Reward evaluation

pip install composo

import os
from composo import Composo

client = Composo()

# Evaluate response quality
result = client.evaluate(
    messages=[
        {"role": "user", "content": "I'm frustrated with my device not working."},
        {"role": "assistant", "content": "I'm sorry to hear that. Let's see how I can help you resolve this problem."}
    ],
    criteria="Reward responses that express appropriate empathy if the user is facing a problem they're finding frustrating"
)

print(f"Score: {result.score}")
print(f"Explanation: {result.explanation}")

import asyncio
from composo import AsyncComposo

async def main():
    client = AsyncComposo()
        result = await client.evaluate(
            messages=[
                {"role": "user", "content": "I'm frustrated with my device not working."},
                {"role": "assistant", "content": "I'm sorry to hear that. Let's see how I can help you resolve this problem."}
            ],
            criteria="Reward responses that express appropriate empathy if the user is facing a problem they're finding frustrating"
        )
        
        print(f"Score: {result.score}")
        print(f"Explanation: {result.explanation}")

asyncio.run(main())

import os
from composo import Composo

client = Composo()

messages = [
    {"role": "user", "content": "Explain quantum computing in simple terms"},
    {"role": "assistant", "content": "Quantum computing uses quantum mechanics to process information..."}
]

criteria = [
    "Reward responses that explain complex topics in simple terms",
    "Reward responses that provide accurate technical information",
    "Reward responses that are engaging and easy to understand"
]

results = client.evaluate(messages=messages, criteria=criteria)

for i, result in enumerate(results):
    print(f"Criteria {i+1}: Score = {result.score}")
    print(f"Explanation: {result.explanation}\n")

import os
from composo import Composo

client = Composo()

messages = [
    {"role": "user", "content": "What's the weather like in New York?"},
    {
        "role": "assistant", 
        "content": "Let me check the weather for you.",
        "tool_calls": [
            {
                "id": "call_123",
                "type": "function",
                "function": {
                    "name": "get_weather",
                    "arguments": '{"location": "New York"}'
                }
            }
        ]
    }
]

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather information for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City name"}
                },
                "required": ["location"]
            }
        }
    }
]

result = client.evaluate(
    messages=messages,
    tools=tools,
    criteria="Reward responses that make relevant tool calls to address the user's prompt"
)

print(f"Tool Call Score: {result.score}")

import os
from composo import Composo

client = Composo()

messages = [
    {"role": "user", "content": "What is 2+2?"},
    {"role": "assistant", "content": "2+2 equals 4"}
]

result = client.evaluate(
    messages=messages,
    criteria="Response passes if it provides the correct mathematical answer"
)

print(f"Passed: {abs(result.score - 1.0) < 1e-6}")
print(f"Explanation: {result.explanation}")

import os
import openai
from composo import Composo

client = Composo()

openai_client = openai.OpenAI(api_key="your-openai-key")
openai_result = openai_client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "What is machine learning?"}]
)

result = client.evaluate(
    messages=[{"role": "user", "content": "What is machine learning?"}],
    result=openai_result,
    criteria="Reward accurate technical explanations"
)

print(f"Score: {result.score}")

class EvaluationResponse:
    score: Optional[float]      # Score from 0-1
explanation: str            # Evaluation explanation

result = client.evaluate(messages=messages, criteria=criteria)

print(f"Score: {result.score}")
print(f"Explanation: {result.explanation}")