Homepage
Open in app
Sign inGet started

MantisNLP

We are a consultancy helping companies to solve hard problems with Artificial Intelligence. We’ll be writing about machine learning and natural language processing in particular, chatbots, open source software, and more.

ChatGPT for GOV.UK

ChatGPT for GOV.UK

We’ve built an application based on ChatGPT for querying GOV.UK, but more up-to-date and with fewer errors, and it works rather well.
Go to the profile of Matthew Upson
Matthew Upson
Mar 15
Eight examples is all you need ✨

Eight examples is all you need ✨

It is no secret that the power of machine learning models comes from the data that they are trained on. It should come as no surprise then…
Go to the profile of Nick Sorros
Nick Sorros
Mar 1
Prompt Engineering — Part III — Examples of prompt construction

Prompt Engineering — Part III — Examples of prompt construction

In the last blog from our series, we covered how to construct a prompt for Large Language Models (LLMs). In this blog we’ll look at some…
Go to the profile of Popescu Daniel
Popescu Daniel
Feb 22

Why we’re switching to Hugging Face Inference Endpoints, and maybe you should too

Hugging Face recently launched Inference Endpoints. In this blog post we look at some of the pros and cons, and why we’re using them.
Go to the profile of Matthew Upson
Matthew Upson
Feb 15
Prompt Engineering — Part II — How to construct prompts

Prompt Engineering — Part II — How to construct prompts

The fundamentals for writing good prompts for a Large Language Models
Go to the profile of Popescu Daniel
Popescu Daniel
Feb 8
Prompt Engineering — Part I — How to interact with Large Language Models

Prompt Engineering — Part I — How to interact with Large Language Models

This is the first in a series of blog posts that will dive into prompt engineering. The blogs accompany the presentation by Daniel Popescu…
Go to the profile of Popescu Daniel
Popescu Daniel
Dec 21, 2022
Speed up 🏎️ data annotation with active learning ✨

Speed up 🏎️ data annotation with active learning ✨

Access to high quality annotated data remains one of the biggest limiting factors preventing companies from progressing an AI use case into…
Go to the profile of Nick Sorros
Nick Sorros
Nov 8, 2022
Extracting useful information from documents with Named Entity Recognition

Extracting useful information from documents with Named Entity Recognition

Working with a large charitable foundation to help them understand their data.
Go to the profile of Matthew Upson
Matthew Upson
Nov 1, 2022
Data Version Control for Reproducible Analytical Pipelines

Data Version Control for Reproducible Analytical Pipelines

Why DVC might be your RAP’s new best friend.
Go to the profile of Matthew Upson
Matthew Upson
Oct 17, 2022
Match text from different domains using language models 📑

Match text from different domains using language models 📑

Organizations with a large collection (corpus) of documents often need to find similar documents. For a grant-giving organization (for…
Go to the profile of Nick Sorros
Nick Sorros
Sep 28, 2022
About MantisNLPLatest StoriesArchiveAbout MediumTermsPrivacy