🏥 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
1 maintainer
Metadata
1 maintainer
Release files for ho-rag 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| ho_rag-1.0.0.tar.gz | 4.3 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ho_rag-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 10.5 kB
Release files / ho_rag-1.0.0.tar.gz
| Download URL | ho_rag-1.0.0.tar.gz |
|---|---|
| Size | 4.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f74680df625188a0a8580f3aa870b3ebe74b15d5746f4c1417000f1c5133b27d
|
|
BLAKE2b-256 checksum How to use checksums |
ebc77c7feddfd1294b08c90608607b699b1cd661bda931cc84032a2ede5bdc35
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.17
|
Release files / ho_rag-1.0.0-py3-none-any.whl
| Download URL | ho_rag-1.0.0-py3-none-any.whl |
|---|---|
| Size | 6.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1b8c00226b02d97f8b9e7e402958ebcea63f9e6d58ca4aaee971b77ef3189d29
|
|
BLAKE2b-256 checksum How to use checksums |
4eedfd82e687dccb110e6ea079db6b336fab8d7e34ff6fc1e6d8fdf533f8efab
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.17
|
Security for ho-rag 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
