texttoknowledge

texttoknowledge is a lightweight Python package that transforms unstructured text from documents into structured, query‑able knowledge. By leveraging the llmatch-messages library and a language model (LLM), the package extracts key information and organizes it into predefined formats, making critical details easy to retrieve and keep up‑to‑date.

Features

• Simple API – Call a single function with your raw text.
• Customizable LLM – Use the default ChatLLM7 or provide any LangChain‑compatible LLM (OpenAI, Anthropic, Google, etc.).
• Regex‑driven output – Guarantees that the extracted data conforms to a pattern you define.
• No boilerplate – Handles LLM initialization, API key resolution, and error handling for you.

Installation

pip install texttoknowledge

Quick Start

from texttoknowledge import texttoknowledge

# Your raw document text
raw_text = """
Project Alpha:
- Owner: Alice
- Deadline: 2025-03-15
- Status: In progress
"""

# Extract structured knowledge
structured_data = texttoknowledge(user_input=raw_text)

print(structured_data)

API Reference

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

Returns: List[str] – Extracted pieces of knowledge that match the predefined regex pattern.

Using a Custom LLM

You can pass any LangChain‑compatible LLM that adheres to BaseChatModel. Below are a few examples:

OpenAI

from langchain_openai import ChatOpenAI
from texttoknowledge import texttoknowledge

llm = ChatOpenAI()  # Configure as needed
response = texttoknowledge(user_input="Your document text here", llm=llm)

Anthropic

from langchain_anthropic import ChatAnthropic
from texttoknowledge import texttoknowledge

llm = ChatAnthropic()
response = texttoknowledge(user_input="Your document text here", llm=llm)

Google Generative AI

from langchain_google_genai import ChatGoogleGenerativeAI
from texttoknowledge import texttoknowledge

llm = ChatGoogleGenerativeAI()
response = texttoknowledge(user_input="Your document text here", llm=llm)

Default LLM – ChatLLM7

If you do not provide an LLM, texttoknowledge automatically uses ChatLLM7 from the langchain_llm7 package:

from langchain_llm7 import ChatLLM7

The free tier of LLM7 offers generous rate limits suitable for most use cases. To increase limits, simply supply your own API key:

response = texttoknowledge(user_input="...", api_key="YOUR_LLM7_API_KEY")

You can obtain a free API key by registering at https://token.llm7.io/.

Environment Variables

• LLM7_API_KEY – If set, the package will use this key for the default ChatLLM7 instance.

Contributing & Issues

If you encounter bugs or have feature requests, please open an issue:

GitHub Issues: https://github....

License

This project is licensed under the MIT License.

Author

• Eugene Evstafev – chigwell
  Email: hi@euegne.plus

Happy structuring! 🎉