Agent Inference

Gradient allows you to create multi-agent workflows to power your AI applications. This allows developers to integrate agents into your AI applications.

Endpoint Access Keys

You can create an agent endpoint access key in the settings of your agent in the console.

Examples

Sync Client

For example, you can access agent inference using the SDK:

Python

import os
from do_gradientai import GradientAI

agent_client = GradientAI(
    agent_key=os.environ.get("GRADIENTAI_AGENT_KEY"),
    agent_endpoint="https://my-agent.agents.do-ai.run",
)

agent_response = agent_client.agents.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "What is the capital of Portugal?",
        }
    ],
    model="ignored",
)

print(agent_response.choices[0].message.content)

Async Client

The async client uses the exact same interface.

Python

import os
from do_gradientai import AsyncGradientAI

agent_client = AsyncGradientAI(
    agent_key=os.environ.get("GRADIENTAI_AGENT_KEY"),
    agent_endpoint="https://my-agent.agents.do-ai.run",
)

agent_response = await agent_client.agents.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "What is the capital of Portugal?",
        }
    ],
    model="ignored",
)

print(agent_response.choices[0].message.content)