yangjianchuan
commited on
Commit
·
96601d6
0
Parent(s):
first commit
Browse files- Dockerfile +21 -0
- README.md +104 -0
- index.html +96 -0
- qwen.py +299 -0
- requirements.txt +3 -0
- static/favicon.png +0 -0
Dockerfile
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM python:3.9-slim
|
2 |
+
|
3 |
+
# 设置工作目录
|
4 |
+
WORKDIR /app
|
5 |
+
|
6 |
+
# 复制依赖文件
|
7 |
+
COPY requirements.txt .
|
8 |
+
|
9 |
+
# 安装依赖
|
10 |
+
RUN pip install -r requirements.txt
|
11 |
+
|
12 |
+
# 复制应用代码
|
13 |
+
COPY index.html .
|
14 |
+
COPY qwen.py .
|
15 |
+
COPY static ./static
|
16 |
+
|
17 |
+
# 暴露端口
|
18 |
+
EXPOSE 8000
|
19 |
+
|
20 |
+
# 启动命令
|
21 |
+
CMD ["python", "qwen.py"]
|
README.md
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Q
|
3 |
+
emoji: 🏢
|
4 |
+
colorFrom: indigo
|
5 |
+
colorTo: purple
|
6 |
+
sdk: docker
|
7 |
+
pinned: false
|
8 |
+
license: mit
|
9 |
+
app_port: 8000
|
10 |
+
---
|
11 |
+
|
12 |
+
# 通义千问 API 代理服务器
|
13 |
+
|
14 |
+
这是一个基于 FastAPI 实现的通义千问 API 代理服务器,用于转发和处理与通义千问 API 的通信。
|
15 |
+
|
16 |
+
## 主要功能
|
17 |
+
|
18 |
+
- 模型列表获取 API
|
19 |
+
- 聊天完成 API
|
20 |
+
- 支持流式响应
|
21 |
+
- 内置模型列表缓存机制
|
22 |
+
- 自动重试机制
|
23 |
+
|
24 |
+
## 环境要求
|
25 |
+
|
26 |
+
- Python 3.7+
|
27 |
+
- FastAPI 0.104.1+
|
28 |
+
- Uvicorn 0.24.0+
|
29 |
+
- HTTPX 0.25.1+
|
30 |
+
|
31 |
+
## 安装步骤
|
32 |
+
|
33 |
+
1. 克隆项目到本地
|
34 |
+
|
35 |
+
2. 安装依赖:
|
36 |
+
```bash
|
37 |
+
pip install -r requirements.txt
|
38 |
+
```
|
39 |
+
|
40 |
+
3. 使用 Docker(可选):
|
41 |
+
```bash
|
42 |
+
docker build -t qwen-api-proxy .
|
43 |
+
docker run -p 8000:8000 qwen-api-proxy
|
44 |
+
```
|
45 |
+
|
46 |
+
## 运行服务
|
47 |
+
|
48 |
+
```bash
|
49 |
+
python qwen.py
|
50 |
+
```
|
51 |
+
或使用 uvicorn:
|
52 |
+
```bash
|
53 |
+
uvicorn qwen:app --host 0.0.0.0 --port 8000
|
54 |
+
```
|
55 |
+
|
56 |
+
服务将在 http://localhost:8000 上运行。
|
57 |
+
|
58 |
+
## API 接口说明
|
59 |
+
|
60 |
+
### 1. 获取模型列表
|
61 |
+
|
62 |
+
```
|
63 |
+
GET /api/models
|
64 |
+
Header: Authorization: Bearer <your-token>
|
65 |
+
```
|
66 |
+
|
67 |
+
返回可用的模型列表,结果会被缓存1小时。
|
68 |
+
|
69 |
+
### 2. 聊天完成
|
70 |
+
|
71 |
+
```
|
72 |
+
POST /api/chat/completions
