die Karten neu mischt
  18. ✨ prodigy v1.18.0
  19. Mastering spaCy
  20. Prozessvisualisierung mit generativer KI im Praxistest
  21. What the history of the web can teach us about the future of AI
  22. What the history of the web can teach us about the future of AI
  23. Using natural language processing to identify emergency department patients with incidental lung nodules requiring follow-up
  24. Best Way to OCR a PDF in Python
  25. Streaming spaCy

2024 65

  1. Prodigy Dashboard Plugin
  2. Cracking the Code: How to Start a Career in AI
  3. spaCy Natural Language Processing: From Beginner to Advanced
  4. PyLadies entrepreneurs and career development
  5. Recognising non-named spatial entities in literary texts: a novel spatial entities classifier
  6. From PDFs to AI-ready structured data: a deep dive
  7. 🔌 prodigy-pdf v0.4.0
  8. 🔌 prodigy-pdf v0.3.0
  9. uOttawa at LegalLens-2024: Transformer-based Classification Experiments
  10. Distill Your LLMs and Surpass Their Performance
  11. Serverless custom NLP with LLMs, Modal and Prodigy
  12. Accelerate your Career with Open-Source AI
  13. Reality is not an End-to-End Prediction Problem: Applied NLP in the Age of Generative AI
  14. Applied NLP with LLMs: Beyond Black-Box Monoliths
  15. The 100 who are shaping AI in Europe
  16. 💫 spacy v3.8.0
  17. Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
  18. Applied NLP in the Age of Generative AI
  19. Combining the Best of Two Worlds: From TF-IDF to Llama LLM
  20. How GitLab uses spaCy to analyze support tickets and empower their community
  21. Szczecin stolicą programowania
  22. 10 Years of Open Source: Navigating the Next AI Revolution
  23. Assessing Fine-Tuned NER Models with Limited Data in French: Automating Detection of New Technologies, Technological Domains, and Startup Names in Renewable Energy
  24. The NLP and AI Revolution with the spaCy Creators
  25. spaCy Chunks v0.0.2
  26. Practical Tips for Bootstrapping Information Extraction Pipelines
  27. The Window-Knocking Machine Test
  28. Toward Automatic Summarization of Hospital Discharge Notes
  29. Back to our roots: Company update and future plans
  30. Building the Future of NLP: Insights on spaCy, Prodigy and Generative AI
  31. Happy 10th Birthday, spaCy!
  32. The AI Revolution Will Not Be Monopolized
  33. Once a Maintainer: Sofie Van Landeghem
  34. A practical guide to human-in-the-loop distillation
  35. How S&P Global is making markets more transparent with NLP, spaCy and Prodigy
  36. How to uncover and avoid structural biases in evaluating your Machine Learning/NLP projects
  37. Simply Simplify Language
  38. Exploring the AI nexus with the mind behind spaCy
  39. Towards Structured Data: LLMs from Prototype to Production
  40. spaCy meets LLMs: Using Generative AI for Structured Data
  41. The AI Revolution Won’t Be Monopolized
  42. KI – Die künstlerische Intelligenz?
  43. ZenML v0.58.0
  44. Getting Started with NLP and spaCy
  45. The application of natural language processing for the extraction of mechanistic information in toxicology
  46. Economies of Scale Can’t Monopolise the AI Revolution
  47. spaCyEx v0.0.2
  48. The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
  49. The AI Revolution Will Not Be Monopolized: Behind the scenes
  50. 🔮 thinc v9.0.0
  51. 🤖 curated-transformers v2.0.0
  52. Ines Montani on Natural Language Processing
  53. The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs
  54. Designing for tomorrow’s programming workflows
  55. 🦦 weasel v0.4.0
  56. 🔌 prodigy-evaluate v0.1.0
  57. Zero-Shot NER with GliNER and spaCy
  58. Constructing a knowledge base with spaCy and spacy-llm
  59. T-RAG: Lessons from the LLM Trenches
  60. How Nesta uses NLP to process 7m job ads and shed light on the UK’s labor market
  61. Describing Images Fast and Slow: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes
  62. KAZU v1.5
  63. spacy-llm: From quick prototyping with LLMs to more reliable and efficient NLP solutions
  64. Microsoft Presidio v2.2.352
  65. 🦙 spacy-llm v0.7.0

