Skip to main content

Add your description here

Project description

🏥 Patient Query Assistant with RAG + OpenAI API

A Python-based MCP Server that answers patient-specific medical queries using a Retrieval-Augmented Generation (RAG) system integrated with the OpenAI Chat Completions API.
The function retrieves context-specific medical data about a patient from an Azure AI Search (a Vector Database), and uses an LLM to generate precise, context-aware responses.


📖 Overview

This utility allows you to query a patient's medical information by providing:

  • patient_name: The name of the patient (as a string).
  • query: The natural language question you want to ask (as a string).

The system normalizes the patient’s name by removing spaces and converting it to lowercase, retrieves relevant data using an indexer, and sends this context along with your query to an OpenAI model to generate a smart, human-readable response.


🛠️ Features

✅ Patient name normalization (removes spaces and lowercases for consistent lookups)
✅ Retrieval-Augmented Generation (RAG) powered by Azure AI Search and Storage Accounts ✅ Natural language interaction via OpenAI Chat Completions API
✅ Designed for secure and context-aware medical information handling


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ho_rag-0.1.0.tar.gz (3.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ho_rag-0.1.0-py3-none-any.whl (5.4 kB view details)

Uploaded Python 3

File details

Details for the file ho_rag-0.1.0.tar.gz.

File metadata

  • Download URL: ho_rag-0.1.0.tar.gz
  • Upload date:
  • Size: 3.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.17

File hashes

Hashes for ho_rag-0.1.0.tar.gz
Algorithm Hash digest
SHA256 297007e787cee04e23024f575cdf305cd798fb1e6479e4dc186ad3db79371bda
MD5 9616bd0f7f781d501af433390101a4cb
BLAKE2b-256 3a2f83e18914f79288fc26dea6931bc970ae45c982d0109935ab1017712d3a08

See more details on using hashes here.

File details

Details for the file ho_rag-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: ho_rag-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 5.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.17

File hashes

Hashes for ho_rag-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c668b4abcfb0934eeb142e9bd3ee60bd22b36edec5cad008e7d71248cb2c74ad
MD5 d94a60af23c64d48633eb4f3022b438a
BLAKE2b-256 c8cbe150342a02d2cdac8cdb35c8d75d044a2695240d6dd3ef7df0f91f3fa0c6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page