A simple implémentation of Agentic Wordflow and Agent datascience.
An Agentic demo of a basic data science use case. The goal is to test differences between Agent and Workflow in reliability and complexity.
- Features
- Demo
- Quick start
- Soon
- Prerequisites
- Installation
- Technology
- Project structure
- Test
- Warning
- License
Technology
Example Agent execution
Note
- First go to installation to setup Ollama.
- You can change CSV file in "data" folder.
uv venv --python 3.12
source .venv/bin/activate
pip install -r requirements.txtpython main_agent.py- Workflow datascience
- Full containerized
- Linux (AMD & Nvidia) or Windows with WSL2 (Nvidia)
- Docker installed
- Docker Compose installed
Instructions for installing the project, use compose.amd.yml:
docker compose -f compose.amd.yml up -dInstructions for installing the project, use compose.nvidia.yml:
docker compose -f compose.nvidia.yml up -ddocker psYou should see 1 service :
- ollama_service
Check models available in your Ollama container
docker exec -it ollama_service ollama listDownload a model to your Ollama container
docker exec -it ollama_service ollama pull qwen3-coder:30b| Technology | Description | License | Documentation |
|---|---|---|---|
| Python | A high-level programming language. | MIT | Docs |
| Docker | A platform for containerization. | Apache 2.0 | Docs |
| Ollama | A tool for running large language models locally. | MIT | Docs |
| Agno | A unified stack for multi-agent systems. | Apache 2.0 | Docs |
This project has been tested on the following hardware configuration:
- OS: Linux Solus
- CPU: AMD Ryzen 5 9600X
- GPU: AMD Radeon Pro 9700 AI & AMD RX 9070
- Storage: 2.5" SATA SSD
Note
CSV data file must be correctly structured.
This project is open source and the code is usable and modifiable. However, the author disclaims all responsibility and no technical support is provided.