2023 94

  1. Muted: Multilingual Targeted Offensive Speech Identification and Visualization
  2. Prodigy-Segment for Pixel Segmentation
  3. 🔌 prodigy-segment v0.1.0
  4. Herding LLMs Towards Structured NLP
  5. DeepZensols: A Deep Learning Natural Language Processing Framework for Experimentation and Reproducibility
  6. On the Creation of Classifiers to Support Assessment of E-Portfolios
  7. Prodigy in 2023: LLMs, task routers, QA and plugins
  8. Neuradicon: operational representation learning of neuroimaging reports
  9. Who said what: using machine learning to correctly attribute quotes
  10. Impoliteness and morality as instruments of destructive informal social control in online harassment targeting Swedish journalists
  11. calamanCy: A Tagalog Natural Language Processing Toolkit
  12. Developing a Named Entity Recognition Dataset for Tagalog
  13. 🔌 prodigy-whisper v0.1.0
  14. State-of-the-Art Transformer Pipelines in spaCy
  15. Half hour of labeling power: Can we beat GPT?
  16. GERNERMED++: Semantic annotation in German medical NLP through transfer-learning, translation and word alignment
  17. Prodigy-ANN for Image Retrieval via CLIP
  18. Explosion, NLP, Generative AI, Entrepreneurship
  19. How many Labelled Examples do you need for a BERT-sized Model to Beat GPT-4 on Predictive Tasks?
  20. Prodigy-PDF for PDF annotation and OCR
  21. Toward a Critical Toponymy Framework for Named Entity Recognition: A Case Study of Airbnb in New York City
  22. 🔌 prodigy-hf v0.1.0
  23. Identifying Signs and Symptoms of Urinary Tract Infection from Emergency Department Clinical Notes Using Large Language Models
  24. DaCy v2.7.2
  25. Natural Language Processing and Python
  26. Finding Video Games with Sense2Vec
  27. 🦙 spacy-llm v0.6.0
  28. 🔌 prodigy-lunr v0.1.0
  29. 🔌 prodigy-ann v0.1.0
  30. 🔌 prodigy-pdf v0.1.0
  31. 🤖 curated-transformers v1.3.0
  32. 💫 spacy v3.7.0
  33. scispacy v0.5.3
  34. MP Interests Tracker: Utilising GenAI to uncover insights in the UK Register of Financial Interest
  35. 🛸 spacy-transformers v1.3.1
  36. Panel: Large Language Models
  37. Natural Intelligence is All You Need[tm]
  38. 🦙 spacy-llm v0.5.0
  39. Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts
  40. Models as annotators in Prodigy
  41. 🦦 weasel v0.3.0
  42. 🔮 thinc v8.2.0
  43. How to Host Your Own API of Open Language Models For Free
  44. 🦦 weasel v0.2.0
  45. 🤖 curated-transformers v1.0.0
  46. Large Language Models: From Prototype to Production
  47. Task Routers in Prodigy
  48. ACL LAW Workshop Poster
  49. Introducing spaCy v3.6
  50. 🦙 spacy-llm v0.4.0
  51. Prodigy v1.12: OpenAI integration, prompt engineering, task routers, deployment docs and more
  52. 🍬 confection v0.1.0
  53. Concepts and measures of bureaucratic constraints in European Union laws from hand-coding to machine-learning
  54. spaCy: a customizable NLP toolkit designed for developers
  55. 🦙 spacy-llm v0.3.0
  56. 🦦 weasel v0.1.0
  57. Inter-rater agreement for the annotation of neurologic signs and symptoms in electronic health records
  58. How Good is the Model in Model-in-the-loop Event Coreference Resolution Annotation?
  59. Large Language Models: From Prototype to Production
  60. SpanCat with spaCy and Prodigy on real data
  61. Finding Bad Labels for Text Classification with Jupyter and Prodigy
  62. 🦙 spacy-llm v0.2.0
  63. Against LLM maximalism
  64. 🦙 spacy-llm v0.1.0
  65. Efficient Information Extraction From Text With spaCy
  66. spaCy Plugin for VSCode
  67. Implementing a custom trainable component for relation extraction
  68. You are what you read: Building a personal internet front-page with spaCy and Prodigy
  69. Incorporating LLMs into practical NLP workflows
  70. Predicting relations between SOAP note sections: The value of incorporating a clinical information model
  71. Finding Duplicates in Tabular Data with Jupyter and Prodigy
  72. Intro to NLP with spaCy for Digital Humanities
  73. The Tale of Bloom Embeddings and Unseen Entities
  74. Creating Custom Event Data Without Dictionaries: A Bag-of-Tricks
  75. textaCy v0.13.0
  76. Rulers, NER, and data iteration
  77. Slovak Dataset for Multilingual Question Answering
  78. Modular Journalism: The new way to find stories?
  79. The Nesta Skills Extractor Library
  80. Fiscal data in text: Information extraction from audit reports using Natural Language Processing
  81. NLP: From Prototype to Production
  82. Deploying a Prodigy cloud service for Posh’s financial chatbots
  83. 🕊️ radicli v0.0.3
  84. Towards a Tagalog NLP pipeline
  85. AI/ML for the rest of us
  86. Calmcode, Explosion, Data Science
  87. Introducing spaCy v3.5
  88. Explosion in 2022: Our Year in Review
  89. Robust solutions with Explosion’s applied NLP philosophy
  90. Training spaCy NER Models with Prodigy
  91. 🛸 spacy-transformers v1.2.0
  92. Reflections on a year of spaCy consulting at Explosion
  93. Extracting Structured Information from Greek Legislation Data
  94. WW2 spaCy v0.0.9

