Blog
Creating Representative Samples of Software Repositories
Software repositories are one of the main sources of data for empirical software engineering. Choosing the right sample for your study is key. We create such sample for you.
How to use LLMs and RAG in a chatbot?
A great chatbot combines intent-based techniques for “can’t be wrong” questions together with RAG and LLMs techniques for more open, exploratory, questions
Automatic Generation of Conversational Interfaces for Tabular Data Analysis
Conversational User Interfaces (CUIs) such as chatbots and voicebots could improve the accessibility of tabular data. We are now introducing a scalable, no-code tool that automatically creates chatbots for tabular data based on a schema inferred from the data itself.
Building a Biases LLM Leaderboard
We have released the first (AFAIK) leaderboard for LLMs specialized in assessing their ethical biases, such as ageism, racism, sexism, among others.
You need an AI Policy in your software consultancy company ASAP
On the importance of writing an AI policy and guidelines for your company
Is Hugging Face Hub a good source of data for empirical studies on ML development?
Learning how machine learning projects are developed based on the empirical analysis of hugging face hub data
BESSER Bot Framework – A Python library to build chatbots
An open source and python-based framework to build all types of bots, chatbots and voicebots thanks to our bot DSL , NLP support and runtime engine
Landscape of the High-Performance Python Ecosystem
A survey on the libraries, frameworks and options to speed up the performance of your python programs.
For a more transparent governance of open source
A thorough analysis of open source projects in GitHub shows a massive lack of transparency. Some thoughts on why and how to fix this and evolve towards a more transparent governance in open source
A GitHub template repository with best practices to kick-start your new project
A template repository with best practices to kick-start your GitHub project, covering aspects like the contributing and governance guidelines, funding and security policies and much more!
Benchmarks for evaluating intent-based chatbots
Our collection of datasets to evaluate the quality of intent detection and entity recognition in chatbot libraries