🔖 write prompts as python functions
Project description
funcchain
> pip install funcchain
Introduction
funcchain
is the most pythonic way of writing cognitive systems. Leveraging pydantic models as output schemas combined with langchain in the backend allows for a seamless integration of llms into your apps.
It works perfect with OpenAI Functions and soon with other models using JSONFormer.
Demo
from pydantic import BaseModel, Field
from funcchain import chain
class Item(BaseModel):
name: str = Field(description="Name of the item")
description: str = Field(description="Description of the item")
keywords: list[str] = Field(description="Keywords for the item")
class ShoppingList(BaseModel):
""" List of items to buy """
items: list[Item]
store: str = Field(description="The store to buy the items from")
class TodoList(BaseModel):
todos: list[Item]
urgency: int = Field(description="The urgency of all tasks (1-10)")
def extract_list(user_input: str) -> TodoList | ShoppingList:
"""
The user input is either a shopping List or a todo list.
"""
return chain()
lst = extract_list(
input("Enter your list: ")
)
if isinstance(lst, ShoppingList):
print("Here is your Shopping List: ")
for item in lst.items:
print(f"{item.name}: {item.description}")
print(f"You need to go to: {lst.store}")
if isinstance(lst, TodoList):
print("Here is your Todo List: ")
for item in lst.todos:
print(f"{item.name}: {item.description}")
print(f"Urgency: {lst.urgency}")
Features
- increased productivity
- prompts as Python functions
- pydantic models as output schemas
- langchain schemas in the backend
- fstrings or jinja templates for prompts
- fully utilises OpenAI Functions
- minimalistic and easy to use
- langsmith support
- async support
Documentation
Coming soon and feel free to contribute
Contribution
You want to contribute? That's great! Please run the dev setup to get started:
> git clone https://github.com/shroominic/funcchain.git && cd funcchain
> ./dev_setup.sh
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
funcchain-0.1.9.tar.gz
(362.5 kB
view hashes)
Built Distribution
funcchain-0.1.9-py3-none-any.whl
(26.6 kB
view hashes)
Close
Hashes for funcchain-0.1.9-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | dd38afffefa9e5b6c8115f2a5478646cdbd644c491877ded49e972e3f1a3ee2c |
|
MD5 | 041b2e12d6344f1d9293b7df5e05726a |
|
BLAKE2b-256 | 78923a1143cacf7d734e66ddcc75afe61e021cea359886d6630c8e5cec4a0e3f |