fintextract is a lightweight Python package that extracts and structures key financial and business insights from unstructured news text.
Give it a raw news sentence and receive a clear, machine‑readable summary containing:

• Subject – the main person or organization
• Key figures – monetary amounts, percentages, etc.
• Significant event – the core business event described

Designed for financial analysts, business reporters, and investors who need to quickly parse breaking news.

• One‑function API (fintextract) that returns a list of extracted data items.
• Built‑in default LLM: ChatLLM7 (via the langchain_llm7 integration).
• Seamless integration with any LangChain‑compatible LLM (OpenAI, Anthropic, Google, …).
• Simple regex‑based output validation ensures the response matches the expected pattern.

pip install fintextract

from fintextract import fintextract

news = "Elon Musk becomes first person worth $700B following pay package ruling."

result = fintextract(user_input=news)

print(result)
# Example output:
# ['Subject: Elon Musk', 'Key figure: $700B', 'Event: pay package ruling']

def fintextract(
    user_input: str,
    api_key: Optional[str] = None,
    llm: Optional[BaseChatModel] = None,
) -> List[str]:

The function returns a list of strings that match the pre‑defined output pattern (subject, key figure, event).

If you prefer another language model, simply pass a LangChain LLM instance:

from langchain_openai import ChatOpenAI
from fintextract import fintextract

llm = ChatOpenAI()
response = fintextract(user_input="Your news text", llm=llm)

from langchain_anthropic import ChatAnthropic
from fintextract import fintextract

llm = ChatAnthropic()
response = fintextract(user_input="Your news text", llm=llm)

from langchain_google_genai import ChatGoogleGenerativeAI
from fintextract import fintextract

llm = ChatGoogleGenerativeAI()
response = fintextract(user_input="Your news text", llm=llm)

Any LangChain‑compatible BaseChatModel can be used in the same way.

• ChatLLM7 (the default) uses the free tier rate limits, which are sufficient for typical usage.
• To obtain a free API key, register at https://token.llm7.io/.
• Set the key via the environment variable LLM7_API_KEY or pass it directly:

response = fintextract(user_input="Your news text", api_key="YOUR_API_KEY")

If higher limits are needed, upgrade your LLM7 plan accordingly.

Contributions, bug reports, and feature requests are welcome!
Please open an issue or submit a pull request on GitHub:

Issues: https://github.com/chigwell/fintextract/issues

Pull Requests: https://github.com/chigwell/fintextract/pulls

This project is licensed under the MIT License.

Eugene Evstafev – hi@euegne.plus
GitHub: chigwell

• ChatLLM7 integration from the langchain_llm7 package – https://pypi.org/project/langchain-llm7/
• Pattern matching powered by llmatch_messages.llmatch.

Happy extracting!