RAG using OLLAMA model evaluation with RAGAS

[OlfaCh]

[ ] I checked the documentation and related resources and couldn't find an answer to my question.

I am using RAGAS to evaluate my RAG pipeline with a local Ollama model (qwen2.5:32b). I instantiate it via LangChain using OllamaLLM. However, when I call evaluate(...), I get an OpenAIError saying that the OPENAI_API_KEY must be set.

But I'm not using OpenAI, so this seems like an unnecessary requirement.

How can I prevent RAGAS from defaulting to OpenAI’s API when I’m explicitly using a local ollama model? code : `from ragas import evaluate from ragas.metrics import ( faithfulness, answer_relevancy, context_recall, context_precision, ) llm_codegeneration = Ollama(model="qwen2.5:32b", num_ctx=8192)

all_results = {}

for file_name, dataset in dataset_per_file.items(): print(f"--- Evaluation of : {file_name} ---")

result = evaluate(
    dataset=dataset,
    metrics=[
        context_precision,
        context_recall,
        faithfulness,
        answer_relevancy,
    ],llm=llm_codegeneration
)

df = result.to_pandas()
all_results[file_name] = df

` error: OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

Thanks for any clarification or fix you can provide . Olfa,