ragmetrics-client 0.1.12

Monitor your LLM calls. Test your LLM app.

RagMetrics

Monitor your LLM calls. Test your LLM app.

RagMetrics offers:

• The best LLM judge on the market (>95% human agreement)
• A/B testing for your entire LLM pipeline
• Evaluations for retrievals, not just generation

With this package, you can log your LLM calls to RagMetrics and use them as labeled data

Quickstart

pip install ragmetrics-client

import ragmetrics
from openai import OpenAI

## login to ragmetrics account via portal key
ragmetrics.login(key="your_ragmetrics_key")
openai_client = OpenAI()

## Monitor OpenAI, LangChain or LiteLLM clients
ragmetrics.monitor(openai_client)

## Then use as usual. All calls will be logged
resp = openai_client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": f"What is the capital of Spain?"}]
)

Get your key and read docs at RagMetrics.ai