Embedding large language models (LLMs) into unstructured data workflows using Python
A three-hour, online, hands-on workshop where participants use a large language model (LLM) to analyse unstructured data.
On this page:
Research often involves working through large volumes of unstructured material, such as text, images, and other formats that don't fit neatly into rows and columns. This can be time-consuming to process by hand and difficult to scale. Building on concepts showcased in the Introduction to AI-assisted workflows for unstructured data: Demonstrating programmatic use of LLMs workshop, participants will build, using the Python programming language, an AI-assisted workflow that leverages LLMs to extract features and identify themes across collections of unstructured data (such as text and images). Participants need basic experience with Python as this workshop involves writing and executing Python code.
Event details
Dates for 2026:
- Tuesday 14 April, 1pm-4pm
- Tuesday 6 October, 1pm-4pm
Learning outcomes
- Build an LLM-assisted workflow to aid analyses of unstructured data
- Practice effective prompting techniques to prepare, label, and analyse unstructured data
- Identify key ethical risks, including bias, data privacy, and model hallucinations and sycophancy
- Critically evaluate and validate LLM outputs
After the workshop
- Researchers and postdoctoral students are encouraged to engage with their peers by joining Hacky Hour to post questions and exchange ideas, and to contact Centre for eResearch (CeR) staff.
Contact
Research Data Support Services
Email: researchdata@auckland.ac.nz
Toby Johnson
eResearch Engagement Specialist, Centre for eResearch
Email: toby.johnson@auckland.ac.nz