本地LLM的OpenAI兼容API（Ollama、vLLM、LM Studio）-- Python与Node.js指南 2026

# 1. Install the OpenAI library
pip install openai

# 2. Connect to Ollama
from openai import OpenAI

client = OpenAI(
  base_url="http://localhost:11434/v1",
  api_key="ollama"  # dummy key; Ollama ignores it
)

# 3. Make a request
response = client.chat.completions.create(
  model="llama3.2:3b",
  messages=[
    {"role": "user", "content": "What is 2+2?"}
  ]
)

print(response.choices[0].message.content)

// 1. Install
npm install openai

// 2. Connect to Ollama
const OpenAI = require("openai").default;

const client = new OpenAI({
  baseURL: "http://localhost:11434/v1",
  apiKey: "ollama"
});

// 3. Make a request
const response = await client.chat.completions.create({
  model: "llama3.2:3b",
  messages: [{
    role: "user",
    content: "What is 2+2?"
  }]
});

console.log(response.choices[0].message.content);

# Python: Connect to LM Studio (localhost:1234)
from openai import OpenAI

client = OpenAI(
  base_url="http://localhost:1234/v1",
  api_key="lm-studio"  # any string; LM Studio ignores it
)

response = client.chat.completions.create(
  model="llama-3.2-3b-instruct",  # exact model name shown in LM Studio
  messages=[
    {"role": "user", "content": "What is 2+2?"}
  ]
)

print(response.choices[0].message.content)

// Browser-side JavaScript (if server is localhost:3000, Ollama is localhost:11434)
fetch("http://localhost:11434/v1/chat/completions", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    model: "llama3.2:3b",
    messages: [{ role: "user", content: "What is 2+2?" }]
  })
})
  .then(res => res.json())
  .then(data => console.log(data.choices[0].message.content))

# Python: streaming example
from openai import OpenAI

client = OpenAI(
  base_url="http://localhost:11434/v1",
  api_key="ollama"
)

stream = client.chat.completions.create(
  model="llama3.2:3b",
  messages=[{"role": "user", "content": "Count to 10"}],
  stream=True
)

for chunk in stream:
  if chunk.choices[0].delta.content:
    print(chunk.choices[0].delta.content, end="", flush=True)

# Example: local model calls a weather function
tools = [{
  "type": "function",
  "function": {
    "name": "get_weather",
    "description": "Get current weather",
    "parameters": {
      "type": "object",
      "properties": {
        "location": {"type": "string"}
      }
    }
  }
}]

response = client.chat.completions.create(
  model="llama3.2:8b",
  messages=[{"role": "user", "content": "What is the weather in SF?"}],
  tools=tools
)

# Check if model returned a function call
if response.choices[0].message.tool_calls:
  call = response.choices[0].message.tool_calls[0]
  print(f"Call function: {call.function.name} with {call.function.arguments}")