|
73 |
+
Header: Authorization: Bearer <your-token>
|
74 |
+
|
75 |
+
{
|
76 |
+
"model": "string",
|
77 |
+
"messages": [
|
78 |
+
{
|
79 |
+
"role": "user",
|
80 |
+
"content": "string"
|
81 |
+
}
|
82 |
+
],
|
83 |
+
"stream": boolean,
|
84 |
+
"max_tokens": number (可选)
|
85 |
+
}
|
86 |
+
```
|
87 |
+
|
88 |
+
支持流式和非流式响应,可以通过 stream 参数控制。
|
89 |
+
|
90 |
+
## 错误处理
|
91 |
+
|
92 |
+
- 服务内置了自动重试机制,最多重试3次
|
93 |
+
- 500错误或HTML响应会触发重试
|
94 |
+
- 401错误表示未授权,需要检查token
|
95 |
+
- 400错误表示请求参数有误
|
96 |
+
|
97 |
+
## 获取 API Key
|
98 |
+
|
99 |
+
1. 访问 https://chat.qwenlm.ai/ 并登录
|
100 |
+
2. 打开浏览器开发者工具(通常按 F12)
|
101 |
+
3. 切换到"应用程序"选项卡
|
102 |
+
4. 在左侧菜单中选择"Cookies" -> "https://chat.qwenlm.ai"
|
103 |
+
5. 找到名称为"token"的cookie
|
104 |
+
6. 复制其值,这就是你的API Key
|
index.html
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<!DOCTYPE html>
|
2 |
+
<html>
|
3 |
+
<head>
|
4 |
+
<title>API 接口说明</title>
|
5 |
+
<link rel="icon" type="image/png" href="/static/favicon.png">
|
6 |
+
<style>
|
7 |
+
body { font-family: Arial, sans-serif; margin: 20px; }
|
8 |
+
h1 { color: #333; }
|
9 |
+
.endpoint { margin: 20px 0; padding: 15px; background: #f5f5f5; border-radius: 5px; }
|
10 |
+
.method { font-weight: bold; color: #007bff; }
|
11 |
+
.url { color: #28a745; }
|
12 |
+
.description { margin-top: 10px; }
|
13 |
+
</style>
|
14 |
+
</head>
|
15 |
+
<body>
|
16 |
+
<h1>API 接口说明</h1>
|
17 |
+
|
18 |
+
<h2>项目概述</h2>
|
19 |
+
<p>这是一个基于 FastAPI 实现的通义千问 API 代理服务器,用于转发和处理与通义千问 API 的通信。</p>
|
20 |
+
|
21 |
+
<h2>主要功能</h2>
|
22 |
+
<ul>
|
23 |
+
<li>模型列表获取 API</li>
|
24 |
+
<li>聊天完成 API</li>
|
25 |
+
<li>支持流式响应</li>
|
26 |
+
<li>内置模型列表缓存机制</li>
|
27 |
+
<li>自动重试机制</li>
|
28 |
+
</ul>
|
29 |
+
|
30 |
+
<h2>环境要求</h2>
|
31 |
+
<ul>
|
32 |
+
<li>Python 3.7+</li>
|
33 |
+
<li>FastAPI 0.104.1+</li>
|
34 |
+
<li>Uvicorn 0.24.0+</li>
|
35 |
+
<li>HTTPX 0.25.1+</li>
|
36 |
+
</ul>
|
37 |
+
|
38 |
+
<h2>安装步骤</h2>
|
39 |
+
<ol>
|
40 |
+
<li>克隆项目到本地</li>
|
41 |
+
<li>安装依赖:
|
42 |
+
<pre><code>pip install -r requirements.txt</code></pre>
|
43 |
+
</li>
|
44 |
+
<li>使用 Docker(可选):
|
45 |
+
<pre><code>docker build -t qwen-api-proxy .
