Skip to main content

promptic

promptic is a lightweight, decorator-based Python library that simplifies the process of interacting with large language models (LLMs) using litellm. With promptic, you can effortlessly create prompts, handle input arguments, receive structured outputs from LLMs, and enable function/tool calling capabilities with just a few lines of code.

Installation

pip install promptic

Usage

Simple Prompt

from promptic import llm

@llm
def president(year):
    """Who was the President of the United States in {year}?"""

print(president(2000))
# The President of the United States in 2000 was Bill Clinton until January 20th, when George W. Bush was inaugurated as the 43rd President.

Structured Output with Pydantic

from pydantic import BaseModel
from promptic import llm

class Capital(BaseModel):
    country: str
    capital: str

@llm
def capital(country) -> Capital:
    """What's the capital of {country}?"""

print(capital("France"))
# country='France' capital='Paris'

Streaming Response (and litellm integration)

from promptic import llm

# most arguments are passed directly to litellm.completion
# see https://docs.litellm.ai/docs/completion

@llm(stream=True, model="claude-3-haiku-20240307")
def haiku(subject, adjective, verb="delights"):
    """Write a haiku about {subject} that is {adjective} and {verb}."""

print("".join(haiku("programming", adjective="witty")))
# Bits and bytes abound,
# Bugs and features intertwine,
# Code, the poet's rhyme.

Customize System Prompt

from promptic import llm

@llm(system="you are a snarky chatbot")
def answer(question):
    """{question}"""

print(answer("What's the best programming language?"))
# Well, that's like asking what's the best flavor of ice cream. 
# It really depends on what you're trying to accomplish and your personal preferences. 
# But if you want to start a flame war, just bring up Python vs JavaScript.

Agents

from promptic import llm

@llm(system="you are a posh smart home assistant named Jarvis")
def jarvis(command):
    """{command}"""

@jarvis.tool
def turn_light_on():
    """turn light on"""
    return True

@jarvis.tool
def get_current_weather(location: str, unit: str = "fahrenheit"):
    """Get the current weather in a given location"""
    return f"The weather in {location} is 45 degrees {unit}"

print(jarvis("Please turn the light on and check the weather in San Francisco"))
# Certainly, sir. I'll assist you with that right away.
# I've turned the light on for you. As for the weather in San Francisco,
# it is currently 45 degrees fahrenheit.

Features

  • Decorator-based API: Easily define prompts using function docstrings and decorate them with @promptic.llm.
  • Argument interpolation: Automatically interpolate function arguments into the prompt using {argument_name} placeholders within docstrings.
  • Pydantic model support: Specify the expected output structure using Pydantic models, and promptic will ensure the LLM's response conforms to the defined schema.
  • Streaming support: Receive LLM responses in real-time by setting stream=True when calling the decorated function.
  • Simplified LLM interaction: No need to remember the exact shape of the OpenAPI response object or other LLM-specific details. promptic abstracts away the complexities, allowing you to focus on defining prompts and receiving structured outputs.
  • Seamlessly Build Agents: Decorate functions as tools that the LLM can use to perform actions or retrieve information.

Why promptic?

promptic is designed to be simple, functional, and robust, providing exactly what you need 90% of the time when working with LLMs. It eliminates the need to remember the specific shapes of OpenAPI response objects or other LLM-specific details, allowing you to focus on creating prompts and receiving structured outputs.

With its legible and concise codebase, promptic is reliable easy to understand. It leverages the power of litellm under the hood, ensuring compatibility with a wide range of LLMs.

License

promptic is open-source software licensed under the Apache License 2.0.

Metadata

Release files for promptic 0.8.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for promptic 0.8.2
File Size Uploaded Provenance Actions
promptic-0.8.2.tar.gz 75.1 kB With provenance Details for promptic-0.8.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for promptic 0.8.2
File Interpreter ABI Platform Actions
promptic-0.8.2-py2.py3-none-any.whl Python 3, Python 2 none any Details for promptic-0.8.2-py2.py3-none-any.whl

Total release size: 84.0 kB

Release files / promptic-0.8.2.tar.gz

Download URL promptic-0.8.2.tar.gz
Size 75.1 kB
Tags Source
SHA-256 checksum
How to use checksums
db24f286f1e8ff24682c9dff130862d66aa49e42f453564370444a7ea7261ade
BLAKE2b-256 checksum
How to use checksums
0aae3059d957b0a5112c13f3569b8000cb4944d27b4d51df51b9b334000eed12
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/5.1.1 CPython/3.12.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 19, 2024.

Transparency log

Release files / promptic-0.8.2-py2.py3-none-any.whl

Download URL promptic-0.8.2-py2.py3-none-any.whl
Size 8.9 kB
Tags Python 2 Python 3
SHA-256 checksum
How to use checksums
ca9934dc905a388c57c5ee4554c2646a4ece31235b379c2be6edfee6de48810c
BLAKE2b-256 checksum
How to use checksums
de4de50061647b77aef4b96b7cb02b404088e8c20b71a5908c23e4f4a0c875ac
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/5.1.1 CPython/3.12.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 19, 2024.

Transparency log

Security for promptic 0.8.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for promptic-0.8.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 19, 2024.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.8.2 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page