问题

在国内使用llamaIndex连接openai报错，如何使用自定义模型？

众所周知，openai对国内访问做了限制，所以连接报错。

解决

方法一：使用第三方中转到openai服务器

如果你就是想用openai的模型，用国内的第三方中转到openai服务器就好了。

llamaIndex线上访问模型，只支持openai的模型名，如果你想用其他厂商模型，请尝试修改源代码。

然后新建一个.env文件

OPENAI_BASE_URL = "https://sg.uiuiapi.com/v1"
OPENAI_API_KRY = "这儿替换你申请的key"

用python安装依赖的包：pip install dotenv openai

新建一个starter.py文件，运行后成功返回结果！

import asyncio
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
from dotenv import load_dotenv
import openai
import os
# 加载当前目录.env文件存储的环境变量
load_dotenv()
# 变量赋值，以用于中转到openai
openai.api_key = os.environ["OPENAI_API_KEY"]
openai.base_url = os.environ["OPENAI_BASE_URL"]

# Define a simple calculator tool
def multiply(a: float, b: float) -> float:
    """Useful for multiplying two numbers."""
    return a * b


# Create an agent workflow with our calculator tool
agent = FunctionAgent(
    tools=[multiply],
    llm=OpenAI(model="gpt-4o-mini"),
    system_prompt="You are a helpful assistant that can multiply two numbers.",
)


async def main():
    # Run the agent
    response = await agent.run("What is 1234 * 4567?")
    print(str(response))


# Run the agent
if __name__ == "__main__":
    asyncio.run(main())

方法二：本地用ollama部署llama、qwen

如果用ollama部署模型，就不需要设置环境变量。

新建文件：starter_ollama.py，运行成功

import asyncio
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.ollama import Ollama


# Define a simple calculator tool
def multiply(a: float, b: float) -> float:
    """Useful for multiplying two numbers."""
    return a * b


# Create an agent workflow with our calculator tool
agent = FunctionAgent(
    tools=[multiply],
    llm=Ollama(
        model="llama3.1:latest",
        request_timeout=360.0,
        # Manually set the context window to limit memory usage
        context_window=8000,
    ),
    system_prompt="You are a helpful assistant that can multiply two numbers.",
)


async def main():
    # Run the agent
    response = await agent.run("What is 1234 * 4567?")
    print(str(response))


# Run the agent
if __name__ == "__main__":
    asyncio.run(main())