win本地运行llm（借助于ollama）

一、准备工作

1、下载ollama

官网链接：Ollama

常见指令链接：GitHub - ollama/ollama: Get up and running with Llama 2, Mistral, Gemma, and other large language models.

2、llama2为例子

ollama run llama2

接下来就可以下载，在终端进行一些简单的对话。

二、client.py连接(本地pycharm运行)

1、启动ollama，并且保证ollama里面有llama2大模型，采用指令。

ollama list

2、ollama的默认接口是127.0.0.1:11434

用python简单的网络连接的代码为：

import json
import requests

# NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve`
model = "llama2"  # TODO: update this for whatever model you wish to use


def chat(messages):
 
    r = requests.post(
        "http://127.0.0.1:11434/api/chat",
        json={"model": model, "messages": messages, "stream": True},
    )
   
    r.raise_for_status()
    output = ""

    for line in r.iter_lines():
        body = json.loads(line)
        if "error" in body:
            raise Exception(body["error"])
        if body.get("done") is False:
            message = body.get("message", "")
            content = message.get("content", "")
            output += content
            # the response streams one token at a time, print that as we receive it
            print(content, end="", flush=True)

        if body.get("done", False):
            message["content"] = output
            return message


def main():
    messages = []

    while True:
        user_input = input("Enter a prompt: ")
        if not user_input:
            exit()
        print()
        messages.append({"role": "user", "content": user_input})
        message = chat(messages)
        messages.append(message)
        print("\n\n")


if __name__ == "__main__":
    main()

启动后可以，进行一系列对话。

注：网络要保证稳定，确定没有其他进程在连接11434端口，最好不要挂着梯子用，不然都会容易报错失败。

3、运行效果