JSON 输出示例

此示例中包含两个 Python 脚本。randomaddresses.py 从不同国家生成随机地址。predefinedschema.py 设置模型填充的模板。

运行示例

1. 确保您已安装 llama2 模型：

ollama pull llama2

2. 安装 Python 需求。

pip install -r requirements.txt

3. 运行随机地址示例：

python randomaddresses.py

4. 运行预定义模式示例：

python predefinedschema.py

查看代码

这两个程序基本相同，每个都有不同的提示，展示了两个不同的想法。从模型中获取 JSON 的关键部分是在提示或系统提示中声明它应该使用 JSON 响应，并在数据体中指定 format 为 json。

prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and  phone number. Do not use common names. Respond using JSON. Key names should with no backslashes, values should use plain ascii with no special characters."

data = {
    "prompt": prompt,
    "model": model,
    "format": "json",
    "stream": False,
    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
}

当运行 randomaddresses.py 时，您会看到模式根据选择的国家而改变和适应。

在 predefinedschema.py 中，也在提示中指定了模板。它被定义为 JSON 然后转储到提示字符串中，使其更易于使用。

两个示例都关闭了流式传输，这样我们就可以一次性得到完整的 JSON。我们需要将 response.text 转换为 JSON，这样当我们将其输出为字符串时，我们可以设置缩进间距，使输出易于阅读。

response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
json_data = json.loads(response.text)

print(json.dumps(json.loads(json_data["response"]), indent=2))

源码

predefinedschema.py

import requests
import json
import random

model = "llama2"
template = {
  "firstName": "",
  "lastName": "",
  "address": {
    "street": "",
    "city": "",
    "state": "",
    "zipCode": ""
  },
  "phoneNumber": ""
}

prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in the US, and  phone number. \nUse the following template: {json.dumps(template)}."

data = {
    "prompt": prompt,
    "model": model,
    "format": "json",
    "stream": False,
    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
}

print(f"Generating a sample user")
response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
json_data = json.loads(response.text)
print(json.dumps(json.loads(json_data["response"]), indent=2))

randomaddresses.py

import requests
import json
import random

countries = [
    "United States",
    "United Kingdom",
    "the Netherlands",
    "Germany",
    "Mexico",
    "Canada",
    "France",
]
country = random.choice(countries)
model = "llama2"

prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and phone number. Do not use common names. Respond using JSON. Key names should have no backslashes, values should use plain ascii with no special characters."

data = {
    "prompt": prompt,
    "model": model,
    "format": "json",
    "stream": False,
    "options": {"temperature": 2.5, "top_p": 0.99, "top_k": 100},
}

print(f"Generating a sample user in {country}")
response = requests.post("http://localhost:11434/api/generate", json=data, stream=False)
json_data = json.loads(response.text)

print(json.dumps(json.loads(json_data["response"]), indent=2))

仓库地址

python-json-datagenerator