-
JetBrains
- Berlin, Germany
-
simple-rag-document-qa Public
A simple RAG application for doing question-answering on a PDF document. Uses the PyCharm documentation as the source document and langchain to build the RAG pipeline.
-
-
lies-damned-lies-ts Public
A version of my talk on LLM hallucinations in TypeScript.
TypeScript UpdatedOct 1, 2024 -
can-you-trust-your-model Public
Resources for my talk, "Can you trust your (large language) model", given as a keynote at NDC Porto 2024.
5 UpdatedSep 27, 2024 -
-
beginners-data-workshop Public
Forked from mborus/beginners-data-workshopHumble Data aims to increase inclusivity and provide a safe community for Python and Data Science. We organise free workshops for people who are outside of the mainstream in the data science and te…
-
mirror-mirror Public
Materials for talk "Mirror, Mirror: LLMs and the Illusion of Humanity"
4 UpdatedJun 7, 2024 -
-
-
text-to-vectors Public
Repo containing supporting notebooks for "Text to vectors ... ?" presentation
-
reproducible-research Public
Resources for the talk "Building Reproducibility Into Your Data Science Projects With Datalore"
UpdatedOct 27, 2023 -
pandas Public
Forked from pandas-dev/pandasFlexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
-
intro_to_sprinting_codeless_project Public
Forked from chalmerlowe/intro_to_sprinting_codeless_projectA sample "code-less" project in support of the "Intro to Sprinting" workshop.
UpdatedApr 24, 2023 -
feature-trainer-ds-demos Public
A repo containing all of the required files for setting up the DS/PY data science demos for upcoming conferences in 2023.
-
scikit-learn Public
Forked from scikit-learn/scikit-learnscikit-learn: machine learning in Python
-
which-visualization-to-use Public
A repository containing code to accompany a blog post on "Picking the right data visualization".
Jupyter Notebook UpdatedJan 20, 2023 -
Blog-posts Public
A place for draft blog posts before deploying onto the website
-
-
vectorising-python Public
A collection of tutorials for using numpy functions to speed up data science code
-
my-versioned-workspace Public
Repo to demonstrate using Git with DataSpell
Jupyter Notebook UpdatedAug 15, 2022 -
-
gresearch-questions Public
Test notebooks for answering G-Research Jupyter questions
Jupyter Notebook UpdatedJun 7, 2022 -
-
grad-dipl-maths-notes Public
A collection of my personal notes while completing my Graduate Diploma in Mathematics
UpdatedAug 29, 2020 -
This repo contains the code files and Jupyter notebooks for an analysis I did to learn how to use scikit-learn in AWS Sagemaker. The analysis is a classification problem, where I predicted the corr…
Jupyter Notebook UpdatedJan 17, 2020 -
-
-
fortran95-tutorial Public
Basic exercises in Fortran 95 from http://www.fortrantutorial.com/basics/index.php
Jupyter Notebook UpdatedJul 3, 2017 -
text2num Public
Forked from ghewgill/text2numPython library to convert textual numbers to integers
Python UpdatedApr 16, 2017 -