|
46 |
+
docker run -p 8000:8000 qwen-api-proxy</code></pre>
|
47 |
+
</li>
|
48 |
+
</ol>
|
49 |
+
|
50 |
+
<h2>运行服务</h2>
|
51 |
+
<pre><code>python qwen.py</code></pre>
|
52 |
+
<p>或使用 uvicorn:</p>
|
53 |
+
<pre><code>uvicorn qwen:app --host 0.0.0.0 --port 8000</code></pre>
|
54 |
+
<p>服务将在 <a href="http://localhost:8000">http://localhost:8000</a> 上运行。</p>
|
55 |
+
|
56 |
+
<h2>错误处理</h2>
|
57 |
+
<ul>
|
58 |
+
<li>服务内置了自动重试机制,最多重试3次</li>
|
59 |
+
<li>500错误或HTML响应会触发重试</li>
|
60 |
+
<li>401错误表示未授权,需要检查token</li>
|
61 |
+
<li>400错误表示请求参数有误</li>
|
62 |
+
</ul>
|
63 |
+
|
64 |
+
<h2>获取 API Key</h2>
|
65 |
+
<ol>
|
66 |
+
<li>访问 <a href="https://chat.qwenlm.ai/">https://chat.qwenlm.ai/</a> 并登录</li>
|
67 |
+
<li>打开浏览器开发者工具(通常按 F12)</li>
|
68 |
+
<li>切换到"应用程序"选项卡</li>
|
69 |
+
<li>在左侧菜单中选择"Cookies" -> "https://chat.qwenlm.ai"</li>
|
70 |
+
<li>找到名称为"token"的cookie</li>
|
71 |
+
<li>复制其值,这就是你的API Key</li>
|
72 |
+
</ol>
|
73 |
+
|
74 |
+
<h2>许可证</h2>
|
75 |
+
<p>本项目采用 MIT License 开源许可证。</p>
|
76 |
+
|
77 |
+
<div class="endpoint">
|
78 |
+
<div class="method">GET</div>
|
79 |
+
<div class="url">/api/models</div>
|
80 |
+
<div class="description">
|
81 |
+
获取可用模型列表<br>
|
82 |
+
请求头需要包含 Authorization: Bearer {api_key}
|
83 |
+
</div>
|
84 |
+
</div>
|
85 |
+
|
86 |
+
<div class="endpoint">
|
87 |
+
<div class="method">POST</div>
|
88 |
+
<div class="url">/api/chat/completions</div>
|
89 |
+
<div class="description">
|
90 |
+
与模型进行对话<br>
|
91 |
+
请求头需要包含 Authorization: Bearer {api_key}<br>
|
92 |
+
支持流式响应(stream: true)
|
93 |
+
</div>
|
94 |
+
</div>
|
95 |
+
</body>
|
96 |
+
</html>
|
qwen.py
ADDED
@@ -0,0 +1,299 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from fastapi import FastAPI, Request, Response, UploadFile, File
|
2 |
+
from fastapi.responses import StreamingResponse, FileResponse
|
3 |
+
from fastapi.staticfiles import StaticFiles
|
4 |
+
import httpx
|
5 |
+
import json
|
6 |
+
import asyncio
|
7 |
+
import time
|
8 |
+
import base64
|
9 |
+
from typing import Optional, Dict, Any, List
|
10 |
+
from io import BytesIO
|
11 |
+
|
12 |
+
# 配置常量
|
13 |
+
QWEN_API_URL = "https://chat.qwenlm.ai/api/chat/completions"
|
14 |
+
QWEN_MODELS_URL = "https://chat.qwenlm.ai/api/models"
|
15 |
+
QWEN_FILES_URL = "https://chat.qwenlm.ai/api/v1/files/"
|
16 |
+
MAX_RETRIES = 3
|
17 |
+
RETRY_DELAY = 1 # 1秒
|
18 |
+
|
19 |
+
# 缓存设置
|
20 |
+
cached_models = None
|
21 |
+
cached_models_timestamp = 0
|
22 |
+
CACHE_TTL = 60 * 60 # 缓存1小时
|
23 |
+
|
24 |
+
app = FastAPI()
|
25 |
+
app.mount("/static", StaticFiles(directory="static"), name="static")
|
26 |
+
client = httpx.AsyncClient()
|
27 |
+
|
28 |
+
@app.get("/")
|
29 |
+
async def root():
|
30 |
+
return FileResponse("index.html")
|
31 |
+
|
32 |
+
async def sleep(seconds: float):
|
33 |
+
await asyncio.sleep(seconds)
|
34 |
+
|
35 |
+
# 添加 base64 转换为文件的函数
|
36 |
+
async def base64_to_file(base64_str: str) -> BytesIO:
|
37 |
+
try:
|
