Gemini 3.1 Flash Lite 正式 GA：高吞吐 Agent 与低延迟场景的最优解

import openai

client = openai.OpenAI(
    api_key="your-apiyi-api-key",
    base_url="https://api.apiyi.com/v1"
)

response = client.chat.completions.create(
    model="gemini-3.1-flash-lite",  # GA 版，不再带 -preview
    messages=[
        {"role": "system", "content": "你是一个高效的结构化数据提取助手。"},
        {"role": "user", "content": "从订单文本中提取 order_id、金额、币种，输出 JSON。"}
    ],
    temperature=0.2,
    response_format={"type": "json_object"}
)

print(response.choices[0].message.content)

tools = [{
    "type": "function",
    "function": {
        "name": "search_internal_kb",
        "description": "在企业知识库检索相关文档",
        "parameters": {
            "type": "object",
            "properties": {
                "query": {"type": "string"},
                "top_k": {"type": "integer", "default": 5}
            },
            "required": ["query"]
        }
    }
}]

resp = client.chat.completions.create(
    model="gemini-3.1-flash-lite",
    messages=[{"role": "user", "content": "帮我找一下退款流程相关的内部文档"}],
    tools=tools,
    tool_choice="auto"
)
print(resp.choices[0].message.tool_calls)