suihuanglab / improving-agent

An Autonomous Reasoning Agent in the NCATS Biomedical Translator Network that uses EHR and multi-omic cohorts to rank results from user queries
MIT License
2 stars 4 forks source link
ncats-translator

imProving Agent

imProving Agent is Autonomous Reasoning Agent built on top of Scalable Precision Medicine Oriented Knowledge Engine (SPOKE) and is part of the NCATS Biomedical Data Translator Network. It aims to improve user queries by utilizing EHR and multi-omic cohorts to extract the best knowledge for a given concept. Use these links to find out more about imProving Agents's Data, its algorithms, or some of its multi-omic cohort data.

Using imProving Agent as a client

Find a Jupyter notebook with some basic examples of appropriate Translator Reasoner API queries here.

Deploying

SPOKE database

imProving Agent relies on a bolt connection to a Neo4j instance of SPOKE

PSEVs

For ranking, imProving Agent relies on PSEVs. PSEVs are accessed via the psev-service

Environment variables

Depending on the environment in which imProving Agent is to be run, a number of environment variables must be set.

ITRB deployment

The following variables must be set for deployment in the ITRB test, staging, and production environments:

Local and dev deployment

Networking

The imProving Agent HTTP service will be exposed on port 3031 and uwsgi stats will be exposed on port 3032. When running locally via docker-compose, these ports are bound to host ports 3033 and 3034, respectively.

Running imProving Agent

Given the depedencies described above, start the service with docker-compose up web