腾讯云-HAI域探秘——自行搭建AI对话服务对话

单独访问效果：

vscode内运行效果：

我们使用腾讯云来创建，有完整的操作流程，很方便我们搭建使用。

一、服务创建

创建效果：

步骤1：

步骤2：(这里可以下拉选择大一些的硬盘)

剩余的时间需要等待。

创建完毕效果：

二、操作面板介绍

1、chatglm_gradio:

我们可以直接通过这个网址进行对话操作。

2、jupyter_lab:

创建控制台窗口，可以在这里进行具体的代码编辑与运行。

三、基础服务示例(jupyter_lab操作)

1、进入并启动服务

代码语言：javascript复制

cd /root/ChatGLM2-6B/
python api.py

运行起来能看到有信息提示。

2、启动后开启访问端口(8000)

进入到服务详情。

添加防火墙可通过的端口号。

添加效果：

3、Python接口访问效果

添加后即可访问：http://你的公网IP:8000/ 的这个接口，具体服务参数如下列代码：

代码语言：javascript复制

import requests

# 定义测试数据，以及FastAPI服务器的地址和端口
server_url = "http://0.0.0.0:8000"  # 请确保将地址和端口更改为您的API服务器的实际地址和端口
test_data = {
    "prompt": "'电影雨人讲的是什么？'",
    "history": [],
    "max_length": 50,
    "top_p": 0.7,
    "temperature": 0.95
}

# 发送HTTP POST请求
response = requests.post(server_url, json=test_data)

# 处理响应
if response.status_code == 200:
    result = response.json()
    print("Response:", result["response"])
    print("History:", result["history"])
    print("Status:", result["status"])
    print("Time:", result["time"])
else:
    print("Failed to get a valid response. Status code:", response.status_code)

访问效果：

四、正式服务代码

1、修改【openai-api.py】文件

使用以下代码覆盖原有的代码：

代码语言：javascript复制

# coding=utf-8
# Implements API for ChatGLM2-6B in OpenAI's format. (https://platform.openai.com/docs/api-reference/chat)
# Usage: python openai_api.py
# Visit http://localhost:8000/docs for documents.

import time
import torch
import uvicorn
from pydantic import BaseModel, Field
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from contextlib import asynccontextmanager
from typing import Any, Dict, List, Literal, Optional, Union
from transformers import AutoTokenizer, AutoModel
from sse_starlette.sse import ServerSentEvent, EventSourceResponse


@asynccontextmanager
async def lifespan(app: FastAPI): # collects GPU memory
    yield
    if torch.cuda.is_available():
        torch.cuda.empty_cache()
        torch.cuda.ipc_collect()


app = FastAPI(lifespan=lifespan)

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

class ModelCard(BaseModel):
    id: str
    object: str = "model"
    created: int = Field(default_factory=lambda: int(time.time()))
    owned_by: str = "owner"
    root: Optional[str] = None
    parent: Optional[str] = None
    permission: Optional[list] = None


class ModelList(BaseModel):
    object: str = "list"
    data: List[ModelCard] = []


class ChatMessage(BaseModel):
    role: Literal["user", "assistant", "system"]
    content: str


class DeltaMessage(BaseModel):
    role: Optional[Literal["user", "assistant", "system"]] = None
    content: Optional[str] = None


class ChatCompletionRequest(BaseModel):
    model: str
    messages: List[ChatMessage]
    temperature: Optional[float] = None
    top_p: Optional[float] = None
    max_length: Optional[int] = None
    stream: Optional[bool] = False


class ChatCompletionResponseChoice(BaseModel):
    index: int
    message: ChatMessage
    finish_reason: Literal["stop", "length"]


class ChatCompletionResponseStreamChoice(BaseModel):
    index: int
    delta: DeltaMessage
    finish_reason: Optional[Literal["stop", "length"]]


class ChatCompletionResponse(BaseModel):
    model: str
    object: Literal["chat.completion", "chat.completion.chunk"]
    choices: List[Union[ChatCompletionResponseChoice, ChatCompletionResponseStreamChoice]]
    created: Optional[int] = Field(default_factory=lambda: int(time.time()))


