idea-distiller 2025.12.21102518

A new package would process text inputs describing unconventional or controversial business or social initiatives, such as the 2012 program where homeless individuals were employed as mobile Wi-Fi hot

idea‑distiller

idea‑distiller is a tiny utility package that extracts a concise, neutral summary of the core problem addressed by unconventional or controversial business and social initiatives.
It leverages a language model (LLM) to focus on the “problem statement” of the input text while stripping away technical details, implementation specifics, and sensitive content.

---

Installation

pip install idea_distiller

---

Quick start

from idea_distiller import idea_distiller

# Raw description of an initiative
user_input = """
In 2012 a program hired homeless people to become mobile Wi‑Fi hotspots,
providing free internet in public places while giving them a source of
income.
"""

# Get the distilled summary
summary = idea_distiller(user_input)

print(summary)
# → ['Problem: Lack of free public internet access and unemployment among homeless individuals.']

---

Function signature

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

Parameter	Type	Description
user_input	str	The raw text describing the initiative you want to distill.
llm	Optional[BaseChatModel]	A LangChain LLM instance. If omitted, the package creates a ChatLLM7 instance automatically.
api_key	Optional[str]	API key for the default ChatLLM7 service. If not supplied, the environment variable LLM7_API_KEY is used.

The function returns a list of strings that match the validation pattern defined in the package (normally a single concise sentence).

---

Using a custom LLM

You can plug any LangChain‑compatible chat model instead of the default ChatLLM7.

OpenAI

from langchain_openai import ChatOpenAI
from idea_distiller import idea_distiller

llm = ChatOpenAI(model="gpt-4o-mini")
response = idea_distiller(user_input, llm=llm)
print(response)

Anthropic

from langchain_anthropic import ChatAnthropic
from idea_distiller import idea_distiller

llm = ChatAnthropic(model="claude-3-haiku-20240307")
response = idea_distiller(user_input, llm=llm)
print(response)

Google Gemini

from langchain_google_genai import ChatGoogleGenerativeAI
from idea_distiller import idea_distiller

llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash")
response = idea_distiller(user_input, llm=llm)
print(response)

---

API key & rate limits (default LLM7)

• The free tier of LLM7 provides enough quota for most development and low‑volume use cases.
• To obtain a free API key, register at: https://token.llm7.io/.
• You can supply the key directly:

response = idea_distiller(user_input, api_key="YOUR_LLM7_API_KEY")

• Or set the environment variable beforehand:

export LLM7_API_KEY="YOUR_LLM7_API_KEY"

If higher rate limits are required, upgrade your LLM7 plan on the provider’s website.

---

Contributing & Support

• Issues & feature requests: https://github.com/chigwell/idea_distiller/issues
• Pull requests: Welcome! Please follow the contributor guidelines in the repository.

---

Author

Eugene Evstafev
📧 Email: [e-mail]
🐙 GitHub: chigwell

---

License

This project is licensed under the MIT License. See the LICENSE file for details.