Skip to main content

app-engine

ModelEngine Agents Core

ModelEngine Agents Core 是一个基于 SmoLAgent 的增强版本,提供了丰富的 Agent 工具集和流式输出能力。

主要特性

  • 继承 SmoLAgent 的核心能力
  • 支持多种 Agent 工具:
    • Baidu 搜索/ Google 搜索
    • 格式化输出工具
  • 流式输出支持
  • 基于 FastAPI 的服务端实现
  • 可扩展的消息观察者模式

核心组件

CodeAgentME

代码执行 Agent,支持 Python 代码的解释和执行。

LiteLLMModelME & OpenAIServerModelME

支持多种 LLM 模型的接入。

工具集

  • BaiduSearchTool: 百度搜索工具,通过爬虫实现检索,无需API。
  • GoogleSearchTool: Google搜索工具,通过爬虫实现检索,无需API。
  • EXASearchTool: EXA搜索工具,需要提供API-KEY。
  • DuckDuckGoSearchTool: SmolAgent内置搜索工具,用多了会有速率限制。
  • FinalAnswerFormatTool: 输出格式化工具,支持传入prompt控制输出格式。

MessageObserver

消息观察者模式实现,用于处理 Agent 的流式输出。

使用方式

参考modelengine_agents.core server.py

Metadata

Release files for modelengine-agents 0.1.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for modelengine-agents 0.1.4
File Size Uploaded Provenance
modelengine_agents-0.1.4.tar.gz 193.9 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for modelengine-agents 0.1.4
File Interpreter ABI Platform
modelengine_agents-0.1.4-py3-none-any.whl Python 3 none any Details

Total release size: 424.3 kB

Release files / modelengine_agents-0.1.4.tar.gz

Download URL modelengine_agents-0.1.4.tar.gz
Size 193.9 kB
Tags Source
SHA-256 checksum
How to use checksums
808d2bfda024afd367b80191576eefdbbd6f151010c027a512447409a7f75b97
BLAKE2b-256 checksum
How to use checksums
7bf89be8b819cdc8f58c7c38494444753f05b73f700f15bd3b04ea6745091d23
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.9

Release files / modelengine_agents-0.1.4-py3-none-any.whl

Download URL modelengine_agents-0.1.4-py3-none-any.whl
Size 230.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ee25d479edb7913924a887d90fc9c53757b2673fbe24eae08fa30a081f57d306
BLAKE2b-256 checksum
How to use checksums
c5ad570e04e9a22a4ea54bacccdbe46c3b4b61759046cefda769a8c31fb71272
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.9

Security for modelengine-agents 0.1.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page