112 lines
3.7 KiB
Python
112 lines
3.7 KiB
Python
import os
|
|
|
|
import pytest
|
|
from datasets import Dataset
|
|
from evaluations.evaluators import LLMJudge
|
|
|
|
from haiku.rag.client import HaikuRAG
|
|
from haiku.rag.config import Config
|
|
from haiku.rag.config.models import ModelConfig
|
|
from haiku.rag.qa.agent import QuestionAnswerAgent
|
|
|
|
OPENAI_AVAILABLE = bool(os.getenv("OPENAI_API_KEY"))
|
|
ANTHROPIC_AVAILABLE = bool(os.getenv("ANTHROPIC_API_KEY"))
|
|
VLLM_QA_AVAILABLE = bool(Config.providers.vllm.qa_base_url)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_qa_ollama(qa_corpus: Dataset, temp_db_path):
|
|
"""Test Ollama QA with LLM judge."""
|
|
client = HaikuRAG(temp_db_path)
|
|
qa = QuestionAnswerAgent(
|
|
client, ModelConfig(provider="ollama", name="gpt-oss", enable_thinking=False)
|
|
)
|
|
llm_judge = LLMJudge()
|
|
|
|
doc = qa_corpus[1]
|
|
await client.create_document(
|
|
content=doc["document_extracted"], uri=doc["document_id"]
|
|
)
|
|
|
|
question = doc["question"]
|
|
expected_answer = doc["answer"]
|
|
|
|
answer = await qa.answer(question)
|
|
is_equivalent = await llm_judge.judge_answers(question, answer, expected_answer)
|
|
|
|
assert is_equivalent, (
|
|
f"Generated answer not equivalent to expected answer.\nQuestion: {question}\nGenerated: {answer}\nExpected: {expected_answer}"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.skipif(not OPENAI_AVAILABLE, reason="OpenAI not available")
|
|
async def test_qa_openai(qa_corpus: Dataset, temp_db_path):
|
|
"""Test OpenAI QA with LLM judge."""
|
|
client = HaikuRAG(temp_db_path)
|
|
qa = QuestionAnswerAgent(client, ModelConfig(provider="openai", name="gpt-4o-mini"))
|
|
llm_judge = LLMJudge()
|
|
|
|
doc = qa_corpus[1]
|
|
await client.create_document(
|
|
content=doc["document_extracted"], uri=doc["document_id"]
|
|
)
|
|
|
|
question = doc["question"]
|
|
expected_answer = doc["answer"]
|
|
|
|
answer = await qa.answer(question)
|
|
is_equivalent = await llm_judge.judge_answers(question, answer, expected_answer)
|
|
|
|
assert is_equivalent, (
|
|
f"Generated answer not equivalent to expected answer.\nQuestion: {question}\nGenerated: {answer}\nExpected: {expected_answer}"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.skipif(not ANTHROPIC_AVAILABLE, reason="Anthropic not available")
|
|
async def test_qa_anthropic(qa_corpus: Dataset, temp_db_path):
|
|
"""Test Anthropic QA with LLM judge."""
|
|
client = HaikuRAG(temp_db_path)
|
|
qa = QuestionAnswerAgent(
|
|
client, ModelConfig(provider="anthropic", name="claude-3-5-haiku-20241022")
|
|
)
|
|
llm_judge = LLMJudge()
|
|
|
|
doc = qa_corpus[1]
|
|
await client.create_document(
|
|
content=doc["document_extracted"], uri=doc["document_id"]
|
|
)
|
|
|
|
question = doc["question"]
|
|
expected_answer = doc["answer"]
|
|
|
|
answer = await qa.answer(question)
|
|
is_equivalent = await llm_judge.judge_answers(question, answer, expected_answer)
|
|
|
|
assert is_equivalent, (
|
|
f"Generated answer not equivalent to expected answer.\nQuestion: {question}\nGenerated: {answer}\nExpected: {expected_answer}"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.skipif(not VLLM_QA_AVAILABLE, reason="vLLM QA server not configured")
|
|
async def test_qa_vllm(qa_corpus: Dataset, temp_db_path):
|
|
"""Test vLLM QA with LLM judge."""
|
|
client = HaikuRAG(temp_db_path)
|
|
qa = QuestionAnswerAgent(client, ModelConfig(provider="vllm", name="Qwen/Qwen3-4B"))
|
|
llm_judge = LLMJudge()
|
|
|
|
doc = qa_corpus[1]
|
|
await client.create_document(
|
|
content=doc["document_extracted"], uri=doc["document_id"]
|
|
)
|
|
|
|
question = doc["question"]
|
|
expected_answer = doc["answer"]
|
|
answer = await qa.answer(question)
|
|
is_equivalent = await llm_judge.judge_answers(question, answer, expected_answer)
|
|
|
|
assert is_equivalent, (
|
|
f"Generated answer not equivalent to expected answer.\nQuestion: {question}\nGenerated: {answer}\nExpected: {expected_answer}"
|
|
)
|