38 |
+
# 去除 data:image/jpeg;base64, 这样的前缀
|
39 |
+
if ',' in base64_str:
|
40 |
+
base64_str = base64_str.split(',', 1)[1]
|
41 |
+
|
42 |
+
# 解码 base64 数据
|
43 |
+
image_data = base64.b64decode(base64_str)
|
44 |
+
return BytesIO(image_data)
|
45 |
+
except Exception as e:
|
46 |
+
raise Exception(f"Failed to convert base64 to file: {str(e)}")
|
47 |
+
|
48 |
+
# 添加图片上传函数
|
49 |
+
async def upload_image_to_qwen(auth_header: str, image_data: BytesIO) -> str:
|
50 |
+
try:
|
51 |
+
files = {'file': ('image.jpg', image_data, 'image/jpeg')}
|
52 |
+
headers = {
|
53 |
+
"Authorization": auth_header,
|
54 |
+
"accept": "application/json"
|
55 |
+
}
|
56 |
+
|
57 |
+
async with httpx.AsyncClient() as client:
|
58 |
+
response = await client.post(
|
59 |
+
QWEN_FILES_URL,
|
60 |
+
headers=headers,
|
61 |
+
files=files
|
62 |
+
)
|
63 |
+
|
64 |
+
if response.is_success:
|
65 |
+
data = response.json()
|
66 |
+
if not data.get('id'):
|
67 |
+
raise Exception("File upload failed: No valid file ID returned")
|
68 |
+
return data['id']
|
69 |
+
else:
|
70 |
+
raise Exception(f"File upload failed with status {response.status_code}")
|
71 |
+
|
72 |
+
except Exception as e:
|
73 |
+
raise Exception(f"Failed to upload image: {str(e)}")
|
74 |
+
|
75 |
+
# 添加消息处理函数
|
76 |
+
async def process_messages(messages: List[Dict], auth_header: str) -> List[Dict]:
|
77 |
+
processed_messages = []
|
78 |
+
|
79 |
+
for message in messages:
|
80 |
+
if isinstance(message.get('content'), list):
|
81 |
+
new_content = []
|
82 |
+
for content in message['content']:
|
83 |
+
if (content.get('type') == 'image_url' and
|
84 |
+
content.get('image_url', {}).get('url', '').startswith('data:')):
|
85 |
+
# 处理 base64 图片
|
86 |
+
image_data = await base64_to_file(content['image_url']['url'])
|
87 |
+
image_id = await upload_image_to_qwen(auth_header, image_data)
|
88 |
+
new_content.append({
|
89 |
+
'type': 'image',
|
90 |
+
'image': image_id
|
91 |
+
})
|
92 |
+
else:
|
93 |
+
new_content.append(content)
|
94 |
+
message['content'] = new_content
|
95 |
+
processed_messages.append(message)
|
96 |
+
|
97 |
+
return processed_messages
|
98 |
+
|
99 |
+
async def fetch_with_retry(url: str, options: Dict, retries: int = MAX_RETRIES):
|
100 |
+
last_error = None
|
101 |
+
|
102 |
+
for i in range(retries):
|
103 |
+
try:
|
104 |
+
response = await client.request(
|
105 |
+
method=options.get("method", "GET"),
|
106 |
+
url=url,
|
107 |
+
headers=options.get("headers", {}),
|
108 |
+
json=options.get("json"),
|
109 |
+
)
|
110 |
+
|
111 |
+
if response.is_success:
|
112 |
+
return response
|
113 |
+
|
114 |
+
content_type = response.headers.get("content-type", "")
|
115 |
+
if response.status_code >= 500 or "text/html" in content_type:
|
116 |
+
last_error = {
|
117 |
+
"status": response.status_code,
|
118 |
+
"content_type": content_type,
|
119 |
+
"response_text": response.text[:1000],
|
120 |
+
"headers": dict(response.headers)
