v0.11.0

What's Changed

• Add support for Azure via OpenaiChatModel by @jackmpcollins in #65

Full Changelog: v0.10.0...v0.11.0

v0.10.0

What's Changed

• Update openai to v1 by @jackmpcollins in #59

Full Changelog: v0.9.1...v0.10.0

v0.9.1

Bound openai version <1.0

Full Changelog: v0.9.0...v0.9.1

v0.9.0

What's Changed

• Add LiteLLM backend by @jackmpcollins in #54

Full Changelog: v0.8.0...v0.9.0

---

Example of LiteLLM backend

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


@prompt(
    "Talk to me! ",
    model=LitellmChatModel("ollama/llama2"),
)
def say_hello() -> str:
    ...


say_hello()

See the Backend/LLM Configuration section of the README for how to set the LiteLLM backend as the default.

v0.8.0

What's Changed

• Make backend configurable by @jackmpcollins in #46
• Bump urllib3 from 2.0.6 to 2.0.7 by @dependabot in #47
• Replace black with ruff formatter by @jackmpcollins in #48
• Handle pydantic generic BaseModel in name_type and function schema by @jackmpcollins in #52
• Allow ChatModel to be set with context manager by @jackmpcollins in #53

Full Changelog: v0.7.2...v0.8.0

---

Allow the chat_model/LLM to be set using a context manager. This allows the same prompt-function to easily be reused with different models, and also makes it neater to dynamically set the model.

from magentic import OpenaiChatModel, prompt


@prompt("Say hello")
def say_hello() -> str:
    ...


@prompt(
    "Say hello",
    model=OpenaiChatModel("gpt-4", temperature=1),
)
def say_hello_gpt4() -> str:
    ...


say_hello()  # Uses env vars or default settings

with OpenaiChatModel("gpt-3.5-turbo"):
    say_hello()  # Uses gpt-3.5-turbo due to context manager
    say_hello_gpt4()  # Uses gpt-4 with temperature=1 because explicitly configured

v0.7.2

What's Changed

• Allow setting max_tokens param by @jackmpcollins in #45

Full Changelog: v0.7.1...v0.7.2

---

Allow setting max_tokens param in OpenaiChatModel. The default value for this can also be set using an environment variable MAGENTIC_OPENAI_MAX_TOKENS.

Example

from magentic import prompt
from magentic.chat_model.openai_chat_model import OpenaiChatModel

@prompt("Hello, how are you?", model=OpenaiChatModel(max_tokens=3))
def test() -> str:
    ...

test()
# 'Hello! I'

v0.7.1

What's Changed

• Bump urllib3 from 2.0.4 to 2.0.6 by @dependabot in #36
• add optional max_calls argument to prompt_chain by @pachacamac in #39
• Add instructions for setting OPENAI_API_BASE by @jackmpcollins in #40

New Contributors

• @pachacamac made their first contribution in #39

Full Changelog: v0.7.0...v0.7.1

v0.7.0

What's Changed

• Add Asyncio section to README by @jackmpcollins in #28
• Add chatprompt decorator by @jackmpcollins in #34
• Make openai tests less flaky by @jackmpcollins in #35

Full Changelog: v0.6.0...v0.7.0

---

Chat Prompting

The @chatprompt decorator works just like @prompt but allows you to pass chat messages as a template rather than a single text prompt. This can be used to provide a system message or for few-shot prompting where you provide example responses to guide the model's output. Format fields denoted by curly braces {example} will be filled in all messages - use the escape_braces function to prevent a string being used as a template.

from magentic import chatprompt, AssistantMessage, SystemMessage, UserMessage
from magentic.chatprompt import escape_braces

from pydantic import BaseModel


class Quote(BaseModel):
    quote: str
    character: str


@chatprompt(
    SystemMessage("You are a movie buff."),
    UserMessage("What is your favorite quote from Harry Potter?"),
    AssistantMessage(
        Quote(
            quote="It does not do to dwell on dreams and forget to live.",
            character="Albus Dumbledore",
        )
    ),
    UserMessage("What is your favorite quote from {movie}?"),
)
def get_movie_quote(movie: str) -> Quote:
    ...


get_movie_quote("Iron Man")
# Quote(quote='I am Iron Man.', character='Tony Stark')

v0.6.0

What's Changed

• Move function schemas into own file by @jackmpcollins in #18
• Bump certifi from 2023.5.7 to 2023.7.22 by @dependabot in #21
• Bump jupyter-server from 2.7.0 to 2.7.2 by @dependabot in #20
• Bump tornado from 6.3.2 to 6.3.3 by @dependabot in #19
• Add example notebook for Chain of Verification by @jackmpcollins in #22
• Handle Iterable type with no item type by @jackmpcollins in #24
• Handle BaseModel parameters in functions by @jackmpcollins in #23
• Make AsyncIterableFunctionSchema.serialize_args raise NotImplementedError by @jackmpcollins in #25
• Rename chat_model files by @jackmpcollins in #26

New Contributors

• @dependabot made their first contribution in #21

Full Changelog: v0.5.0...v0.6.0

v0.5.0

What's Changed

• Add docstrings where useful by @jackmpcollins in #14
• Enable async prompt_chain. Remove FunctionCallMessage by @jackmpcollins in #17

Full Changelog: v0.4.1...v0.5.0

---

from magentic import prompt_chain


async def get_current_weather(location, unit="fahrenheit"):
    """Get the current weather in a given location"""
    return {
        "location": location,
        "temperature": "72",
        "unit": unit,
        "forecast": ["sunny", "windy"],
    }


@prompt_chain(
    template="What's the weather like in {city}?",
    functions=[get_current_weather],
)
async def describe_weather(city: str) -> str:
    ...


output = await describe_weather("Boston")