This project aims to serve as a server that processes pipelines using Prefect, stores temporal memory to use for AI Agents and serves as a REST API to retrieve the results of the pipelines.
- Init a virtual environment
python -m venv venv
- Activate the virtual environment
.\venv\Scripts\activate
-
Install the dependencies with
pip install -r requirements.txt
-
Run the project with
prefect server start
-
Start a work pool
prefect work-pool start my-work-pool
- Create a new folder in the src/pipelines folder with the name of the pipeline.
- Create a new python file named run.py in the folder and add the code for the pipeline. It must contain at least a function decorated with @flow.
- In the root/prefect.yaml file, add a new deployment for the pipeline.
- Run the command
prefect deploy
to deploy the pipeline.