entari-plugin-hyw 3.4.0

Use large language models to interpret chat messages

Entari Plugin HYW

English | 简体中文

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).

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.

Features

• 📖 Agentic Workflow
  Autonomous decision-making process to search, browse, and reason.

• 🎑 Multi-Modal Support
  Native support for image analysis using Vision Language Models (VLMs).

• 🔍 Web Search & Crawling
  Integrated DuckDuckGo and Crawl4AI for real-time information retrieval.

• 🎨 Rich Rendering
  Responses are rendered as images containing Markdown, syntax-highlighted code, LaTeX math, and citation badges.

• 🔌 Protocol Support
  Deep integration with OneBot 11 and Satori protocols, handling reply context and JSON cards perfectly.

Installation

pip install entari-plugin-hyw

Configuration

Configure the plugin in your entari.yml.

Minimal Configuration

plugins:
  entari_plugin_hyw:
    model_name: google/gemini-3-flash-preview
    api_key: "your-or-api-key-here"

Usage

Commands

• Text Query

  /q What's the latest news on Rust 1.83?
  

• Image Analysis (Send an image with command, or reply to an image)

  /q [Image] Explain this error.
  

• Quote Query

  [quote: User Message] /q
  

• Follow-up Reply to the bot's message to continue the conversation.

Documentation for AI/LLMs

• Instruction Guide (English)
• 指导手册 (简体中文)

---

License

This project is licensed under the MIT License.