2022 41

  1. Setting your ML project up for success
  2. Multi hash embeddings in spaCy
  3. Data is the new coffee
  4. Group-by statements that save the day
  5. How the Guardian uses AI to analyse articles
  6. Custom Interfaces with blocks
  7. The triangulation of ethical leader signals using qualitative, experimental, and data science methods
  8. Is it possible to have entities within entities within entities?
  9. Fast transformer inference with Metal Performance Shaders
  10. Tools to Improve Training Data
  11. Coreference Resolution in spaCy
  12. Finetuning and Bulk Labelling Images with Prodigy
  13. medspacy v1.0
  14. spaCy Cheat Sheet
  15. How the Guardian approaches quote extraction with NLP
  16. End-to-end Neural Coreference Resolution in spaCy
  17. 🧪 spacy-experimental v0.6.0
  18. spaCy behind the scenes: library patterns & design concepts explained
  19. floret: lightweight, robust word vectors
  20. 🍏 thinc-apple-ops v0.1.0
  21. Introducing Holmes 4.0
  22. Introducing spaCy v3.4
  23. Speech acts in the Dutch COVID-19 Press Conferences
  24. Bulk Labelling and Prodigy
  25. Introducing Span Categorization in Prodigy and spaCy
  26. Spancat: a new approach for span labeling
  27. 🧪 spacy-experimental v0.5.0
  28. Evolution of spaCy
  29. Diary of a spaCy project: Predicting GitHub Tags
  30. Solutions for Advanced NLP for Diverse Languages
  31. Introducing spaCy v3.3
  32. How we built a Stack Overflow Community questions analyzer
  33. Finding Bad Image Data using UMAP and Prodigy
  34. Compact word vectors with Bloom embeddings
  35. Automated Identification of Clinical Procedures in Free-Text Electronic Clinical Records with a Low-Code Named Entity Recognition Workflow
  36. skweak v0.3.1
  37. Applied Language Technology
  38. 🧪 spacy-experimental v0.4.0
  39. Introducing spaCy Tailored Pipelines
  40. When Women Make Headlines
  41. Creating Tools that Spark Joy with Ines Montani

