Benjamin Senst's repositories
llm-enhanced-ehr
Contribution to the LabLabAI AI Challenge Hackathon October 2023
streamlit-llm
The purpose of this application is to test LLM-generated interpretations of medical observations. The explanations are generated fully automatically by a large language model. This application should be used for experimental purposes only. It does not provide support for real world cases and does not replace advice from medical professionals.
board_certification
A personalized learning environment build with Streamlit.
llm-reasoning
This experimental application serves an open source large language model Llama-2 that is connect to a streamlit user interface. The user can define a list of custom symptoms or ICD-10 symptoms as input to the LLM. A two-step chain of prompts will output a list of differential diagnoses followed by a list of examinations to workup these diagnoses.
st-milvus-connection
Connect your streamlit app to milvus database. Open-source contribution to the Streamlit community.
board-certification-preparation
The healthcare questions and answers collected here are for educational purposes only. They may not be used for medical decision making.
Connections-Hackathon
Submission to the Streamlit Connections Hackathon
data-engineering-2024
Accompanies the Data Talks Club Data Engineering Course 2024 iteration
housing-germany
Machine learning project based on the Kaggle "Apartment rental offers in Germany" dataset for the Data Talks Club Machine Learning Zoomcamp 2023.
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
langchain
⚡ Building applications with LLMs through composability ⚡
Learn_Prompting
Prompt Engineering, Generative AI, and LLM Guide by Learn Prompting | Join our discord for the largest Prompt Engineering learning community
MedCATtrainer
A simple interface to inspect, improve and add concepts to biomedical NER+L -> MedCAT.
mistral
Improve medical history taking with support from a large language model. This application is for trial purposes alone. Personally identifying information should never be entered. The application may not be used in the real world. The application does not replace assessment by healthcare professionals.
mlbookcamp-code
The code from the Machine Learning Bookcamp book and a free course based on the book
packaging_tutorial
This is a test repository for publishing a pypi package.
projects
🪐 End-to-end NLP workflows from prototype to production
risingwave-data-talks-workshop-2024-03-04
DataTalks Workshop Materials
stock-markets-analytics-zoomcamp
Course Materials for Analytics in Stock Markets Zoomcamp
Text-De-Identifizierer
Automatic removal of direct personal identifiers
vectara-streamlit
contribution to the vectara hackathon