zpwiki/pages/interns/bogdan_paul_chis/README.md
2026-03-20 09:52:13 +01:00

35 lines
992 B
Markdown

---
title: Bogdan Paul Chiș
published: true
taxonomy:
category: [erasmus]
tag: [nlp, ie, rag, medical]
author: Daniel Hladek
---
ERASMUS Intern Spring 2026, 20 March - 21 May (62 days)
Topic:
(multilingual) Triplet extraction from medical data
Goal:
- Construct a knowledge graph from medical package inserts in multiple languages
- Utilize the graph in an intelligent agent that recommends medication.
Tasks:
- Learn intelligent agents and generative models - OpenAI API, Agent frameworks, RAG systems.
- Learn about knowledge graphs and GraphRAG. Read several research papers.
- Prepare a Python based workflow, use git code repository
- Try Light RAG - Simple RAG.
- Scrape package inserts and parse the data.
- Index the data and write a script that extracts a knowledge graph from data.
- Visualize the graph
- Prepare an agent that utilizes the unstructured data and graph-data.
- Evaluate the agent using DeepEval or RAGAS.
- Write a report
- Put all code to GIT