Ollama整合OpenAI

Ollama提供了部分OpenAI API的兼容，以帮助将现有应用程序连接到Ollama。今天大家就来一起看看该怎么处理吧。

使用

OpenAI Python库

from openai import OpenAI

client = OpenAI(
    base_url='http://localhost:11434/v1/',

    # required but ignored
    api_key='ollama',
)

chat_completion = client.chat.completions.create(
    messages=[
        {
            'role': 'user',
            'content': 'Say this is a test',
        }
    ],
    model='llama3',
)

OpenAI JavaScript库

import OpenAI from 'openai'

const openai = new OpenAI({
  baseURL: 'http://localhost:11434/v1/',

  // required but ignored
  apiKey: 'ollama',
})

const chatCompletion = await openai.chat.completions.create({
  messages: [{ role: 'user', content: 'Say this is a test' }],
  model: 'llama3',
})

curl

curl http://localhost:11434/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "llama3",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Hello!"
            }
        ]
    }'

Models

在使用模型之前，先进行本地拉取模型

ollama pull llama3

默认模型名称

对于依赖于默认OpenAI模型名称（如gpt-3.5-turbo）的工具，使用ollama cp命令将现有模型名称复制到临时名称：

ollama cp llama3 gpt-3.5-turbo

然后，可以在模型字段中指定这个新模型名

curl http://localhost:11434/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "gpt-3.5-turbo",
        "messages": [
            {
                "role": "user",
                "content": "Hello!"
            }
        ]
    }'