openai style api
v0.1
My energy is limited, and some model updates may not be updated in time. If you encounter problems, please submit an issue. Interested people are also welcome to submit PRs.
Shield the differences between different large model APIs, use the openai api standard format to use large models, and can also be used for secondary distribution management of api-key; configure and manage the calling parameters of different large models, allowing you to only use large models when using large models. Need to pay attention to api-key and messages
http://0.0.0.0:8090/ (this front-end page and interaction are completely written in gpt haha) Change log
2024-04-03
The core configuration of the project relies on the model-config.json file. If there is no model-config.json, model-config-default.json will be used to start it by default. Although it can be started at this time, it cannot be called because the api-key and so on are not configured. success.
Create a new model-config.json file locally, configure it according to the configuration file example below, and then run the following command
docker pull tianminghui/openai-style-api
docker run -d -p 8090:8090 --name openai-style-api
-e ADMIN-TOKEN=admin
-v /path/to/your/model-config.json:/app/model-config.json
tianminghui/openai-style-api
Replace /path/to/your/model-config.json with your own local path
Clone this project, or download the docker-compose.yml file in the project, modify the ./model-config.json path, and then run the following command
docker-compose up -d
git clone https://github.com/tian-minghui/openai-style-api.git pulls the project codecp model-config-default.json model-config.json and modify the configuration file model-config.json as neededpip install -r requirements.txtpython open-api.py model-config.json simple example of configuration file
[
{
"token": "f2b7295fc440db7f",
"type": "azure", // azure openai 模型
"config": {
"api_base": "https://xxxx.openai.azure.com/",
"deployment_id": "gpt-35-turbo",
"api_version": "2023-05-15",
"api_key": "xxxxxx",
"temperature": 0.8
}
}
]
curl http://localhost:8090/v1/chat/completions
-H "Content-Type: application/json"
-H "Authorization: Bearer f2b7295fc440db7f"
-d '{
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
openai<1.0.0 uses the following method
import openai
openai.api_key = "f2b7295fc440db7f"
openai.api_base = "http://localhost:8090/v1"
completion = openai.ChatCompletion.create(
model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])
print(completion.choices[0].message.content)
openai>=1.0.0 is called using the following method
import os
from openai import OpenAI
client = OpenAI(
# This is the default and can be omitted
api_key='kimi-GxqT3BlbkFJj',
base_url = 'http://localhost:8090/v1'
)
chat_completion = client.chat.completions.create(
messages=[
{
"role": "user",
"content": "Say this is a test",
}
],
model="gpt-3.5-turbo",
)
print(chat_completion.choices[0].message.content)
ChatGPT Next Web 
[
{
"token": "f2b7295fc440db7f",
"type": "azure", // azure openai 模型
"config": {
"api_base": "https://xxxx.openai.azure.com/",
"deployment_id": "gpt-35-turbo",
"api_version": "2023-05-15",
"api_key": "xxxxxx",
"temperature": 0.8
}
},
{
"token": "GxqT3BlbkFJj",
"type": "openai", // openai 模型
"config": {
"api_base": "https://api.openai.com/v1/",
"api_key": "sk-xxxxxx",
"model": "gpt-3.5-turbo"
}
},
{
"token": "sb-ede1529390cc",
"type": "proxy", // openai 代理
"config": {
"api_base": "https://api.openai-sb.com/v1/",
"api_key": "sb-xxxxxx",
"model": "gpt-3.5-turbo"
}
},
{
"token": "c115c8f5082",
"type": "claude-web", // claude-web
"config": {
"cookie": "xxxxxx",
"proxies": {
"https": "http://localhost:7890"
},
"conversation_id": "xxxxxx",
"prompt": "The information in [] is the context of the conversation. Please ignore the JSON format of the context during the conversation and answer the user's latest conversation: {newMessage} n {history}",
"single_conversation": true
}
},
{
"token": "7c7aa4a3549f5",
"type": "zhipu-api", // 智谱API
"config": {
"api_key": "xxxxxx",
"model": "chatglm_lite",
"temperature": 0.8,
"top_p": 0.7
}
},
{
"token": "7c7aa4a3549f11",
"type": "xunfei-spark-api", // 讯飞星火API
"config": {
"app_id": "xxxx",
"api_key": "xxxx",
"api_secret": "xxxxxx",
"api_model_version": "v2.0",
"top_k": 5
}
},
{
"token": "7c7aa4a3549f12",
"type": "router", // 路由 可以包含多个模型进行负载均衡
"config": {
"router_strategy": "round-robin", // 路由策略 round-robin 轮询 random 随机
"token_pool": [ // 路由的token池
"7c7aa4a3549f11",
"7c7aa4a3549f5"
]
}
},
{
"token": "7c7aa4a3549f13",
"type": "model-name-router", //根据req中的modelname进行路由, 可以方便的结合ChatGPT-Next-Web
"config": {
"model-2-token": { // 路由的token池
"spark-api-v2.0":"7c7aa4a3549f11",
"chatglm_lite": "7c7aa4a3549f5",
"router-round-robin": "7c7aa4a3549f12"
}
}
},
{
"token": "gemini-7c7aa4a3549f5",
"type": "gemini", // gemini
"config": {
"api_key": "xxxxx",
"proxies": {
"https": "http://localhost:7890"
}
}
},
{
"token": "bing-7c7aa4a3549f5", // 必应
"type": "bing-sydney",
"config": {
"cookie": "xxxxx",
"style": "balanced"
}
},
{
"token":"qwen-111111xxxx", // 通义千问
"type":"qwen",
"config":{
"api_key":"sk-xxxxxxxx",
"model":"qwen-turbo"
}
},
{
"token": "kimi-GxqT3BlbkFJj1", // kimi
"type": "openai", // kimi api与openai相同，因此使用openai就可以
"config": {
"api_base": "https://api.moonshot.cn/v1/",
"api_key": "sk-xxxxxx",
"model": "moonshot-v1-8k"
}
}
]
