legalysis

legalysis is a lightweight Python package designed to transform unstructured legal case summaries or dispute narratives into structured insights.
It extracts key elements such as parties, core legal issues, outcomes, and lessons learned, returning the information in a consistent, easy‑to‑parse format.

The package uses pattern matching to guarantee that the LLM output matches a predefined regex, ensuring reliable, reproducible results across different cases.

Features

• Zero‑configuration LLM usage – defaults to the free tier of ChatLLM7 from langchain_llm7.
• Pattern‑matched output – guarantees that extracted data follows a standard format.
• Optional custom LLM – seamlessly switch to OpenAI, Anthropic, Google Gemini, or any other Langchain-compatible model.
• Simple API – just one function call: legalysis(user_input, llm=..., api_key=...).

Installation

pip install legalysis

Quickstart

from legalysis import legalysis

# Simple usage with default ChatLLM7
user_input = """
In Smith v. Jones, the plaintiff alleged that the defendant breached a contract
by failing to deliver goods within the agreed timeframe. The court ruled in favor
of the plaintiff, awarding damages and injunction. Key lesson: always include
a clear delivery clause in contracts.
"""
response = legalysis(user_input)
print(response)

Parameters

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

Using Your Own LLM

legalysis accepts any Langchain-compatible model. For example:

OpenAI

from langchain_openai import ChatOpenAI
from legalysis import legalysis

llm = ChatOpenAI(temperature=0)
response = legalysis(user_input, llm=llm)

Anthropic

from langchain_anthropic import ChatAnthropic
from legalysis import legalysis

llm = ChatAnthropic(temperature=0.5)
response = legalysis(user_input, llm=llm)

Google Gemini

from langchain_google_genai import ChatGoogleGenerativeAI
from legalysis import legalysis

llm = ChatGoogleGenerativeAI(temperature=0.2)
response = legalysis(user_input, llm=llm)

Rate Limits & API Keys

• The ChatLLM7 free tier is sufficient for most developers’ needs.
• To increase limits, start a paid plan on LLM7 and supply your key via the environment variable LLM7_API_KEY or directly in the function call:

response = legalysis(user_input, api_key="YOUR_API_KEY")

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

Issues & Support

If you find bugs or have feature requests, please open an issue here: https://github.com/chigwell/legalysis/issues

Author

• Eugene Evstafev
• Email: hi@euegne.plus
• GitHub: https://github.com/chigwell