智能体搭建：DeepSeek的Ollama部署FastAPI封装调用

 ollama pull deepseek-r1:1.5b

 ollama run deepseek-r1:1.5b

 ollama ps

import requests
# 调用ollama，指定模型和本地部署后api地址
def query_ollama(prompt, model="deepseek-r1:1.5b"):
    url = "http://localhost:11434/api/generate"
    data = {
        "model": model,
        "prompt": prompt,
        "stream": False  
    }
    response = requests.post(url, json=data)
    if response.status_code == 200:
        return response.json()["response"]
    else:
        raise Exception(f"API 请求失败: {response.text}")
# 使用示例
response = query_ollama("你好，你是什么大模型，请浓重介绍一下自己！")
print(response)

<think>
您好！我是由中国的深度求索（DeepSeek）公司开发的智能助手DeepSeek-R1。如您有任何任何问题，我会尽我所能为您提供帮助。
</think>
您好！我是由中国的深度求索（DeepSeek）公司开发的智能助手DeepSeek-R1。如您有任何任何问题，我会尽我所能为您提供帮助。

import requests
# 流模式输出结果内容
def query_ollama(prompt, model="deepseek-r1:1.5b", stream=False):
    url = "http://localhost:11434/api/generate"
    data = {
        "model": model,
        "prompt": prompt,
        "stream": stream  
    }
    if stream:
        # 开始处理流式响应结果
        with requests.post(url, json=data, stream=True) as response:
            if response.status_code == 200:
                # 逐行打印结果内容
                for line in response.iter_lines(decode_unicode=True):
                    if line:
                        # Ollama流式返回每行是一个json字符串
                        try:
                            import json
                            obj = json.loads(line)
                            print(obj.get("response", ""), end="", flush=True)
                        except Exception as e:
                            print(f"解析流式响应出错: {e}")
            else:
                raise Exception(f"API 请求失败: {response.text}")
    else:
        response = requests.post(url, json=data)
        if response.status_code == 200:
            return response.json()["response"]
        else:
            raise Exception(f"API 请求失败: {response.text}")
# 使用示例
print("流式响应结果输出：")
query_ollama("你好，你是什么大模型，请隆重介绍一下自己", stream=True)

 http://127.0.0.1:8000/api/aichat

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
import requests
app = FastAPI()
# 定义请求模型
class ChatRequest(BaseModel):
    prompt: str
    model: str = "deepseek-r1:1.5b"
# 允许跨域请求（根据需要配置）
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_methods=["*"],
    allow_headers=["*"],
)
#此处画重点，外部访问的接口地址
@app.post("/api/aichat")
async def chat(request: ChatRequest):
    ollama_url = "http://localhost:11434/api/generate"
    data = {
        "model": request.model, #接口调用要传入的模型参数
        "prompt": request.prompt, #接口调用要传入的指令
        "stream": False
    }
    response = requests.post(ollama_url, json=data)
    if response.status_code == 200:
        return {"response": response.json()["response"]}
    else:
        return {"error": "Failed to get response from Ollama"}, 500
if __name__ == "__main__":
    import uvicorn
#外部调用时访问的端口
    uvicorn.run(app, host="0.0.0.0", port=8000)

INFO:     Started server process [10588]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit) 

import requests
response = requests.post(
    "http://localhost:8000/api/aichat",
    json={"model":"deepseek-r1:1.5b","prompt": "你好，请介绍一下你自己"}
)
print(response.json())

 {'response': '<think>\n\n</think>\n\n您好！我是由中国的深度求索（DeepSeek）公司开发的智能助手DeepSeek-R1。关于我以及我的能力，请参考官方文档或使用相关AI服务工具获取详细信息。'}