newsstructure

A Python package that takes a news headline or short text snippet as input and returns a structured summary of the key event, actors, and context. It uses an LLM to generate the content and pattern matching to ensure the output follows a consistent format. Ideal for news aggregation, automated reporting, and content tagging.

Installation

pip install newsstructure

Usage

Basic Example

from newsstructure import newsstructure

user_input = "Apple announces new iPhone with advanced AI features"
result = newsstructure(user_input)
print(result)

Using a Custom LLM

You can pass your own LangChain-compatible LLM instance. For example, to use OpenAI:

from langchain_openai import ChatOpenAI
from newsstructure import newsstructure

llm = ChatOpenAI()
user_input = "Tesla stock surges after earnings report"
response = newsstructure(user_input, llm=llm)

To use Anthropic:

from langchain_anthropic import ChatAnthropic
from newsstructure import newsstructure

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

To use Google Generative AI:

from langchain_google_genai import ChatGoogleGenerativeAI
from newsstructure import newsstructure

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

Using a Custom API Key

By default, the package uses the free tier of LLM7 (via langchain_llm7). You can provide your own API key either via environment variable or directly:

import os
os.environ["LLM7_API_KEY"] = "your_api_key_here"

# or

response = newsstructure(user_input, api_key="your_api_key_here")

Get a free API key by registering at https://token.llm7.io/.

Parameters

• user_input (str): The text input (e.g., news headline or snippet) to process.
• llm (Optional[BaseChatModel]): A LangChain LLM instance. If not provided, defaults to ChatLLM7.
• api_key (Optional[str]): API key for LLM7. If not provided, the package will try to read from the LLM7_API_KEY environment variable.

License

This project is licensed under the MIT License.

Issues

Report issues or feature requests on GitHub.

Author

Eugene Evstafev
Email: hi@euegne.plus
GitHub: chigwell