Kevin Armengol's repositories
data-dictionary-cui-mapping
This repository aims to speed up the process of querying and assigning relevant UMLS CUIs to fields in your data dictionary. Currently, you can customize batch query scripts that utilize the UMLS api, MetaMap api, and/or an experimental semantic search approach with vector embeddings. Further development in progress.
custom-agency-swarms
playground for custom gpts built with agency-swarms (https://github.com/VRSEN/agency-swarm)
brics-tools
studysearch_app is a Retrieval-Augmented-Generation (RAG) pipeline/interface for querying FITBIR Data Repository study metadata.
Animal-Rearing-Box-Sensors-and-Light-Cycle-
Arduino-controlled monitoring of temperature/humidity for animal housing with light cycle regulation
arealglam-gpt-backend
arealglam python backend for OpenAI gpt integration
boiler-plate
WIP: dev boiler plate repo for Python + Poetry + Cursor/VS Code
brics-crossmap
semantic search pipeline for mapping user variables to BRICS data elements
data-juicer
A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！
digital-cv
Kevin Armengol
fhir-to-brics
Scripts to create BRICS data elements from FHIR resources
FITBIR-study-closeout-analysis
scripts for running FITBIR Study Closeout Analysis pipeline
multi-agent-postgres-data-analytics
The way we interact with our data is changing.
OpenAI_Agent_Swarm
HAAS = Hierarchical Autonomous Agent Swarm - "Resistance is futile!"
developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
dspygen
A Ruby on Rails style framework for the DSPy (Demonstrate, Search, Predict) project for Language Models like GPT, BERT, and LLama.
GPT-4-Research-assistant
The GPT-4 Research Assistant is a tool designed to leverage the power of GPT-4 in assisting with academic research. It searches for academic papers on ArXiv, identifies the most promising paper based on a given search term, downloads the paper, extracts its contents, and then summarizes it. The tool also suggests new search terms
MemGPT
Teaching LLMs memory management for unbounded context 📚🦙
python-nextjs-template
A full stack webapp template using Python, NextJS, and PostgresQL
rc505mkii_scripts
Useful scripts for rc505
rdddy
Reactive DDD with DSPy
semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
xmc.dspy
In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.