@app.get("/v1/models", response_model=ModelList)
async def list_models():
    global model_args
    model_card = ModelCard(id="gpt-3.5-turbo")
    return ModelList(data=[model_card])


@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
async def create_chat_completion(request: ChatCompletionRequest):
    global model, tokenizer

    if request.messages[-1].role != "user":
        raise HTTPException(status_code=400, detail="Invalid request")
    query = request.messages[-1].content

    prev_messages = request.messages[:-1]
    if len(prev_messages) > 0 and prev_messages[0].role == "system":
        query = prev_messages.pop(0).content   query

    history = []
    if len(prev_messages) % 2 == 0:
        for i in range(0, len(prev_messages), 2):
            if prev_messages[i].role == "user" and prev_messages[i 1].role == "assistant":
                history.append([prev_messages[i].content, prev_messages[i 1].content])

    if request.stream:
        generate = predict(query, history, request.model)
        return EventSourceResponse(generate, media_type="text/event-stream")

    response, _ = model.chat(tokenizer, query, history=history)
    choice_data = ChatCompletionResponseChoice(
        index=0,
        message=ChatMessage(role="assistant", content=response),
        finish_reason="stop"
    )

    return ChatCompletionResponse(model=request.model, choices=[choice_data], object="chat.completion")


async def predict(query: str, history: List[List[str]], model_id: str):
    global model, tokenizer

    choice_data = ChatCompletionResponseStreamChoice(
        index=0,
        delta=DeltaMessage(role="assistant"),
        finish_reason=None
    )
    chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
    #yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
    yield "{}".format(chunk.model_dump_json(exclude_unset=True))

    current_length = 0

    for new_response, _ in model.stream_chat(tokenizer, query, history):
        if len(new_response) == current_length:
            continue

        new_text = new_response[current_length:]
        current_length = len(new_response)

        choice_data = ChatCompletionResponseStreamChoice(
            index=0,
            delta=DeltaMessage(content=new_text),
            finish_reason=None
        )
        chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
        #yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
        yield "{}".format(chunk.model_dump_json(exclude_unset=True))

    choice_data = ChatCompletionResponseStreamChoice(
        index=0,
        delta=DeltaMessage(),
        finish_reason="stop"
    )
    chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
    #yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
    yield "{}".format(chunk.model_dump_json(exclude_unset=True))
    yield '[DONE]'



if __name__ == "__main__":
    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", revision="v1.0", trust_remote_code=True)
    model = AutoModel.from_pretrained("THUDM/chatglm2-6b", revision="v1.0", trust_remote_code=True).cuda()
    # 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
    # from utils import load_model_on_gpus
    # model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)
    model.eval()

    uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)

2、运行【openai-api.py】文件，服务端开启服务

在控制台直接输入python openai-api.py即可运行

五、可视化页面搭建

1、在创建cloud Studio的时候选择【应用推荐】

选择【ChatGPT Next Web】

2、Fork项目

3、修改【.env.template】文件

直接替换我下面的就行，但是需要替换一下你服务的IP。

代码语言：javascript复制

# Your openai api key. (required)
OPENAI_API_KEY="hongMuXiangXun"

# Access passsword, separated by comma. (optional)
CODE=

# You can start service behind a proxy
PROXY_URL=http://你的IP:8000

# Override openai api request base url. (optional)
# Default: https://api.openai.com
# Examples: http://your-openai-proxy.com
BASE_URL=http://你的IP:8000

# Specify OpenAI organization ID.(optional)
# Default: Empty
OPENAI_ORG_ID=

# (optional)
# Default: Empty
# If you do not want users to input their own API key, set this value to 1.
HIDE_USER_API_KEY=

# (optional)
# Default: Empty
# If you do not want users to use GPT-4, set this value to 1.
DISABLE_GPT4=

# (optional)
# Default: Empty
# If you do not want users to query balance, set this value to 1.
HIDE_BALANCE_QUERY=