Skip to content

Rubicon - AI agent capable of doing search on scientific papers and making scripts

Notifications You must be signed in to change notification settings

tomaznovak/rubicon-mvp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Rubicon

Description

This is the source code for Rubicon - AI agent. The agent itself is capable of searching for scientific papers on [[https://arxiv.org/]], downloading them and extracting the main points and explanation of the research. The whole agent is developed in agency-swarm framework developed by Arsenii Shatokhin [[https://github.com/VRSEN/agency-swarm]].

Agent is in my daily included in my daily workflow as i use it for writing scripts for my short form podcast ( generated by NotebookLM), which I download daily on my YT chanel. This is the first part of my automation that process.

This version is runnable on the google cloud with database integrated.

Quick Start

After you clone the reposotory create .env files with next environment variables in it:

  • OPENAI_API_KEY, DATABASE_HOSTNAME, DATABASE_PORT, DATABASE_PASSWORD, DATABASE_NAME, DATABASE_USERNAME, SECRET_KEY, ALGORITHM, ACCESS_TOKEN_EXPIRE_MINUTES, REFRESH_TOKEN_EXPIRE_DAYS

Next thing establish virtual environment and run pip install -r requirements.txt in cmd

Next run the code python main.py and the web application of the agent should be running on https://localhost:8080/agent

If you want to deploy on GCP using Docker

Configure your Dockerfile to look something like this

FROM python:3.12

WORKDIR /your-project-directory

ENVPYTHONPATH=/your-project-directory

COPY requirements.txt requirements.txt

RUN pip install -r requirements.txt

COPY . .

CMD ["python", "main.py"]

About

Rubicon - AI agent capable of doing search on scientific papers and making scripts

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published