Skip to main content

No project description provided

Project description

MarkPrompt

MarkPrompt 是一个用于 LLM 的提示词模板引擎。

特性

  • YAML 元数据支持
  • 基于角色的内容块
  • 模板变量渲染
  • 安全检查机制
  • 工具调用功能(Function Calling)

安装

pip install -e .

使用

from markprompt.client import MarkPromptClient

client = MarkPromptClient("templates")
response = client.generate("example")

工具调用功能

MarkPrompt支持工具调用功能,允许你将Python函数作为工具传递给LLM,并自动执行被调用的函数。

示例

# 定义工具函数
def get_weather(city: str, date: str = "today"):
    """获取指定城市的天气信息"""
    # 实际功能实现
    return f"{city}{date}天气..."

# 使用工具
response = client.generate(
    "assistant", 
    prompt="北京今天天气怎么样?",
    tools=[get_weather]  # 传递工具函数列表
)

更详细的示例请查看 examples/tools_example.py

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

markprompt-0.1.3.tar.gz (36.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

markprompt-0.1.3-py3-none-any.whl (10.4 kB view details)

Uploaded Python 3

File details

Details for the file markprompt-0.1.3.tar.gz.

File metadata

  • Download URL: markprompt-0.1.3.tar.gz
  • Upload date:
  • Size: 36.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.5

File hashes

Hashes for markprompt-0.1.3.tar.gz
Algorithm Hash digest
SHA256 128d797c80d38d0b95df1cff54338551931fcca9dc176ead38c15f2ff3387eab
MD5 67ea69cdaf33d62b9b93885632c528a0
BLAKE2b-256 1ab862c32b5e7a1daefb4c6f37ee8e1a2dcc1959e90e5a121d830a83268b505f

See more details on using hashes here.

File details

Details for the file markprompt-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: markprompt-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 10.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.5

File hashes

Hashes for markprompt-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 f918d5e12e1dfdbc0ac72b91a2dc1e61e0baeaa6264147f2a51248401f75e848
MD5 aa2637dfdb2fe662717761809966a04b
BLAKE2b-256 3f5e100748edcf441363416713bca50336101eb92440e2388d148776ca52843f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page