2021 33

  1. Explosion in 2021: Our Year in Review
  2. Healthsea: an end-to-end spaCy pipeline for exploring health supplement effects
  3. Universal Dependencies v2.5 Benchmarks for spaCy
  4. Neural edit-tree lemmatization for spaCy
  5. Talking sense: using machine learning to understand quotes
  6. spaCy v3's project and config systems are pretty great
  7. Introducing spaCy v3.2
  8. 🌸 floret v0.10.0
  9. 🛸 spacy-transformers v1.1.0
  10. Anecdotes from 11 Role Models in Machine Learning
  11. We’ve sold 5% of Explosion
  12. Reproducible spaCy NLP Experiments with Weights & Biases
  13. Introduction to Japanese Natural Language Processing
  14. Mastering spaCy
  15. Introducing spaCy v3.1
  16. 🤗 spacy-huggingface-hub v0.0.1
  17. Applied NLP Thinking: How to Translate Problems into Solutions
  18. Interview: Ines Montani & Sebastián Ramírez
  19. What does “real-world NLP” look like and how can students get ready for it?
  20. spaCy v3: State-of-the-art NLP from Prototype to Production
  21. Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence
  22. Building Industrial-Strength NLP Applications
  23. A Bit of AI Episode 7
  24. Intro to NLP with spaCy (6): Detecting programming languages
  25. How We Found Pricey Provisions in New Jersey Police Contracts
  26. 🦆 sense2vec v2.0.0
  27. spaCy v3: Custom trainable relation extraction component
  28. spaCy v3: Design concepts explained (behind the scenes)
  29. 🛸 spacy-transformers v1.0.0
  30. spaCy v3: State-of-the-art NLP from Prototype to Production
  31. Introducing spaCy v3.0
  32. 🔮 thinc v8.0.0
  33. Building a Data Science Startup

2020 23

  1. Explosion in 2020: Our Year in Review
  2. How to build resilient NLP applications
  3. Building Industrial-Strength NLP Pipelines
  4. Ines becomes a Python Software Foundation Fellow
  5. spaCy v3.0: Bringing State-of-the-art NLP from Prototype to Production
  6. Ines Montani brought linguistic and computers together
  7. How We Analyzed Google’s Search Results
  8. The Physical Traits that Define Men and Women in Literature
  9. 👑 spacy-streamlit v0.0.2
  10. 🦉 srsly v2.1.0
  11. Designing Practical NLP Solutions
  12. Prodigy v1.10: Dependencies, relations, audio, video & more
  13. Introducing spaCy v2.3
  14. Intro to NLP with spaCy (5): Detecting programming languages
  15. 🛸 spacy-transformers v0.6.0
  16. Training a custom entity linking model with spaCy
  17. Identifying Predictors of Suicide in Severe Mental Illness: A Feasibility Study of a Clinical Prediction Rule
  18. Image Captioning with Prodigy & PyTorch
  19. Training a Named Entity Recognition Model with Prodigy and Transfer Learning
  20. Intro to NLP with spaCy (4): Detecting programming languages
  21. Building customizable NLP pipelines with spaCy
  22. PyCon Colombia Speaker Interview
  23. The Future of NLP in Python

