MIAPI — Grounded Web Answers

MIAPI — 有据可依的 AI 答案 API

MIAPI 的官方 Python 客户端 MIAPI — 获取基于实时网页搜索的 AI 答案。

安装

pip install miapi-sdk

快速入门

from miapi import MIAPI

client = MIAPI("YOUR_API_KEY")

# Get a grounded answer with citations
result = client.answer("What is quantum computing?", citations=True)
print(result.answer)     # AI-generated answer with [1][2] markers
print(result.sources)    # List of source URLs
print(result.confidence) # 0.0 - 1.0

功能

基于网页信息的答案

result = client.answer("Who won the last World Cup?")
print(result.answer)

知识模式 — 根据你的数据回答

result = client.answer(
    "What is the return policy?",
    mode="knowledge",
    knowledge="Returns accepted within 30 days with receipt..."
)
print(result.answer)

仅搜索 — 原始结果

sources = client.search("latest AI research papers")
for source in sources:
    print(source.title, source.url)

新闻搜索

news = client.news("technology", num_results=5)
for article in news:
    print(article.title, article.date)

图片搜索

images = client.images("golden retriever")
for img in images:
    print(img.url, img.width, img.height)

流式传输

for event in client.stream("Explain quantum computing"):
    if event['type'] == 'answer':
        print(event['content'], end='', flush=True)
    elif event['type'] == 'done':
        print(f"\nDone in {event.get('query_time_ms')}ms")

查看用量

info = client.usage()
print(f"Used {info.queries_this_month}/{info.monthly_limit} this month")
print(f"Tier: {info.tier}")

自定义选项

result = client.answer(
    "Compare Python and Rust",
    response_format="markdown",   # text, short, json, markdown
    temperature=0.5,              # 0.0 (precise) to 1.0 (creative)
    max_tokens=800,               # Max answer length
    language="French",            # Answer in any language
    search_domains=["wikipedia.org"],  # Restrict sources
    system_prompt="Answer like a professor",
)

错误处理

from miapi import MIAPI, MIAPIError, RateLimitError, AuthenticationError

client = MIAPI("YOUR_API_KEY")

try:
    result = client.answer("Hello")
except AuthenticationError:
    print("Bad API key")
except RateLimitError as e:
    print(f"Rate limited: {e.message}")
except MIAPIError as e:
    print(f"Error: {e.message} (HTTP {e.status_code})")

OpenAI 即插即用替代方案

MIAPI 也兼容 OpenAI Python 客户端：

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_MIAPI_KEY",
    base_url="https://api.miapi.uk/v1"
)

response = client.chat.completions.create(
    model="miapi-grounded",
    messages=[{"role": "user", "content": "What is AI?"}]
)
print(response.choices[0].message.content)

获取 API 密钥

在 miapi.uk 免费注册 — 每月包含 500 次查询。

链接

• 网站
• API 文档
• 操场
• 定价

在 Claude Desktop、Cursor 或 Windsurf 中使用（MCP）

MIAPI 内置 MCP 服务，因此 AI 助手可以搜索网页并获取 带有真实引用的答案，无需编写任何代码。

pip install "miapi-sdk[mcp]"

然后将其添加到助手的 MCP 配置中：

{
  "mcpServers": {
    "miapi": {
      "command": "miapi-mcp",
      "env": { "MIAPI_API_KEY": "your_key_here" }
    }
  }
}

提供的工具：web_answer、web_search、news_search、image_search、 check_usage。

在 https://miapi.uk 获取密钥 — 包含免费套餐。