pip install llama-index-core llama-index-llms-openai-like

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="your-model",
    api_base="http://localhost:18181/v1",  # Nexa SDK endpoint
    api_key="fake",
    context_window=8000,
    is_chat_model=True,
)

# Text completion
response = llm.complete("What is AI?")
print(response)

# Chat
from llama_index.core.base.llms.types import ChatMessage

messages = [
    ChatMessage(role="system", content="You are helpful."),
    ChatMessage(role="user", content="What is AI?"),
]
chat_response = llm.chat(messages)
print(chat_response)

# Stream completion
response_stream = llm.stream_complete("Tell me a story")
for chunk in response_stream:
    print(chunk.delta, end="")