leanderme/sytora
A sophisticated smart symptom search engine
Implements multilingual symptom-disease classification using a multinomial Naive Bayes classifier trained on curated datasets and standardized through UMLS coding for cross-language support. The backend Flask service integrates cui2vec embeddings for related symptom recommendations, while a React frontend provides the search interface. Data is sourced from public disease-symptom knowledge bases and CC4.0-licensed manual annotations, with deployment via Gunicorn and Nginx.
178 stars. No commits in the last 6 months.
Stars
178
Forks
91
Language
JavaScript
License
—
Category
Last pushed
Nov 19, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/leanderme/sytora"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gustavz/DataChad
Ask questions about any data source by leveraging langchains
e-m3din4/booby-trap-pdf
Embed malware, apks, executables or any other binary file into a PDF, or generate a PDF with...
knowledge-ukraine/medlocalgpt
⚕️ Applying LLM-powered AI Agents to Support for Physical Rehabilitation & Telerehabilitation...
Dr-Hutchinson/nicolay
Nicolay is a digital history experiment that uses artificial intelligence to explore the...
Rakshath66/Chat-With-Your-PDF
Streamlit-based chatbot to interact with PDFs using Retrieval-Augmented Generation (RAG), FAISS,...