File size: 3,747 Bytes
e100b79 ce0c73c e100b79 ce0c73c e100b79 ce0c73c e100b79 ecaf86a e100b79 ce0c73c e100b79 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
import os
import time
import random
import asyncio
import requests
from fastapi import FastAPI, HTTPException, Request
from fastapi.responses import StreamingResponse
from pydantic import BaseModel
from typing import List, Optional, Union
app = FastAPI()
class ChatCompletionMessage(BaseModel):
role: str
content: str
class ChatCompletionRequest(BaseModel):
model: str
messages: List[ChatCompletionMessage]
temperature: Optional[float] = 1.0
max_tokens: Optional[int] = None
stream: Optional[bool] = False
class ChatCompletionResponse(BaseModel):
id: str
object: str
created: int
model: str
choices: List[dict]
usage: dict
def generate_random_ip():
return f"{random.randint(1,255)}.{random.randint(0,255)}.{random.randint(0,255)}.{random.randint(0,255)}"
async def fetch_response(messages: List[ChatCompletionMessage], model: str):
your_api_url = "https://chatpro.ai-pro.org/api/ask/openAI"
headers = {
"content-type": "application/json",
"X-Forwarded-For": generate_random_ip(),
"origin": "https://chatpro.ai-pro.org",
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36"
}
# 将消息列表转换为单个字符串，保留对话历史
conversation = "\n".join([f"{msg.role}: {msg.content}" for msg in messages])
# 添加指导语
conversation += "\n请关注并回复user最近的消息并避免总结对话历史的回答"
data = {
"text": conversation,
"endpoint": "openAI",
"model": model
}
response = requests.post(your_api_url, headers=headers, json=data)
if response.status_code != 200:
raise HTTPException(status_code=response.status_code, detail="Error from upstream API")
return response.json()
async def stream_response(content: str):
# Send the entire content as a single chunk
yield f"data: {{'id': 'chatcmpl-{os.urandom(12).hex()}', 'object': 'chat.completion.chunk', 'created': 1677652288, 'model': 'gpt-3.5-turbo-0613', 'choices': [{'index': 0, 'delta': {{'content': '{content}'}}, 'finish_reason': None}]}}\n\n"
yield f"data: {{'id': 'chatcmpl-{os.urandom(12).hex()}', 'object': 'chat.completion.chunk', 'created': 1677652288, 'model': 'gpt-3.5-turbo-0613', 'choices': [{'index': 0, 'delta': {{}}, 'finish_reason': 'stop'}]}}\n\n"
yield 'data: [DONE]\n\n'
@app.post("/hf/v1/chat/completions")
async def chat_completions(request: Request):
body = await request.json()
chat_request = ChatCompletionRequest(**body)
# 传递整个消息历史到API
api_response = await fetch_response(chat_request.messages, chat_request.model)
content = api_response.get("response", "")
if chat_request.stream:
return StreamingResponse(stream_response(content), media_type="text/event-stream")
else:
openai_response = ChatCompletionResponse(
id="chatcmpl-" + os.urandom(12).hex(),
object="chat.completion",
created=int(time.time()),
model=chat_request.model,
choices=[
{
"index": 0,
"message": {
"role": "assistant",
"content": content
},
"finish_reason": "stop"
}
],
usage={
"prompt_tokens": sum(len(msg.content) for msg in chat_request.messages),
"completion_tokens": len(content),
"total_tokens": sum(len(msg.content) for msg in chat_request.messages) + len(content)
}
)
return openai_response |