OpenAI API 是一套标准化的 RESTful API 接口，用于与大型语言模型进行交互，已成为人工智能领域的事实标准。本文将全面解析 OpenAI API 的核心规范、请求响应格式、流式传输机制及认证方式。

自定义LLM（OpenAI规范）Server

import json
import time
from loguru import logger
from flask import Flask, request, jsonify, Response

app = Flask(__name__)

API_KEY = "YOURAPIKEY"

@app.route('/v1/chat/completions', methods=['POST'])
def chat_completion():
    # 检查API密钥
    auth_header = request.headers.get('Authorization')
    if not auth_header or auth_header.split()[1] != API_KEY:
        return jsonify({"error": "Unauthorized"}), 401

    data = request.json
    logger.info(f"data is {data}")
    task_id = request.args.get('task_id')
    room_id = request.args.get('room_id')
    for header, value in request.headers.items():
        logger.info(f"{header}: {value}")

    # 打印查询参数
    logger.info("\nQuery Parameters:")
    for key, value in request.args.items():
        logger.info(f"{key}: {value}")

    logger.info(f"task_id: {task_id}, room_id: {room_id}")
    stream = data.get('stream', False)

    if stream:
        return Response(generate_stream_response(data), content_type='text/event-stream')
    else:
        return jsonify(generate_response(data))

def generate_response(data):
    response = "这是一个模拟的AI助手响应。实际应用中，这里应该调用真实的AI模型。"

    return {
        "id": "chatcmpl-123",
        "object": "chat.completion",
        "created": int(time.time()),
        "model": data['model'],
        "choices": [{
            "index": 0,
            "message": {
                "role": "assistant",
                "content": response
            },
            "finish_reason": "stop"
        }],
        "usage": {
            "prompt_tokens": sum(len(m['content']) for m in data['messages']),
            "completion_tokens": len(response),
            "total_tokens": sum(len(m['content']) for m in data['messages']) + len(response)
        }
    }

def generate_stream_response(data):
    response = "这是一个模拟的AI助手流式响应。实际应用中，这里应该调用真实的AI模型。"
    words = list(response)
    for i, word in enumerate(words):
        chunk = {
            "id": "chatcmpl-123",
            "object": "chat.completion.chunk",
            "created": int(time.time()),
            "model": data['model'],
            "choices": [{
                "index": 0,
                "delta": {
                    "content": word, 
                    "tool_calls": [  
                        {
                            "id": "call_abc123",  
                            "type": "function",
                            "function": {
                                "name": "hangup", 
                                "arguments": "\{\}"  
                            }
                        }
                    ]
                },
                "finish_reason": None if i < len(words) - 1 else "stop"
            }]
        }
        logger.info(chunk)
        yield f"data: {json.dumps(chunk)}\n\n"
        time.sleep(0.1)  # 模拟处理时间

    yield "data: [DONE]\n\n"

if __name__ == '__main__':
    logger.info(f"Server is running with API_KEY: {API_KEY}")
    app.run(port=8083, debug=True)

测试

curl -X POST "http://localhost:8083/v1/chat/completions?task_id=123&room_id=456" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOURAPIKEY" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
      {"role": "user", "content": "请流式回答这个问题"}
    ],
    "stream": true
  }'