|
121 |
+
}
|
122 |
+
|
123 |
+
if i < retries - 1:
|
124 |
+
await sleep(RETRY_DELAY * (i + 1))
|
125 |
+
continue
|
126 |
+
else:
|
127 |
+
last_error = {
|
128 |
+
"status": response.status_code,
|
129 |
+
"headers": dict(response.headers)
|
130 |
+
}
|
131 |
+
break
|
132 |
+
|
133 |
+
except Exception as error:
|
134 |
+
last_error = error
|
135 |
+
if i < retries - 1:
|
136 |
+
await sleep(RETRY_DELAY * (i + 1))
|
137 |
+
continue
|
138 |
+
|
139 |
+
raise Exception(json.dumps({
|
140 |
+
"error": True,
|
141 |
+
"message": "All retry attempts failed",
|
142 |
+
"last_error": str(last_error),
|
143 |
+
"retries": retries
|
144 |
+
}))
|
145 |
+
|
146 |
+
async def process_line(line: str, previous_content: str) -> tuple[str, Optional[dict]]:
|
147 |
+
try:
|
148 |
+
data = json.loads(line[6:]) # 移除 "data: " 前缀
|
149 |
+
if (data.get("choices") and data["choices"][0].get("delta")):
|
150 |
+
delta = data["choices"][0]["delta"]
|
151 |
+
current_content = delta.get("content", "")
|
152 |
+
|
153 |
+
# 计算增量内容
|
154 |
+
if previous_content and current_content:
|
155 |
+
if current_content.startswith(previous_content):
|
156 |
+
new_content = current_content[len(previous_content):]
|
157 |
+
else:
|
158 |
+
new_content = current_content
|
159 |
+
else:
|
160 |
+
new_content = current_content
|
161 |
+
|
162 |
+
# 构造新的响应数据
|
163 |
+
new_data = {
|
164 |
+
"choices": [{
|
165 |
+
"delta": {
|
166 |
+
"role": delta.get("role", "assistant"),
|
167 |
+
"content": new_content
|
168 |
+
}
|
169 |
+
}]
|
170 |
+
}
|
171 |
+
|
172 |
+
return current_content, new_data
|
173 |
+
return previous_content, data
|
174 |
+
except:
|
175 |
+
return previous_content, None
|
176 |
+
|
177 |
+
async def stream_generator(response: httpx.Response):
|
178 |
+
buffer = ""
|
179 |
+
previous_content = ""
|
180 |
+
|
181 |
+
async for chunk in response.aiter_bytes():
|
182 |
+
chunk_text = chunk.decode()
|
183 |
+
buffer += chunk_text
|
184 |
+
|
185 |
+
lines = buffer.split("\n")
|
186 |
+
buffer = lines.pop() if lines else ""
|
187 |
+
|
188 |
+
for line in lines:
|
189 |
+
line = line.strip()
|
190 |
+
if line.startswith("data: "):
|
191 |
+
previous_content, data = await process_line(line, previous_content)
|
192 |
+
if data:
|
193 |
+
yield f"data: {json.dumps(data)}\n\n"
|
194 |
+
|
195 |
+
if buffer:
|
196 |
+
previous_content, data = await process_line(buffer, previous_content)
|
197 |
+
if data:
|
198 |
+
yield f"data: {json.dumps(data)}\n\n"
|
199 |
+
|
200 |
+
yield "data: [DONE]\n\n"
|
201 |
+
|
202 |
+
@app.get("/healthz")
|
203 |
+
async def health_check():
|
204 |
+
return {"status": "ok"}
|
205 |
+
|
206 |
+
@app.get("/api/models")
|
207 |
+
async def get_models(request: Request):
|
208 |
+
global cached_models, cached_models_timestamp
|
209 |
+
|
210 |
+
auth_header = request.headers.get("Authorization")
|
211 |
+
if not auth_header or not auth_header.startswith("Bearer "):
|
