Skip to main content

Use large language models to interpret chat messages

Project description

Entari Plugin HYW

PyPI version License: MIT Python Versions

Entari Plugin HYW is an advanced agentic chat plugin for the Entari framework. It leverages Large Language Models (LLMs) to provide intelligent, context-aware, and multi-modal responses within instant messaging environments (OneBot 11, Satori).

Entari Plugin HYW 是 Entari 框架的高级智能体聊天插件。它利用大语言模型(LLM)在即时通讯环境(OneBot 11, Satori)中提供智能、上下文感知和多模态的回复体验。

The plugin implements a three-stage pipeline (Vision, Instruct, Agent) to autonomously decide when to search the web, crawl pages, or analyze images to answer user queries effectively.

插件实现了三阶段流水线(视觉指令代理),能够自主决定何时搜索网络、抓取网页或分析图片,从而高效地回答用户问题。

Features / 功能特性

  • 📖 Agentic Workflow (智能工作流)
    Autonomous decision-making process to search, browse, and reason.
    具备自主决策能力,能够自动进行搜索、网页浏览和逻辑推理。

  • 🎑 Multi-Modal Support (多模态支持)
    Native support for image analysis using Vision Language Models (VLMs).
    原生支持图片分析,利用视觉语言模型(VLM)理解图像内容。

  • 🔍 Web Search & Crawling (搜索与抓取)
    Integrated DuckDuckGo and Crawl4AI for real-time information retrieval.
    集成 DuckDuckGo 搜索与 Crawl4AI 网页抓取,实时获取互联网信息。

  • 🎨 Rich Rendering (富媒体渲染)
    Responses are rendered as images containing Markdown, syntax-highlighted code, LaTeX math, and citation badges.
    回答将渲染为包含 Markdown、代码高亮、LaTeX 公式及引用角标的精美图片。

  • 🔌 Protocol Support (多协议适配)
    Deep integration with OneBot 11 and Satori protocols.
    深度适配 OneBot 11 和 Satori 协议,完美处理回复上下文与 JSON 卡片。

Installation / 安装

pip install entari-plugin-hyw

Configuration / 配置

Configure the plugin in your entari.yml.
entari.yml 中进行配置。

Minimal Configuration / 最小配置

plugins:
  entari_plugin_hyw:
    # Trigger command / 触发指令
    question_command: ".q"
    
    # Main Model (Required) / 主模型(必需)
    model_name: "google/gemini-2.0-flash-exp"
    api_key: "your-api-key-here"
    base_url: "https://generativelanguage.googleapis.com/v1beta/openai/"

Configuration Reference / 配置详解

Option (选项) Type Default Description (说明)
Basic
question_command str /q The command to trigger the bot.
触发机器人的指令前缀。
reaction bool true React with emoji on start(now only lagrange ob extension).
收到指令时是否回应表情(目前只支持拉格兰ob扩展)。
quote bool true Quote the user's message in reply.
回复时是否引用原消息。
Models
model_name str None Required. Main Agent model ID.
必需。 主代理模型 ID。
api_key str None Required. API key.
必需。 API 密钥。
base_url str ... OpenAI-compatible API base URL.
兼容 OpenAI 的 API 地址。
extra_body dict null Extra parameters (e.g. reasoning_effort).
传递给 LLM 的额外参数。
Specialized
vision_model_name str None Model for images. Defaults to model_name.
处理图片的模型,默认同主模型。
intruct_model_name str None Model for intent. Defaults to model_name.
意图识别模型,默认同主模型。
Tools
search_provider str ddgs ddgs (DuckDuckGo), crawl4ai, httpx.
搜索后端提供商。
search_limit int 8 Max search results.
搜索结果数量限制。
headless bool true Browser headless mode.
浏览器无头模式。

Usage / 使用方法

Commands / 指令

  • Text Query (文本问答)

    .q What's the latest news on Rust 1.83?
    .q Rust 1.83 有什么新特性?
    
  • Image Analysis (图片分析) (Send an image with command, or reply to an image)
    (发送带图片的指令,或回复一张图片)

    .q [Image] Explain this error.
    .q [图片] 解释一下这个报错。
    
  • Follow-up (追问) Reply to the bot's message to continue the conversation.
    直接回复机器人的消息即可进行连续对话。


License

This project is licensed under the MIT License.

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

entari_plugin_hyw-3.3.7.tar.gz (263.2 kB view details)

Uploaded Source

Built Distribution

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

entari_plugin_hyw-3.3.7-py3-none-any.whl (269.8 kB view details)

Uploaded Python 3

File details

Details for the file entari_plugin_hyw-3.3.7.tar.gz.

File metadata

  • Download URL: entari_plugin_hyw-3.3.7.tar.gz
  • Upload date:
  • Size: 263.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for entari_plugin_hyw-3.3.7.tar.gz
Algorithm Hash digest
SHA256 884b8728beb451c9a411099c9d72292a3f871aaa502248a06ead20715a0cb122
MD5 34e8a9f87d74a5f5f82c97c4386b7d48
BLAKE2b-256 afe4926b442c9ce4706292a2928c8129086a7f08ab891759c28cadc528ca3be1

See more details on using hashes here.

Provenance

The following attestation bundles were made for entari_plugin_hyw-3.3.7.tar.gz:

Publisher: publish.yml on kumoSleeping/entari-plugin-hyw

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

File details

Details for the file entari_plugin_hyw-3.3.7-py3-none-any.whl.

File metadata

File hashes

Hashes for entari_plugin_hyw-3.3.7-py3-none-any.whl
Algorithm Hash digest
SHA256 b9901f2171ea0895a27b240828a2d00dac573862a2d806ce1c5a1fe3a04e4761
MD5 bd76905fed589f1c426793ef9874570e
BLAKE2b-256 9c627d72f1859943b87ccab358921f7172d71da7972d82e6a5ad9043fdabb709

See more details on using hashes here.

Provenance

The following attestation bundles were made for entari_plugin_hyw-3.3.7-py3-none-any.whl:

Publisher: publish.yml on kumoSleeping/entari-plugin-hyw

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