import os

from llama_index.llms.openai_like import OpenAILike

base_url = os.environ["LLAMA_CPP_BASE_URL"]
model = os.environ["LLAMA_CPP_MODEL"]

llm = OpenAILike(
    model=model,
    api_base=base_url,
    api_key=os.getenv("LLAMA_CPP_API_KEY", "not-needed"),
    is_chat_model=False,
    is_function_calling_model=False,
    context_window=4096,
    max_tokens=64,
    temperature=0,
    timeout=120,
)

response = llm.complete(
    "Write one short sentence confirming LlamaIndex reached llama.cpp."
)

print(f"endpoint={base_url}")
print(f"model={model}")
print(f"response={str(response).strip()}")