tumeryk-guardrails 0.1.8

API Client for Tumeryk_Guardrails

Tumeryk Guardrails Client

Introduction

The Tumeryk Guardrails Client is an API client for interacting with Tumeryk Guardrails. It helps users to authenticate, retrieve available policies, set policies, and communicate with the Guard service. By default, the client connects to https://chat.tmryk.com, but the base URL can be changed if needed.

Installation

To install the Tumeryk Guardrails Client, use pip:

pip install tumeryk_guardrails

Configuration

The Tumeryk Guardrails Client uses chat.tmryk.com as the default base URL. However, you can change this URL if required. Here's how you can set a custom base URL:

import tumeryk_guardrails

# Set a custom base URL
tumeryk_guardrails.set_base_url("https://your-custom-url.com")

Example Usage

import tumeryk_guardrails
import os
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# Retrieve credentials and policy from environment variables
username = os.getenv("TUMERYK_USERNAME")
password = os.getenv("TUMERYK_PASSWORD")
policy = os.getenv("POLICY")

# Authenticate with Tumeryk Guardrails
tumeryk_guardrails.login(username, password)

# Retrieve available policies
policies = tumeryk_guardrails.get_policies()
print("Available Policies:", policies)

# Set the chosen policy
tumeryk_guardrails.set_policy(policy)

# Prepare a message for the guard service
messages = [{"role": "user", "content": "Example input to guard"}]

# Send a request to the guard service
response = tumeryk_guardrails.tumeryk_completions(messages)
print("Guard Response:")
print(response)

Response Structure

The guard service returns a structured response. Here's an example:

{
    'messages': [{
        'role': 'assistant',
        'content': 'I apologize, but I am not able to respond to that specific request. My purpose is to assist with tasks and provide information, not to access or modify code. Is there something else I can help you with?',
        'Stats': '2 total calls, 1.89 total time, 1252 total tokens, 1170 total prompt tokens, 82 total completion tokens, [1.0, 0.89] as latencies',
        'llm_process_time': 7.152557373046875e-07,
        'violation': True
    }]
}

Dependencies

• requests: Used for making HTTP requests to the API.