Published inDiscovery at NestaBuilding an AI chatbot with Streamlit and OpenAI’s GPT-4 to drive engagement with online contentHow we used LLMs and prompt engineering to build a custom chatbot to engage readers with long-form content about future signalsFeb 7Feb 7
Published inDiscovery at NestaHow to evaluate large language model chatbots: experimenting with Streamlit and ProdigyWe describe our initial experiments of using Streamlit and Amazon S3 to log user feedback, as well as performing A/B tests using Prodigy.Oct 17, 2023Oct 17, 2023
Published inData science at NestaTutorial: data-driven news discourse analysis with Python (Part 2)Measure word collocations, use spaCy to extract linguistic features, and consider LLMs in speeding up your discourse analysisSep 25, 2023Sep 25, 2023
Published inData science at NestaTutorial: data-driven news discourse analysis with Python (Part 1)Start piecing together the narrative by collecting news articles, analysing trends and using sentence embeddings to uncover themesSep 25, 2023Sep 25, 2023
Published inDiscovery at NestaCombining WhatsApp with large language models: prototyping with Twilio and FlaskExploration of building a WhatsApp chatbot prototype to answer questions and generative personalised activities for early-years educatorsAug 15, 20231Aug 15, 20231
Published inDiscovery at NestaCan we harness generative AI for social good?Nesta’s Discovery Hub is launching a new project to find impactful use cases of generative AI in education, health and sustainabilityJun 16, 20233Jun 16, 20233
Published inDiscovery at NestaTaming and training hunches: Data analytics and foresightHow Nesta’s Discovery Hub harnesses data science to deepen our capacity to evaluate possible futuresJan 3, 2023Jan 3, 2023
How to embed interactive Altair charts in MediumAltair is a great python package for creating interactive charts, and you can bring this interactivity to your Medium posts as well.Sep 12, 2022Sep 12, 2022
