如何在 Python、JavaScript 等编程语言中集成 Ollama？ - 面试题

Ollama 可以轻松集成到各种编程语言和框架中：

Python 集成：

使用 ollama Python 库：

python
import ollama

# 生成文本
response = ollama.generate(model='llama3.1', prompt='Hello, how are you?')
print(response['response'])

# 对话
messages = [
    {'role': 'user', 'content': 'Hello!'},
    {'role': 'assistant', 'content': 'Hi there!'},
    {'role': 'user', 'content': 'How are you?'}
]
response = ollama.chat(model='llama3.1', messages=messages)
print(response['message']['content'])

# 流式响应
for chunk in ollama.generate(model='llama3.1', prompt='Tell me a story', stream=True):
    print(chunk['response'], end='', flush=True)

JavaScript/Node.js 集成：

使用 ollama-js 库：

javascript
import ollama from 'ollama-js'

const client = new ollama.Ollama()

// 生成文本
const response = await client.generate({
  model: 'llama3.1',
  prompt: 'Hello, how are you?'
})
console.log(response.response)

// 对话
const chat = await client.chat({
  model: 'llama3.1',
  messages: [
    { role: 'user', content: 'Hello!' },
    { role: 'assistant', content: 'Hi there!' },
    { role: 'user', content: 'How are you?' }
  ]
})
console.log(chat.message.content)

Go 集成：

go
package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "net/http"
)

type GenerateRequest struct {
    Model  string `json:"model"`
    Prompt string `json:"prompt"`
}

type GenerateResponse struct {
    Response string `json:"response"`
}

func main() {
    req := GenerateRequest{
        Model:  "llama3.1",
        Prompt: "Hello, how are you?",
    }
    
    body, _ := json.Marshal(req)
    resp, _ := http.Post("http://localhost:11434/api/generate", "application/json", bytes.NewBuffer(body))
    
    var result GenerateResponse
    json.NewDecoder(resp.Body).Decode(&result)
    fmt.Println(result.Response)
}

LangChain 集成：

python
from langchain_community.llms import Ollama

llm = Ollama(model="llama3.1")

# 简单调用
response = llm.invoke("Tell me a joke")
print(response)

# 链式调用
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser

prompt = ChatPromptTemplate.from_template("Tell me a {adjective} joke about {topic}")
chain = prompt | llm | StrOutputParser()
print(chain.invoke({"adjective": "funny", "topic": "programming"}))

REST API 集成：

任何支持 HTTP 的语言都可以直接调用 REST API：

bash
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.1",
  "prompt": "Hello, how are you?",
  "stream": false
}'