op405wm/Bakalarska_praca
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
20 Commits 1 Branch 0 Tags 32 MiB
TypeScript 56.4%
Python 38.3%
Dockerfile 2.2%
JavaScript 1.4%
CSS 1.1%
Other 0.6%
54b9229a40
Go to file
Oleh Poiasnik 54b9229a40 Добавить README.md
2025-05-21 20:04:42 +00:00
Backend Обновить Backend/model.py 2025-05-21 19:14:33 +00:00
elasticsearch upd 2025-04-06 15:27:22 +02:00
frontend upd 2025-04-06 15:27:22 +02:00
.gitattributes upd git attributes 2025-04-06 20:06:10 +02:00
.gitignore upd 2025-04-06 15:27:22 +02:00
docker-compose.yml upd 2025-04-06 15:27:22 +02:00
prepare.sh upd endpoint saving data, upd dockerfile backend with fixing elasticsearch waiting 2025-04-06 14:36:54 +02:00
README.md Добавить README.md 2025-05-21 20:04:42 +00:00

README.md

DrugConv: Conversational Drug Recommendation System

DrugConv is a modular, Python-based backend + React frontend application that helps users find relevant medication recommendations, dosages and explanations via a friendly conversational interface powered by Mistral LLM and Elasticsearch.

Features

  • Conversational QA – Ask natural-language questions about medications, indications, dosing, and get follow-ups.
  • Mistral LLM integration – Dual-model (“small” & “large”) pipelines for generation, validation and evaluation.
  • Vector & text search – Hybrid retrieval from Elasticsearch for up-to-date drug documentation.
  • Memory & context – Tracks patient age, anamnesis, prescription type for multi-turn dialogue.
  • React SPA frontend – Built with React, styled with Tailwind CSS and Material UI for a clean, responsive UI.