OpenAI

Use GPT and o-series models from OpenAI's first-party API. OpenAIModel supports native tool calling when passed directly to Agent.

For standalone invoke / stream usage, see LLM Models — OpenAI.

Install

pip install --extra-index-url https://core-packages.elsai.ai/root/elsai-model/ elsai-model==2.0.0

Setup

1. Create an OpenAI API key.
2. Export credentials:

export OPENAI_API_KEY=sk-...
export OPENAI_MODEL_NAME=gpt-4o-mini

3. Install elsai-agents if you have not already:

pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.3.0

Agent — basic

import os
from elsai import Agent
from elsai_model.openai import OpenAIModel

model = OpenAIModel(
    model_id=os.getenv("OPENAI_MODEL_NAME", "gpt-4o-mini"),
    client_args={"api_key": os.environ["OPENAI_API_KEY"]},
    params={"temperature": 0.2, "max_tokens": 256},
)
agent = Agent(
    model=model,
    system_prompt="You are a concise assistant.",
)
result = agent("What is 17 + 28? Reply with just the number.")
print(result.message["content"][0]["text"])

Available models

Model	ID
GPT-4o	gpt-4o
GPT-4o mini	gpt-4o-mini
o1	o1
o3-mini	o3-mini