NeuML - Applying machine learning to solve everyday problems

Applying machine learning to solve everyday problems.

NeuML is the company behind txtai, one of the most popular open-source AI frameworks in the world. We are building a suite of applications to make it easy to integrate AI into production.

We also provide the following services around our stack to help jump start your AI journey.

Book an intro meeting or email us to learn more.

Generative AI Build agents, retrieval-augmented generation (RAG), large language model (LLM) orchestration and chat with your data systems
AI-driven Literature Analysis Automate analysis of unstructured medical, scientific and technical literature
Model Development Create AI, Machine Learning and/or NLP models that excel in industry-specific domains

Advisory and Strategy Leverage our expertise to plan your data, engineering and AI strategy
Proposals Integrate AI into your technical proposals utilizing our knowledge of industry trends
Development Support Meet with us, get txtai implementation guidance and/or outsource development

Applications

txtai

txtai is an all-in-one AI framework for semantic search, LLM orchestration and language model workflows. txtai is one of the most popular open-source AI frameworks in the world with over 10K ⭐'s on GitHub and thousands of downloads a week.

txtai provides the following features.

🔎 Vector search with SQL support
📄 Embeddings generation for text, documents, audio, images and video
💡 Retrieval Augmented Generation (RAG) pipelines
🤖 Agents that autonomously solve complex problems
️⚙️ Web and Model Context Protocol (MCP) APIs

Want us to host your txtai applications? Then join the txtai.cloud preview to learn more.

paperai

paperai is a semantic search and workflow application for medical/scientific papers. Applications range from semantic search indexes that find matches for medical/scientific queries to full-fledged reporting applications powered by AI.

paperai is built with txtai and has the following key features.

Transform unstructured medical and scientific literature into structured data
Semantic search powered by models finetuned for literature
Chat with your papers

Articles

Getting started with semantic search

Semantic search is a new category of search built on recent advances in Natural Language Processing (NLP). Large-scale general language models have rapidly pushed the field forward in ways unimaginable only a few years ago. This article gives a brief overview of semantic search and how it contrasts with keyword search.

Getting started with semantic workflows

Semantic workflows transform and find data driven by user intent. Workflows combine machine learning models together to create powerful transformation and processing functions. This article shows how to build workflows with txtai.

Getting started with RAG

Retrieval Augmented Generation (RAG) reduces the risk of generating factually incorrect data by limiting the context in which a Large Language Model (LLM) can generate answers. This article introduces RAG and covers the latest methods available.

What's new in txtai 8.0

txtai 8.0 adds agents. Agents automatically create workflows to answer multi-faceted user requests. Agents iteratively prompt and/or interface with tools to step through a process and answer questions. This article gives an overview of this new feature.

Meet the team

David Mezzetti - Founder/CEO

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 search and AI workflow applications.

Dave previously co-founded and built Data Works from the ground up into a 50+ person well-respected software services company. This led to a successful acquisition by E3/Sentinel.

Dave also publishes an active social media feed focused on AI, Machine Learning and NLP.