MyGPT is a privacy-first, open-source Retrieval-Augmented Generation (RAG) platform with real-time confidence metrics and in-document source highlighting. Ask questions across your research papers, clinical protocols, and document collections—with verifiable citations and zero third-party API costs, running entirely on your personal device or institutional infrastructure.
A modular RAG stack designed for enterprise, research, and personal use, prioritizing security and factual accuracy.
Deploy locally on your computer or private network. Your confidential PDFs, research papers, and chat histories never leave your device.
Our pipeline forces the local LLM to rely strictly on the retrieved passages of your documents. Every response includes clickable source citations.
MyGPT calculates real-time metrics for every query: Question Relevance Score (QRS), Answer Relevance Score (ARS), and Hallucination Index (HI).
Built-in MCP server and client integration allows you to connect private database context and other LLM ecosystem tools securely.
By leveraging open-source LLMs through Ollama (like Llama 3, Gemma 2, and DeepSeek), you eliminate monthly API subscription fees entirely.
Build your searchable knowledge bases by directly uploading PDFs, importing shared Zotero folders, or organizing custom document collections.
A modular workspace engineered for researchers, clinical teams, and data analysts.
Simultaneously view questions with real-time confidence metrics, navigate library documents, and inspect original PDF pages with cited passage highlights.
Seamlessly expose private document context to Claude Desktop, IDEs, and other MCP-compliant autonomous agent pipelines.
Directly connect your personal or shared Zotero libraries to instantly synchronize collections of papers without manual file copying.
Customize token lengths, overlap margins, Chroma DB vector metrics, and BM25 hybrid indexing tailored to your specific literature domain.
Switch between Llama 3.1, Gemma 2, DeepSeek-R1, Mistral, or edge models with customizable temperature and top-p sampling on the fly.
See exactly how the local pipeline process resolves queries step-by-step from raw question to certified answer.
MyGPT
Ask a question about a paper or a topic from your publication library. We will try to answer it using the GPT models.
© 2026
Set up MyGPT on your system using our prebuilt Docker images and script controls.
Requires at least 8 CPUs, 8 GB RAM (16 GB recommended for faster responses), and 10 GB disk space. Ensure Homebrew, Git, Docker Desktop, and Ollama are installed.
ollama pull llama3
ollama pull nomic-embed-textgit clone https://github.com/stjude/MyGPT.git
cd MyGPTcp .env_backend.example .env_backend
cp .env_frontend.example .env_frontendThese files configure your local container parameters securely without committing secrets.
cd installation/macOS
bash run_docker.shAlternatively, launch directly with Docker Compose from the root folder: docker compose up -d. Once started, open http://localhost:3000 in your browser.
Requires at least 8 CPUs, 8 GB RAM (16 GB recommended), and 10 GB disk space. Compatible with both CPU and NVIDIA GPU acceleration.
sudo systemctl start ollama
ollama pull llama3
ollama pull nomic-embed-textgit clone https://github.com/stjude/MyGPT.git
cd MyGPT
cp .env_backend.example .env_backend
cp .env_frontend.example .env_frontendcd installation/linux
sudo sh run_docker.shFor GPU systems with CUDA: docker compose -f docker-compose-gpu.yml up -d
Ensure Docker Desktop (with WSL 2 backend) and Git are installed on your Windows PC.
ollama pull llama3
ollama pull nomic-embed-textgit clone https://github.com/stjude/MyGPT.git
cd MyGPT
copy .env_backend.example .env_backend
copy .env_frontend.example .env_frontendcd installation\windows
run_docker.batAccess the UI at http://localhost:3000.
For enterprise workgroups, we recommend distributing the frontend, Django backend, and Ollama server across three separate virtual machines. The Ollama VM should have dedicated high-performance GPU resources (CUDA setup).
Set the environment endpoints in your .env_frontend and .env_backend files:
REACT_APP_BACKEND_URL = 'http://<backend-vm-ip>:8000'
OLLAMA_HOST = 'http://<ollama-vm-ip>:11434'Deploy on Azure using isolated NC-series GPU VMs. The following configuration balances performance, security, and cost efficiency.
| Infrastructure Role | Recommended Azure VM Type | Specifications |
|---|---|---|
| LLM Inference Server | NC8as T4 v3 | 1x Nvidia T4, 8 vCPUs, 56 GB RAM |
| Django Backend + UI | E4ads v5 | 4 vCPUs, 32 GB RAM |
MyGPT was developed at St. Jude Children's Research Hospital to democratize privacy-first, verifiable literature exploration.
In text, cite this work as Patel et al. (in press) or (Patel et al., in press).
@article{patel2026mygpt,
author = {Patel, Jaimin and Downing, Jude and Ferguson, Hugh and You, Thika and Malinverni, Duccio and Mathew D. A., Steve and Chen, Ines and Sluter, Madison and Moorefield, Beth and Parej, Katalin and Ragavan, Mukundan and Morris, Cindy and Keerthi, Dinesh and Becerra Armada, Desiree and Meszaros, Balint and Trivedi, Vikas and Alam, Shahinur and Woodard, Anthony and Alford, Dan and Pathak, Sagar and Li, Cai and Umeton, Renato and Rodriguez-Galindo, Carlos and Lam, Catherine G. and Gottschalk, Stephen and Kalodimos, Charalampos G. and Babu, M. Madan},
title = {Democratizing reliable knowledge-seeking with MyGPT: A Privacy-First, Open-Source Retrieval-Augmented Generation Platform},
note = {In press},
doi = {10.5281/zenodo.22165249},
year = {2026}
}PDF document collection curated for biomedical question-answering evaluation, openly deposited in the evaluation repository.
Standardized literature benchmarks with full PMID and DOI references to validate factual precision against ground-truth answers.
Validated across complex global health policy documentation across multiple international languages without external API leakage.