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
