Prompt engineering and Anthropic
In this example, you'll build a pipeline with Dagster that:
- Takes an input question
- Generates prompts to use with Anthropic
- Validates outputs of AI models and passes outputs across assets
Prerequisites
To follow the steps in this guide, you'll need:
- Basic Python knowledge
- Python 3.9+ installed on your system. For more information, see the Installation guide.
Step 1: Set up your Dagster environment
First, set up a new Dagster project.
-
Clone the the Dagster repo and navigate to the project:
cd examples/docs_projects/project_prompt_eng
-
Install the required dependencies with
uv
:uv sync
-
Activate the virtual environment:
- MacOS
- Windows
source .venv/bin/activate
.venv\Scripts\activate
Step 2: Launch the Dagster webserver
To make sure Dagster and its dependencies were installed correctly, navigate to the project root directory and start the Dagster webserver:
dg dev
Next steps
- Continue this example with prompts