函數調用
函數調用允许模型為你定義的函數生成結構化參數。模型本身不會直接执行函數，而是輸出 JSON，你可以在程式碼中據此調用该函數。
工作原理
- 定義工具 — 在請求中提供函數 schema
- 模型決策 — 模型決定是否調用一個或多個工具
- 由你执行 — 解析模型的工具調用並運行實際函數
- 返回結果 — 將函數輸出回傳給模型
- 模型響應 — 模型基於工具結果生成最終回答
定義工具
from openai import OpenAI
client = OpenAI(
base_url="https://api.linkastra.ai/v1",
api_key="YOUR_API_KEY"
)
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "City name, e.g., Beijing"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "Temperature unit"
}
},
"required": ["location"]
}
}
}
]完整示例
import json
response = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "What's the weather like in Shanghai?"}],
tools=tools,
tool_choice="auto"
)
message = response.choices[0].message
if message.tool_calls:
for tool_call in message.tool_calls:
function_name = tool_call.function.name
function_args = json.loads(tool_call.function.arguments)
# Execute the function
if function_name == "get_weather":
result = get_weather(**function_args)
# Send result back to the model
response = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[
{"role": "user", "content": "What's the weather like in Shanghai?"},
message,
{
"role": "tool",
"tool_call_id": tool_call.id,
"content": str(result)
}
]
)
print(response.choices[0].message.content)工具選擇
| 值 | 說明 |
|---|---|
auto | 由模型決定是否調用工具（默认） |
none | 模型不會調用任何工具 |
required | 模型必须至少調用一個工具 |
{"type": "function", "function": {"name": "..."}} | 強制調用指定函數 |
多個工具
你可以在單次請求中定義多個工具：
tools = [
{
"type": "function",
"function": {
"name": "search_products",
"description": "Search the product catalog",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"category": {"type": "string"},
"max_price": {"type": "number"}
},
"required": ["query"]
}
}
},
{
"type": "function",
"function": {
"name": "place_order",
"description": "Place an order for a product",
"parameters": {
"type": "object",
"properties": {
"product_id": {"type": "string"},
"quantity": {"type": "integer"}
},
"required": ["product_id", "quantity"]
}
}
}
]最佳實踐
- 編寫清晰的描述 — 模型依賴函數和參數的描述来決定何時以及如何調用它們
- 為受限值使用 enum — 尽可能用
enum限定參數取值 - 标注必填字段 — 始終將必要參數标记為
required - 優雅地處理錯誤 — 將錯誤資訊作為工具結果返回，便於模型自我纠正
- 控制工具數量 — 工具過多會讓模型困惑，請保持聚焦
並行工具調用
部分模型支援在單次響應中調用多個工具。可遍歷 message.tool_calls 来處理：
if message.tool_calls:
tool_results = []
for tool_call in message.tool_calls:
result = execute_function(tool_call.function.name, json.loads(tool_call.function.arguments))
tool_results.append({
"role": "tool",
"tool_call_id": tool_call.id,
"content": str(result)
})