Skip to main content

一个轻量AI Agent框架,基于DeepSeek API

Project description

Oak DeepSeek

一个轻量的 AI Agent 框架,基于 DeepSeek API 构建。通过队列通信和多线程设计,快速构建支持工具调用、子 Agent 协作的智能体。

安装

pip install oak-deepseek

快速开始

下面是一个完整示例,展示如何创建两个 Agent(主 Agent 和子 Agent)并让它们协作计算数学表达式。

from queue import Queue
from threading import Thread
import os

from oak_deepseek.engine import AgentEngine

def add(a: int, b: int) -> str:
    """
    这个函数用于两个整数相加,并返回str结果给你
    :return: 加法结果
    """
    return f"{a + b}"

def mul(a: int, b: int) -> str:
    """
    这个函数用于两个整数相乘,并返回str结果给你
    :return: 乘法结果
    """
    return f"{a * b}"

engine: AgentEngine = AgentEngine()
engine.create_agent(
    key=("sys","sys"),
    description="一个能进行数学计算的agent",
    prompt="你是一个数学计算助手,会使用工具确保自己计算的正确性。",
    tools=[add],
    sub_agents=[("sys","sub")]
)

engine.create_agent(
    key=("sys","sub"),
    description="能进行乘法计算",
    prompt="你是一个数学计算助手,会使用工具确保自己计算的正确性",
    tools=[mul]
)
history_queue = Queue()

task_queue = Queue()
task_queue.put("计算(679+678)*(2+78)")

def go():
    engine.run(task_queue, key=("sys", "sys"), history_queue=history_queue, api_key=os.getenv("DEEPSEEK_API_KEY"))

def messages():
    while True:
        msg = history_queue.get(block=True)
        if msg is None:
            return
        print(msg)


if __name__ == "__main__":
    agent_thread = Thread(target=go)
    agent_thread.start()

    print_thread = Thread(target=messages)
    print_thread.start()

    agent_thread.join()
    history_queue.put(None)
    print_thread.join()

许可证

MIT license

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

oak_deepseek-0.1.1.tar.gz (13.2 kB view details)

Uploaded Source

Built Distribution

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

oak_deepseek-0.1.1-py3-none-any.whl (15.8 kB view details)

Uploaded Python 3

File details

Details for the file oak_deepseek-0.1.1.tar.gz.

File metadata

  • Download URL: oak_deepseek-0.1.1.tar.gz
  • Upload date:
  • Size: 13.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for oak_deepseek-0.1.1.tar.gz
Algorithm Hash digest
SHA256 0586fa1bacaa4676689b17c81d232ecae5e2ffa907345cd87a4b883b12837658
MD5 bad1f8e2cf88158e31b84e7d62caa9bc
BLAKE2b-256 da8c856be2da0e87aba21039f889a6e953e0bb13213e353670dba11a889a2199

See more details on using hashes here.

Provenance

The following attestation bundles were made for oak_deepseek-0.1.1.tar.gz:

Publisher: publish-to-pypi.yml on WyxGenius/oak-deepseek

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file oak_deepseek-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: oak_deepseek-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 15.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for oak_deepseek-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 922d7c97b621806af627572aa9262d126279b105d512a60fdff34cdf2db67fc5
MD5 efa96129d1cd0fb25206acf115ce936e
BLAKE2b-256 026c0d023c3a2ad02c8e215cc4aa10280c4b11da97fc4c7d22fcaa53537fbd6a

See more details on using hashes here.

Provenance

The following attestation bundles were made for oak_deepseek-0.1.1-py3-none-any.whl:

Publisher: publish-to-pypi.yml on WyxGenius/oak-deepseek

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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