Skip to main content

​
01 — Basic Invocation

The simplest way to call an LLM. Sends a message and prints the response. 
from definable.models.openai import OpenAIChat
from definable.models.message import Message

model = OpenAIChat(id="gpt-4o-mini")

messages = [
    Message(role="system", content="You are a helpful assistant."),
    Message(role="user", content="What is the capital of France?"),
]

response = model.invoke(
    messages=messages,
    assistant_message=Message(role="assistant", content=""),
)

print(response.content)
print(f"Tokens: {response.response_usage.total_tokens}")

python definable/examples/models/01_basic_invoke.py

​
02 — Async Invocation

Same as above, but using asyncio for non-blocking execution. 
import asyncio
from definable.models.openai import OpenAIChat
from definable.models.message import Message

async def main():
    model = OpenAIChat(id="gpt-4o-mini")
    messages = [Message(role="user", content="Hello!")]
    response = await model.ainvoke(
        messages=messages,
        assistant_message=Message(role="assistant", content=""),
    )
    print(response.content)

asyncio.run(main())

python definable/examples/models/02_async_invoke.py

​
03 — Streaming

Stream tokens as they are generated for real-time output. 
from definable.models.openai import OpenAIChat
from definable.models.message import Message

model = OpenAIChat(id="gpt-4o-mini")
messages = [Message(role="user", content="Tell me a short story.")]

for chunk in model.invoke_stream(
    messages=messages,
    assistant_message=Message(role="assistant", content=""),
):
    if chunk.content:
        print(chunk.content, end="", flush=True)

python definable/examples/models/03_streaming.py

​
04 — Structured Output

Return Pydantic models instead of free text. 
from pydantic import BaseModel
from definable.models.openai import OpenAIChat
from definable.models.message import Message

class Movie(BaseModel):
    title: str
    year: int
    genre: str

model = OpenAIChat(id="gpt-4o-mini")
response = model.invoke(
    messages=[Message(role="user", content="Recommend a sci-fi movie.")],
    assistant_message=Message(role="assistant", content=""),
    response_format=Movie,
)
print(response.parsed)  # Movie(title=..., year=..., genre=...)

python definable/examples/models/04_structured_output.py

​
05 — Multi-Provider

Use the same message format across OpenAI, DeepSeek, Moonshot, and xAI. 
from definable.models.openai import OpenAIChat
from definable.models.deepseek import DeepSeekChat
from definable.models.moonshot import MoonshotChat
from definable.models.xai import xAI

providers = [
    OpenAIChat(id="gpt-4o-mini"),
    DeepSeekChat(id="deepseek-chat"),
    MoonshotChat(id="kimi-k2-turbo-preview"),
    xAI(id="grok-beta"),
]

for model in providers:
    response = model.invoke(messages=[...])
    print(f"{model.provider}: {response.content[:100]}")

python definable/examples/models/05_multi_provider.py
Requires API keys for each provider: OPENAI_API_KEY, DEEPSEEK_API_KEY, MOONSHOT_API_KEY, XAI_API_KEY.

​
06 — Vision & Audio

Send images and audio to multimodal models. 
from definable.models.openai import OpenAIChat
from definable.media import Image

model = OpenAIChat(id="gpt-4o")
response = model.invoke(messages=[{
    "role": "user",
    "content": "Describe this image.",
    "images": [Image(url="https://example.com/photo.jpg")],
}])
print(response.content)

python definable/examples/models/06_vision_and_audio.py