Finwell Analyzer

A package designed to analyze user-submitted texts related to financial well-being by employing language models and pattern matching.

Overview

The package processes the input to identify key sentiments, themes, and insights about young adults' perceptions of affordability and financial status. It returns structured data such as summarized opinions, emotional tone, or categorized reasons behind perceptions, helping organizations understand public sentiment on economic issues without handling raw documents or multimedia.

Installation

pip install finwell_analyzer

Usage

from finwell_analyzer import finwell_analyzer

user_input = "I'm struggling to balance my expenses and savings."
response = finwell_analyzer(user_input)
print(response)  # Output: A dictionary with summarized opinions, emotional tone, and categorized reasons behind perceptions.

Parameters

• 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 default rate limits for LLM7 free tier will be used.

Using Custom LLMs

You can safely pass your own LLM instance (based on LangChain LLMs if you want to use another LLM, via passing it like finwell_analyzer(..., llm=their_llm_instance).

Example with OpenAI

from langchain_openai import ChatOpenAI
from finwell_analyzer import finwell_analyzer

llm = ChatOpenAI()
response = finwell_analyzer("I'm struggling to balance my expenses and savings.", llm=llm)

Example with Anthropic

from langchain_anthropic import ChatAnthropic
from finwell_analyzer import finwell_analyzer

llm = ChatAnthropic()
response = finwell_analyzer("I'm struggling to balance my expenses and savings.", llm=llm)

Example with Google Generative AI

from langchain_google_genai import ChatGoogleGenerativeAI
from finwell_analyzer import finwell_analyzer

llm = ChatGoogleGenerativeAI()
response = finwell_analyzer("I'm struggling to balance my expenses and savings.", llm=llm)

API Key

The default rate limits for LLM7 free tier are sufficient for most use cases of this package. If you need higher rate limits for LLM7, you can pass your own API key via environment variable LLM7_API_KEY or via passing it directly like finwell_analyzer(..., api_key="their_api_key"). You can get a free API key by registering at LLM7 Token.

Issues

Have any questions or issues? Please feel free to open a GitHub issue at GitHub Issues.

Author

Eugene Evstafev [email protected]

Acknowledgments

This package uses the LangChain LLMs module, specifically the ChatLLM7 class from langchain_llm7.