Support Mistral API

[jackmpcollins]

Ideally this can be done by simply setting api_base in OpenaiChatModel. That avoids any new dependencies, and basically any new code. This is currently blocked on the Mistral API having a different format for tool_choice than the OpenAI API. Issue for this https://github.com/mistralai/client-python/issues/78

If that issue is not resolved, a new MistralChatModel can be added that reuses all the code from OpenaiChatModel but changes the default api_base to the Mistral url and updates the usage of tool_calls to match the Mistral API format.

[jackmpcollins]

As of https://github.com/jackmpcollins/magentic/releases/tag/v0.19.0 , Mistral works via the openai API as long as the return type is a string type or a union of types (including simply making the return type nullable with | None). Single type return types are broken.

Working example

from magentic import prompt, OpenaiChatModel
from magentic.chat_model.litellm_chat_model import LitellmChatModel

@prompt(
    """Use the tool to return a list of fruits.
    Do not say anthing else. Just use the tool directly.
    """,
    model=OpenaiChatModel(
        "mistral-large-latest",
        api_key="<API_KEY>",
        base_url="https://api.mistral.ai/v1/"
    ),
)
async def test() -> list[str] | None: ...

await test()

[jackmpcollins]

Added mistral backend with MistralChatModel in https://github.com/jackmpcollins/magentic/releases/tag/v0.21.0

Example

from magentic import prompt
from magentic.chat_model.mistral_chat_model import MistralChatModel
from pydantic import BaseModel

class Superhero(BaseModel):
    name: str
    age: int
    power: str
    enemies: list[str]

@prompt(
    """Create a Superhero named {name}""",
    model=MistralChatModel("mistral-large-latest"),
)
def create_superhero(name: str) -> Superhero: ...

create_superhero("Garden Man")
# Superhero(name='Garden Man', age=35, power='Plant control', enemies=['Smog', 'Deforestator'])