Python example
Call the OpenSearch large model answering service from Python using the OpenAI SDK and a custom base URL.
Prerequisites
Before you begin, ensure that you have:
The OpenAI Python SDK installed:
pip install openaiAn API key created on the OpenSearch platform
Send a request
All requests use client.chat.completions.create with the ops-qwen-turbo model and the OpenSearch-compatible base URL.
The messages array defines the conversation. Each message has a role:
system— sets the assistant's behavior for the sessionuser— a message from the end userassistant— a previous reply injected to provide conversation history for multi-turn chat
from openai import OpenAI
def get_response():
client = OpenAI(
api_key="OS_API_KEY", # Replace OS_API_KEY with your API Key created on the platform
base_url="http://xxxx-hangzhou.opensearch.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
model="ops-qwen-turbo",
messages=[
{"role": "system", "content": "You are a robot assistant"},
{"role": "user", "content": "What is the capital of Henan"},
{"role": "assistant", "content": "Zhengzhou"},
{"role": "user", "content": "What are some interesting places there"}
]
)
print(completion.model_dump_json())
if __name__ == '__main__':
get_response()Replace xxxx-hangzhou in the base URL with your actual OpenSearch instance endpoint.
Response structure
A successful response returns a Chat Completions object. The model's answer is in choices[0].message.content.
{
"id": "48657EBF-2B81-4E3E-96B4-27FE7D6E780A",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "Zhengzhou offers a variety of tourist attractions and cultural activities, including the Yellow Emperor's Ancestral Worship Ceremony, Zhengzhou Museum, Zhengzhou Science and Technology Museum, and Zhengzhou Zoo. Visitors can also enjoy scenic leisure spots like Bishagang Park and Zijingshan Park. With its rich cultural heritage and modern amenities, Zhengzhou is well-suited for both tourism and entertainment.",
"role": "assistant",
"function_call": null,
"tool_calls": null
}
}
],
"created": 1719567872,
"model": "ops-qwen-turbo",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": null,
"usage": {
"completion_tokens": 77,
"prompt_tokens": 38,
"total_tokens": 115
}
}