neu ml

Applying machine learning to solve everyday problems.

NeuML builds open-source, easy-to-use, semantic workflow applications. We bridge the gap between research and production.

We also provide the following services around our stack to help jump start your machine learning journey. Contact us to learn more.

  • Advisory and Strategy Support Leverage our expertise to build your data and AI strategy
  • Model Development Create custom AI, Machine Learning and/or NLP models that excel in industry-specific domains
  • Training Group training covering how to implement our open-source stack
  • AI-driven Literature Review Automate reviews of large-scale unstructured medical, scientific and research literature
  • Cloud-native Workflows Scalable NLP workflows for semantic search, summarization, translation and more
  • Media Analytics Sentiment analysis, event discovery and trend detection

Applications

txtai

txtai project

txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications. txtai supports indexing text snippets, documents, audio, images and video. Pipelines and workflows enable transforming data with machine-learning models. NeuML uses txtai and/or the concepts behind it to power all of our Natural Language Processing (NLP) applications.

List of applications powered by txtai:

  • paperai - AI-powered literature discovery and review engine for medical/scientific papers
  • tldrstory - AI-powered understanding of headlines and story text
  • neuspo - Fact-driven, real-time sports event and news site
  • codequestion - Ask coding questions directly from the terminal

paperai

paperai project

paperai is an AI-powered literature discovery and review engine for medical/scientific papers. paperai helps automate tedious literature reviews allowing researchers to focus on their core work. Queries are run to filter papers with specified criteria. Reports powered by extractive question-answering are run to identify answers to key questions within sets of medical/scientific papers.

paperai was used to analyze the COVID-19 Open Research Dataset (CORD-19), winning multiple awards in the CORD-19 Kaggle challenge.

paperai and/or NeuML has been recognized in the following articles:

tldrstory

tldrstory project

tldrstory is a framework for AI-powered understanding of headlines and text content related to stories. tldrstory applies zero-shot labeling over text, which allows dynamically categorizing content. A customizable Streamlit application and FastAPI backend service allows users to review and analyze the data processed.

neuspo

neuspo project

neuspo is laser-focused on identifying fact-driven, real-time event data from sports social media and news data. The platform looks to set an example of media providing tailored experiences to distinct topics of interest, with clarity into how content is recommended.

Articles

Build AI-powered semantic search applications

Search is the base of many applications. Once data starts to pile up, users want to be able to find it. It's the foundation of the internet and an ever-growing challenge that is never solved or done. This article discusses how txtai can be used to build AI-powered semantic search applications.

Run machine-learning workflows to transform data

txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications. This article covers methods to vectorize data, machine-learning pipelines and workflows.

Serverless Vector Search with txtai

Serverless application development is a popular way for developers to skip over the complexity of servers and focus on delivering products to their users. This article shows how to build a txtai vector search instance on a Kubernetes-based environment with Knative.

AI-powered understanding of headlines and story text

Headlines and other attention-grabbing content is constantly put on our screens to try to get us to click through. Putting together a good headline is almost as important as the content. What if we can use NLP to better understand headlines? This article introduces tldrstory, an AI-powered framework for understanding headlines and story text.

Meet the team

profile image

David Mezzetti - Founder/CEO

linkedin twitter medium github

David Mezzetti founded NeuML to apply machine learning to solve everyday problems. He is leading the way in building open-source, easy-to-use, semantic workflow applications.

Dave previously co-founded and built Data Works from the ground up into a 50+ person well-respected software services company. In 2019, Data Works was acquired by E3/Sentinel.

Dave is also an active Medium contributor, his articles have been published with Towards Data Science and Better Programming.