Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

A new package that helps users and organizations analyze and categorize email account usage patterns. The package takes user-submitted text input describing their email management habits and returns a

Notifications You must be signed in to change notification settings

chigwell/inboxpattern

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

1 Commit

Repository files navigation

inboxpattern

PyPI version License: MIT Downloads LinkedIn

inboxpattern is a lightweight Python package that helps users and organizations analyze and categorize email account usage patterns.
Give it a brief text describing your email habits – it will return a structured reply that outlines:

  • How many email accounts you use
  • The purpose of each account
  • Any challenges you face managing them

The output is a list of strings that can be fed straight into a workflow, shared in dashboards, or used for tooling that reduces inbox clutter.

Author: Eugene Evstafev (hi@euegne.plus)
GitHub owner: chigwell

Quick Start

pip install inboxpattern

Basic usage

from inboxpattern import inboxpattern
user_input = (
 "I maintain three email addresses: a personal Gmail, a work Outlook account, "
 "and a project-specific ProtonMail. I often forget which account to use for "
 "which purpose, and I sometimes receive spam in my personal address."
)
response = inboxpattern(user_input)
print(response)
# Example output: [
# "Accounts: 3",
# "Personal: Gmail",
# "Work: Outlook",
# "Project: ProtonMail",
# "Challenges: Misattributed emails, spam in personal inbox"
# ]

Using a different LLM

inboxpattern ships with ChatLLM7 from the langchain_llm7 package by default.
If you already have a LangChain LLM provider (OpenAI, Anthropic, Google, etc.), you can pass it in:

OpenAI

from langchain_openai import ChatOpenAI
from inboxpattern import inboxpattern
llm = ChatOpenAI() # your own OpenAI key already configured
response = inboxpattern(user_input, llm=llm)

Anthropic

from langchain_anthropic import ChatAnthropic
from inboxpattern import inboxpattern
llm = ChatAnthropic()
response = inboxpattern(user_input, llm=llm)

Google Gemini

from langchain_google_genai import ChatGoogleGenerativeAI
from inboxpattern import inboxpattern
llm = ChatGoogleGenerativeAI()
response = inboxpattern(user_input, llm=llm)

Optional API key

The free tier of LLM7 comes with generous limits that are usually enough for most use‐cases.
If you need higher throughput, obtain a key at https://token.llm7.io/ and provide it:

export LLM7_API_KEY="your_llm7_token" # or
inboxpattern(user_input, api_key="your_llm7_token")

Parameters

Parameter Type Description
user_input str Text describing your email‐management habits.
llm Optional[BaseChatModel] A LangChain LLM instance to use; defaults to ChatLLM7.
api_key Optional[str] LLM7 API key; if omitted, the library will look for the LLM7_API_KEY environment variable or default to "None".

Development & Issues

If you encounter bugs or want to request a feature, please open an issue in the repository:

https://github.com/chigwell/inboxpattern/issues

Happy coding, and may your inboxes stay tidy!

Releases

No releases published

Packages

No packages published

Languages

AltStyle によって変換されたページ (->オリジナル) /