2019 38

  1. Explosion in 2019: Our Year in Review
  2. Intro to NLP with spaCy (3): Detecting programming languages
  3. sense2vec reloaded: contextually-keyed word vectors
  4. 🦆 sense2vec v1.0.0
  5. Künstliche Intelligenz Beyond the Hype
  6. spaCy meets Transformers
  7. Interview with Ines Montani
  8. Let Them Write Code
  9. Using spaCy with Hugging Face Transformers
  10. Explosion awarded META Seal of Recognition
  11. spaCy and the future of multi-lingual NLP
  12. Introducing spaCy v2.2
  13. Entity linking for spaCy: Grounding textual mentions
  14. Intro to NLP with spaCy (2): Detecting programming languages
  15. Millennials Kill Everything
  16. Intro to NLP with spaCy (1): Detecting programming languages
  17. Blackstone v0.1.15
  18. spaCy meets Transformers: Fine-tune BERT, XLNet and GPT-2
  19. PyDev of the Week: Ines Montani
  20. Episode 139: f"Yes!" for the f-strings
  21. spaCy and Explosion: past, present & future
  22. David Dodson: spaCy in the News: Quartz’s NLP pipeline
  23. McKenzie Marshall: NLP in Asset Management (Barings)
  24. Patrick Harrison: Financial NLP at S&P Global
  25. Mark Neumann: ScispaCy: A spaCy pipeline & models for scientific & biomedical text
  26. Applied NLP: Lessons from the Field
  27. Entity linking functionality in spaCy
  28. spaCy IRL 2019: 2 days of NLP in Berlin
  29. The Brains behind spaCy
  30. Practical transfer learning for NLP with spaCy and Prodigy
  31. Practical Natural Language Processing with spaCy and Prodigy
  32. Advanced NLP with spaCy: A free online course
  33. Introducing spaCy v2.1
  34. Building a software business with Python
  35. FAQ #1: Tips & tricks for NLP, annotation & training with Prodigy and spaCy
  36. Practical transfer learning for NLP with spaCy and Prodigy
  37. Frag deinen Kühlschrank: Wie künstliche Intelligenz die Welt verändert
  38. Where Do Corpora Come From?

2018 10

  1. The AI Revolution will not be Monopolized
  2. The process: Transforming spaCy’s docs
  3. How to Ignore Most Startup Advice and Build a Decent Software Business
  4. What 1.2 million parliamentary speeches can teach us about gender representation
  5. Building new NLP solutions with spaCy and Prodigy
  6. Can You Verifi This? Studying Uncertainty and Decision-Making About Misinformation
  7. Embed, encode, attend, predict
  8. Rapid NLP annotation
  9. Increasing Data Science Productivity: spaCy & Prodigy
  10. Explosion in 2017: Our Year in Review

2017 13

  1. Training a new entity type with Prodigy – annotation powered by active learning
  2. More than a Million Pro-Repeal Net Neutrality Comments were Likely Faked
  3. spaCy’s entity recognition model: incremental parsing with Bloom embeddings & residual CNNs
  4. Introducing custom pipelines and extensions for spaCy v2.0
  5. Training an insults classifier with Prodigy in ~1 hour
  6. Pseudo-rehearsal: A simple solution to catastrophic forgetting for NLP
  7. Building Prodigy: Our new tool for efficient machine teaching
  8. Prodigy: A new tool for radically efficient machine teaching
  9. Why Python’s the best language for AI (and how to make it even better)
  10. Reflections on running spaCy: commercial open-source NLP
  11. Supervised learning is great — it's data collection that's broken
  12. Supervised similarity: Learning symmetric relations from duplicate question data
  13. Deep text-pair classification with Quora's 2017 question dataset

2016 12

  1. Embed, encode, attend, predict: The new deep learning formula for state-of-the-art NLP models
  2. spaCy v1.0: Deep Learning with custom pipelines and Keras
  3. An open-source named entity visualizer for the modern web
  4. displaCy.js: An open-source NLP visualizer for the modern web
  5. Introducing Explosion AI
  6. How front-end development can improve Artificial Intelligence
  7. A natural language user interface is just a user interface
  8. SyntaxNet in context: Understanding Google's new TensorFlow NLP model
  9. Multi-threading spaCy's parser and named entity recognizer
  10. spaCy now speaks German
  11. Statistical NLP in the Ten Hundred Most Common English Words
  12. Sense2vec with spaCy and Gensim

2015 3

  1. Dead Code Should Be Buried
  2. How spaCy Works
  3. Introducing spaCy

2014 1

  1. Writing C in Cython

2013 2

  1. Parsing English in 500 Lines of Python
  2. A Good Part-of-Speech Tagger in about 200 Lines of Python

Undated 4

  1. Consulting
  2. Software
  3. Events
  4. Legal & Imprint