Overview
This guide will help you get started with Julep in just 5 minutes. You’ll learn how to create your first AI agent and execute a simple task.
What we’ll build
We’ll build a simple agent that uses tasks to write a short story.
name: Story Generator
model: claude-3.5-sonnet
about: A helpful AI assistant that specializes in writing and editing.
name: Write a short story
description: Write a short story about a magical garden
main:
- prompt:
- role: system
content: You are a creative story writer.
- role: user
content: $ f'Write a short story about {steps[0].input.topic}'
Prerequisites
Step 1: Install Julep
Choose your preferred language:
Step 2: Initialize the Client
from julep import Julep
client = Julep(api_key="your_julep_api_key")
Step 3: Create Your First Agent
Let’s create a simple AI agent that can help with writing tasks:
agent = client.agents.create(
name="Writing Assistant",
model="claude-3.5-sonnet",
about="A helpful AI assistant that specializes in writing and editing."
)
Step 4: Create a Simple Task
Let’s create a task that generates a short story based on a given topic:
import yaml
task_definition = yaml.safe_load("""
name: Story Generator
description: Generate a short story based on a given topic
main:
- prompt:
- role: system
content: You are a creative story writer.
- role: user
content: $ f'Write a short story about {steps[0].input.topic}'
""")
task = client.tasks.create(
agent_id=agent.id,
**task_definition # Unpack the task definition
)
Step 5: Execute the Task
Now let’s run the task with a specific topic:
execution = client.executions.create(
task_id=task.id,
input={"topic": "a magical garden"}
)
# Wait for the execution to complete
while (result := client.executions.get(execution.id)).status not in ['succeeded', 'failed']:
print(result.status)
time.sleep(1)
if result.status == "succeeded":
print(result.output)
else:
print(f"Error: {result.error}")
Next Steps
Congratulations! You’ve created your first Julep agent and executed a task. Here’s what you can explore next:
