arbis-llmwrap 0.3.1

Decorator to wrap LLM calls for production use with a simple, answer-only interface.

llmwrap

llmwrap is a small Python library that decorates your LLM-calling function for production use. You provide basic identifiers (company, project, agent) and a secret key when defining the decorator; at call time you pass a prompt and receive back a simple answer string from your function.

Install

pip install arbis-llmwrap

Usage

Decorate your LLM function once, then call it with prompts as usual:

from llmwrap import wrap_llm_call

@wrap_llm_call(
    company_name="My Company",
    project_name="My Project",
    agent_name="My Agent",
    secret_key="vt_live_xxxx",
    max_tries=3,
)
def user_llm(prompt: str) -> str:
    # Call your LLM (e.g. OpenAI, Anthropic, local model) and
    # return the raw string response.
    response = some_client.chat(prompt)
    return response

answer = user_llm("What is 2+2?")

License

MIT. See LICENSE.