212 |
+
return Response(status_code=401, content="Unauthorized")
|
213 |
+
|
214 |
+
now = time.time()
|
215 |
+
if cached_models and now - cached_models_timestamp < CACHE_TTL:
|
216 |
+
return Response(
|
217 |
+
content=cached_models,
|
218 |
+
media_type="application/json"
|
219 |
+
)
|
220 |
+
|
221 |
+
try:
|
222 |
+
response = await fetch_with_retry(
|
223 |
+
QWEN_MODELS_URL,
|
224 |
+
{"headers": {"Authorization": auth_header}}
|
225 |
+
)
|
226 |
+
|
227 |
+
cached_models = response.text
|
228 |
+
cached_models_timestamp = now
|
229 |
+
|
230 |
+
return Response(
|
231 |
+
content=cached_models,
|
232 |
+
media_type="application/json"
|
233 |
+
)
|
234 |
+
except Exception as error:
|
235 |
+
return Response(
|
236 |
+
content=json.dumps({"error": True, "message": str(error)}),
|
237 |
+
status_code=500
|
238 |
+
)
|
239 |
+
|
240 |
+
@app.post("/api/chat/completions")
|
241 |
+
async def chat_completions(request: Request):
|
242 |
+
auth_header = request.headers.get("Authorization")
|
243 |
+
if not auth_header or not auth_header.startswith("Bearer "):
|
244 |
+
return Response(status_code=401, content="Unauthorized")
|
245 |
+
|
246 |
+
request_data = await request.json()
|
247 |
+
messages = request_data.get("messages")
|
248 |
+
stream = request_data.get("stream", False)
|
249 |
+
model = request_data.get("model")
|
250 |
+
max_tokens = request_data.get("max_tokens")
|
251 |
+
|
252 |
+
if not model:
|
253 |
+
return Response(
|
254 |
+
content=json.dumps({"error": True, "message": "Model parameter is required"}),
|
255 |
+
status_code=400
|
256 |
+
)
|
257 |
+
|
258 |
+
try:
|
259 |
+
# 处理消息中的图片
|
260 |
+
processed_messages = await process_messages(messages, auth_header)
|
261 |
+
|
262 |
+
qwen_request = {
|
263 |
+
"model": model,
|
264 |
+
"messages": processed_messages,
|
265 |
+
"stream": stream
|
266 |
+
}
|
267 |
+
|
268 |
+
if max_tokens is not None:
|
269 |
+
qwen_request["max_tokens"] = max_tokens
|
270 |
+
|
271 |
+
response = await client.post(
|
272 |
+
QWEN_API_URL,
|
273 |
+
headers={
|
274 |
+
"Content-Type": "application/json",
|
275 |
+
"Authorization": auth_header
|
276 |
+
},
|
277 |
+
json=qwen_request
|
278 |
+
)
|
279 |
+
|
280 |
+
if stream:
|
281 |
+
return StreamingResponse(
|
282 |
+
stream_generator(response),
|
283 |
+
media_type="text/event-stream"
|
284 |
+
)
|
285 |
+
|
286 |
+
return Response(
|
287 |
+
content=response.text,
|
288 |
+
media_type="application/json"
|
289 |
+
)
|
290 |
+
|
291 |
+
except Exception as error:
|
292 |
+
return Response(
|
293 |
+
content=json.dumps({"error": True, "message": str(error)}),
|
294 |
+
status_code=500
|
295 |
+
)
|
296 |
+
|
297 |
+
if __name__ == "__main__":
|
298 |
+
import uvicorn
|
299 |
+
uvicorn.run(app, host="0.0.0.0", port=8000)
|
requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
fastapi==0.104.1
|
2 |
+
uvicorn==0.24.0
|
3 |
+
httpx==0.25.1
|
static/favicon.png
ADDED
![]() |