magentic

library0.41.1pypypi✓ verified 26d ago

Decorator-based library for seamlessly integrating LLMs as Python functions. Uses @prompt, @chatprompt, and @prompt_chain decorators to turn Python function signatures into LLM calls with typed structured output. Built on pydantic for output validation. Current version: 0.41.1 (Mar 2026). Still pre-1.0 — API may change. Default backend: OpenAI.

llm-agents ai-ml serialization

pip install magentic

package ↗homepage ↗

INSTALL

IMPORT

SIG · MAGENTIC

magentic

llm-agentspythonv0.41.1

Install

11.1s avg

Import

3487ms

Disk

70MB

Pass rate

8/ 10

Env Coverage8 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.41.1 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✓ —

✓ 12.6s

py 3.11

✓ —

✓ 11.23s

py 3.12

✓ —

✓ 10.23s

py 3.13

✓ —

✓ 10.37s

py 3.9

✕ build_error

70MB installed

● package 70MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

prompt

✓ from magentic import prompt

✗ from magentic import prompt

chatprompt

✓ from magentic import chatprompt

prompt_chain

✓ from magentic import prompt_chain

Minimal magentic structured output using @prompt decorator.

# pip install magentic from magentic import prompt from pydantic import BaseModel class Superhero(BaseModel): name: str power: str enemies: list[str] @prompt('Create a superhero named {name}.') def create_superhero(name: str) -> Superhero: ... # never executed hero = create_superhero('Garden Man') print(hero.name) # 'Garden Man' print(hero.power) # 'Control over plants' print(hero.enemies) # ['Pollution Man', ...]

Debug

Known issues

gotchaThe function body of @prompt decorated functions is NEVER executed. Must use ... (ellipsis) as the body. Any actual code in the body is dead code that will never run.

fix

Always use '...' as the function body for @prompt, @chatprompt, @prompt_chain decorated functions.

affects: all

gotchaWhen functions= is passed to @prompt, the LLM may return a FunctionCall object instead of the final result. Must call fn_call() to execute it. Use @prompt_chain to auto-resolve.

fix

result = describe_weather('Boston')() — note the extra () to execute the FunctionCall. Or use @prompt_chain for automatic resolution.

affects: all

gotchaDefault model is gpt-4o-mini (OpenAI). Requires OPENAI_API_KEY. Fails silently if not set — raises AuthenticationError at call time, not at decoration time.

fix

Set OPENAI_API_KEY env var. Or pass model= explicitly: @prompt('...', model=OpenaiChatModel('gpt-4o'))

affects: all

gotchaStill pre-1.0 (0.41.x). API stability not guaranteed. Minor versions may introduce breaking changes.

fix

Pin version in production: pip install magentic==0.41.1

affects: all

gotchaAnthropic and LiteLLM backends require separate extras. 'pip install magentic' alone only includes OpenAI backend.

fix

pip install 'magentic[anthropic]' or 'magentic[litellm]'

affects: all

breakingmagentic requires Python >= 3.10. Installation will fail on older Python versions.

fix

Upgrade Python to 3.10 or newer.

affects: all

Upgrade

Version history

0.41.1latest on PyPI · released Mar 11, 2026

Audit

Dependencies

openairequiredDefault backend. Installed automatically with core package.

pydanticrequiredRequired for structured output validation.

Agent activity

16 hits · last 30 days

node

OpenAI (training)

Resources

packagehttps://pypi.org/project/magentic/ ↗

homepagehttps://magentic.dev ↗