生成结构化 JSON
- cURL
- Python
- JavaScript
curl -X POST https://:11434/api/chat -H "Content-Type: application/json" -d '{
"model": "gpt-oss",
"messages": [{"role": "user", "content": "Tell me about Canada in one line"}],
"stream": false,
"format": "json"
}'
from ollama import chat
response = chat(
model='gpt-oss',
messages=[{'role': 'user', 'content': 'Tell me about Canada.'}],
format='json'
)
print(response.message.content)
import ollama from 'ollama'
const response = await ollama.chat({
model: 'gpt-oss',
messages: [{ role: 'user', content: 'Tell me about Canada.' }],
format: 'json'
})
console.log(response.message.content)
使用模式生成结构化 JSON
为format 字段提供一个 JSON 模式。
最好同时在提示词中以字符串形式传递 JSON 模式，以锚定模型的响应。
- cURL
- Python
- JavaScript
curl -X POST https://:11434/api/chat -H "Content-Type: application/json" -d '{
"model": "gpt-oss",
"messages": [{"role": "user", "content": "Tell me about Canada."}],
"stream": false,
"format": {
"type": "object",
"properties": {
"name": {"type": "string"},
"capital": {"type": "string"},
"languages": {
"type": "array",
"items": {"type": "string"}
}
},
"required": ["name", "capital", "languages"]
}
}'
使用 Pydantic 模型并将
model_json_schema() 传递给 format，然后验证响应from ollama import chat
from pydantic import BaseModel
class Country(BaseModel):
name: str
capital: str
languages: list[str]
response = chat(
model='gpt-oss',
messages=[{'role': 'user', 'content': 'Tell me about Canada.'}],
format=Country.model_json_schema(),
)
country = Country.model_validate_json(response.message.content)
print(country)
使用
zodToJsonSchema() 序列化 Zod 模式并解析结构化响应import ollama from 'ollama'
import { z } from 'zod'
import { zodToJsonSchema } from 'zod-to-json-schema'
const Country = z.object({
name: z.string(),
capital: z.string(),
languages: z.array(z.string()),
})
const response = await ollama.chat({
model: 'gpt-oss',
messages: [{ role: 'user', content: 'Tell me about Canada.' }],
format: zodToJsonSchema(Country),
})
const country = Country.parse(JSON.parse(response.message.content))
console.log(country)
示例：提取结构化数据
定义您想要返回的对象，并让模型填充字段from ollama import chat
from pydantic import BaseModel
class Pet(BaseModel):
name: str
animal: str
age: int
color: str | None
favorite_toy: str | None
class PetList(BaseModel):
pets: list[Pet]
response = chat(
model='gpt-oss',
messages=[{'role': 'user', 'content': 'I have two cats named Luna and Loki...'}],
format=PetList.model_json_schema(),
)
pets = PetList.model_validate_json(response.message.content)
print(pets)
示例：带有结构化输出的视觉功能
视觉模型接受相同的format 参数，从而实现对图像的确定性描述
from ollama import chat
from pydantic import BaseModel
from typing import Literal, Optional
class Object(BaseModel):
name: str
confidence: float
attributes: str
class ImageDescription(BaseModel):
summary: str
objects: list[Object]
scene: str
colors: list[str]
time_of_day: Literal['Morning', 'Afternoon', 'Evening', 'Night']
setting: Literal['Indoor', 'Outdoor', 'Unknown']
text_content: Optional[str] = None
response = chat(
model='gemma3',
messages=[{
'role': 'user',
'content': 'Describe this photo and list the objects you detect.',
'images': ['path/to/image.jpg'],
}],
format=ImageDescription.model_json_schema(),
options={'temperature': 0},
)
image_description = ImageDescription.model_validate_json(response.message.content)
print(image_description)
可靠结构化输出的技巧
- 使用 Pydantic (Python) 或 Zod (JavaScript) 定义模式，以便它们可以被重用于验证。
- 降低温度（例如，将其设置为
0）以获得更具确定性的补全。 - 结构化输出通过
response_format在兼容 OpenAI 的 API 中运行