如何用OpenAI SDK调用Ollama LLM

Ollama目前内置了OpenAI Chat Completions API 的兼容端点，用户可以用OpenAI SDK访问本地Ollama模型，这里示例整个访问过程。

假设Ollama已安装，过程参考

在mac m1基于ollama运行deepseek r1_mac m1 ollama-CSDN博客

1 下载OpenAI SDK和模型

pip install openai

ollama pull qwen3:4b # chat 模型

ollama pull bge-m3:latest # embbeding 模型

2 开发测试例子

ollama目前支持openat的chat、emb等llm的访问。

1）chat接口

python chat例子

from openai import OpenAIclient = OpenAI(base_url="http://localhost:11434/v1",  # ollama openai addrapi_key="ollama"  # 本地未设置api key随意填
)
response = client.chat.completions.create(model="qwen3:4b",  # mac m1算力小使用4b小模型messages=messages=[{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Who won the world series in 2020?"},{"role": "assistant", "content": "The LA Dodgers won in 2020."},{"role": "user", "content": "Where was it played?"}],temperature=0.7,  max_tokens=512  
)
print(response.choices[0].message.content)

curl chat例子

curl http://localhost:11434/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "qwen3:4b",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Hello!"
            }
        ]
    }'

2) embedding接口

python emb 例子

import torch
from openai import OpenAI
client = OpenAI(base_url="http://localhost:11434/v1", # ollama openai addrapi_key="ollama"
)
texts = ["你好，什么是大模型？", "大模型是什么", "告诉我什么是大模型"]
def impl(texts):response = client.embeddings.create(model="bge-m3:latest", input=texts)embeddings = [e.embedding for e in response.data]return torch.tensor(embeddings)
embeddings = impl(texts)
print(embeddings.shape)

reference

---

OpenAI 兼容性

https://ollama.ac.cn/blog/openai-compatibility

ollam 提供兼容 OpenAI 格式的API

https://www.xiexianbin.cn/ai/ollama/api-compatible-openai/index.html