marvin/README.md at main · PrefectHQ/marvin

[ShellLM]

• marvin/README.md at main · PrefectHQ/marvin

Marvin

The AI Engineering Toolkit

Marvin is a lightweight AI toolkit for building natural language interfaces that are reliable, scalable, and easy to trust.

Each of Marvin's tools is simple and self-documenting, using AI to solve common but complex challenges like entity extraction, classification, and generating synthetic data. Each tool is independent and incrementally adoptable, so you can use them on their own or in combination with any other library. Marvin is also multi-modal, supporting both image and audio generation as well as using images as inputs for extraction and classification.

Marvin is for developers who care more about using AI than building AI, and we are focused on creating an exceptional developer experience. Marvin users should feel empowered to bring tightly-scoped "AI magic" into any traditional software project with just a few extra lines of code.

Marvin aims to merge the best practices for building dependable, observable software with the best practices for building with generative AI into a single, easy-to-use library. It's a serious tool, but we hope you have fun with it.

Marvin is open-source, free to use, and made with 💙 by the team at Prefect.

Installation

Install the latest version with pip:

pip install marvin -U

To verify your installation, run marvin version in your terminal.

Tools

Marvin consists of a variety of useful tools, all designed to be used independently. Each one represents a common LLM use case, and packages that power into a simple, self-documenting interface.

General

🦾 Write custom AI-powered functions without source code

Text

🏷️ Classify text into categories
🔍 Extract structured entities from text
🪄 Transform text into structured data
✨ Generate synthetic data from a schema

Images

🖼️ Create images from text or functions
📝 Describe images with natural language
🏷️ Classify images into categories
🔍 Extract structured entities from images
🪄 Transform images into structured data

Audio

💬 Generate speech from text or functions
✍️ Transcribe speech from recorded audio
🎙️ Record users continuously or as individual phrases

Video

🎙️ Record video continuously

Interaction

🤖 Chat with assistants and use custom tools
🧭 Build applications that manage persistent state

Quickstart

Here's a whirlwind tour of a few of Marvin's main features. For more information, check the docs!

🏷️ Classify text

Marvin can classify text using a set of labels:

import marvin

marvin.classify(
    "Marvin is so easy to use!",
    labels=["positive", "negative"],
)

#  "positive"

🔍 Extract structured entities

Marvin can extract structured entities from text:

import pydantic

class Location(pydantic.BaseModel):
    city: str
    state: str

marvin.extract("I moved from NY to CHI", target=Location)

# [
#     Location(city="New York", state="New York"),
#     Location(city="Chicago", state="Illinois")
# ]

Almost all Marvin functions can be given instructions for more control:

marvin.extract(
    "I paid $10 for 3 tacos and got a dollar and 25 cents back.",
    target=float,
    instructions="Only extract money"
)

#  [10.0, 1.25]

✨ Generate data

Marvin can generate synthetic data for you:

class Location(pydantic.BaseModel):
    city: str
    state: str

marvin.generate(
    n=4,
    target=Location,
    instructions="cities in the United States named after presidents"
)

# [
#     Location(city='Washington', state='District of Columbia'),
#     Location(city='Jackson', state='Mississippi'),
#     Location(city='Cleveland', state='Ohio'),
#     Location(city='Lincoln', state='Nebraska'),
# ]

🪄 Standardize text by casting to types

marvin.cast("one two three", list[int])
# [1, 2, 3]

@marvin.model
class Location(pydantic.BaseModel):
    city: str
    state: str

Location("The Big Apple")
# Location(city="New York", state="New York")

🦾 Build AI-powered functions

@marvin.fn
def sentiment(text: str) -> float:
    """
    Returns a sentiment score for `text`
    between -1 (negative) and 1 (positive).
    """

sentiment("I love working with Marvin!") # 0.8
sentiment("These examples could use some work...") # -0.2

🖼️ Generate images from text

marvin.paint("a simple cup of coffee, still warm")

🔍 Converting images to data

marvin.classify(
    marvin.Image.from_path("docs/images/coffee.png"),
    labels=["drink", "food"],
)
# "drink"

Record, modify, and play audio

import marvin
import marvin.audio

# record the user
user_audio = marvin.audio.record_phrase()

# transcribe the text
user_text = marvin.transcribe(user_audio)

# cast the language to a more formal style
ai_text = marvin.cast(user_text, instructions='Make the language ridiculously formal')

# generate AI speech
ai_audio = marvin.speak(ai_text)

# play the result
ai_audio.play()

Get in touch!

💡 Feature idea? Share it in the #development channel in our Discord.

🐛 Found a bug? Feel free to open an issue.

👷 Feedback? Marvin is under active development, and we'd love to hear it.

Suggested labels

None