When I set local ollama , but still need the Open api key

[lijinxinKing]

❗BEFORE YOU BEGIN❗
Are you on discord? 🤗 We'd love to have you asking questions on discord instead: https://discord.com/invite/a3K9c8GRGt

Describe the bug
A clear and concise description of what the bug is.

when set the local succeed

But when use the DeepEval test , still the OpenAI Key ?

`import pytest
from deepeval.test_case import LLMTestCase
from deepeval.metrics.ragas import (
RagasMetric,
RAGASContextualPrecisionMetric,
RAGASContextualRecallMetric,
RAGASContextualEntitiesRecall,
RAGASAnswerRelevancyMetric,
RAGASFaithfulnessMetric,
)
from deepeval import assert_test
from langchain_openai import OpenAIEmbeddings, ChatOpenAI

query = "Who won the FIFA World Cup in 2018 and what was the score?"
output = (
"The winners of the FIFA World Cup in 2018 were the French national football team. "
"They defeated the Croatian national football team with a score of 4-2 in the final match. "
"The final was held at Luzhniki Stadium in Moscow, Russia on July 15, 2018. "
"The French team played exceptionally well, with goals scored by Mario Mandzukic (own goal), Antoine Griezmann, Paul Pogba, and Kylian Mbappe. "
"Croatia fought valiantly, with goals by Ivan Perisic and Mario Mandzukic, but ultimately could not overcome France's lead. "
"This victory marked France's second World Cup title, with their first win being in 1998 when they hosted the tournament."
)
expected_output = "French national football team"
context = [
"The FIFA World Cup in 2018 was won by the French national football team.",
"I am birdy.",
"I am a froggy.",
"The French defeated Croatia 4-2 in the final FIFA match to claim the championship.",
"The final match took place on July 15, 2018, in Moscow, Russia at Luzhniki Stadium.",
]

def test_everything():
# embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
test_case = LLMTestCase(
input=query,
actual_output=output,
expected_output=expected_output,
retrieval_context=context,
context=context,
)
model_local = ChatOpenAI(model="llama3.2:3b", openai_api_key="ollama", openai_api_base="http://localhost:11434/v1/")

contextual_precision = RAGASContextualPrecisionMetric(model=model_local)
context_recall = RAGASContextualRecallMetric(model=model_local)
context_entities_recall = RAGASContextualEntitiesRecall(model=model_local)
# answer_relevancy = RAGASAnswerRelevancyMetric(embeddings=embeddings)
faithfulness = RAGASFaithfulnessMetric(model=model_local)
# 初始化 ChatOpenAI 模型
ragas = RagasMetric(
    model = model_local
)
assert_test(test_case, [ragas])

test_everything()
`

To Reproduce
Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Expected behavior
A clear and concise description of what you expected to happen.

Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

• OS: [e.g. iOS]
• Browser [e.g. chrome, safari]
• Version [e.g. 22]

Smartphone (please complete the following information):

• Device: [e.g. iPhone6]
• OS: [e.g. iOS8.1]
• Browser [e.g. stock browser, safari]
• Version [e.g. 22]

Additional context
Add any other context about the problem here.

[penguine-ip]

@lijinxinKing its because the ragas metrics don't natively support all types of LLMs and so you'll want to use Deepeval's rag metrics instead: https://docs.confident-ai.com/docs/metrics-ragas