A new package that analyzes user-provided text descriptions of their monthly expenses and income to generate a structured affordability assessment.

This package categorizes spending, identifies potential savings areas, and returns a clear breakdown of financial health without requiring sensitive data like bank statements. It helps users understand their budget can be optimized in a private, non-intrusive way.

pip install budgetscribe

from budgetscribe import budgetscribe

user_input = "I spend $500 on rent, $300 on groceries, and $200 on entertainment."
response = budgetscribe(user_input)
print(response)

• user_input: str : the user input text to process
• llm: Optional[BaseChatModel] : the langchain llm instance to use, if not provided the default ChatLLM7 will be used.
• api_key: Optional[str] : the api key for llm7, if not provided the LLM7_API_KEY environment variable will be used.

This package uses ChatLLM7 from langchain_llm7 by default. However, developers can safely pass their own llm instance (based on https://docs.langchain.com) if they want to use another LLM.

For example, to use the openai LLM:

from langchain_openai import ChatOpenAI
from budgetscribe import budgetscribe

llm = ChatOpenAI()
response = budgetscribe(user_input, llm=llm)

or to use the anthropic LLM:

from langchain_anthropic import ChatAnthropic
from budgetscribe import budgetscribe

llm = ChatAnthropic()
response = budgetscribe(user_input, llm=llm)

or to use the google LLM:

from langchain_google_genai import ChatGoogleGenerativeAI
from budgetscribe import budgetscribe

llm = ChatGoogleGenerativeAI()
response = budgetscribe(user_input, llm=llm)

The default rate limits for LLM7 free tier are sufficient for most use cases of this package. However, if higher rate limits are needed, developers can pass their own api_key via environment variable LLM7_API_KEY or directly like budgetscribe(user_input, api_key="their_api_key").

To get a free API key, visit https://token.llm7.io/.

Issues and feature requests: https://github.com/chigwell/budgetscribe

Author: Eugene Evstafev ([email protected])