Skip to main content

Use large language models to interpret chat messages

Project description

Entari Plugin HYW

Entari 智能聊天解释插件

License PyPI Python

IM 环境下的 LLM 智能解释方案

v3.2迎来大幅度改动、现在图文不符

🎑 效果展示

Chat Demo

✨ 功能特性

  • 关于搜索:一次性触发 Bing 网页与图片搜索,组合结果后再回应。
  • 给予 AlconnaMessageChain 混合处理, 深度优化触发体验。
  • 网页获取:使用 Playwright 进行实时页面获取。
  • 多模态理解:支持图片视觉分析。
  • 上下文感知:维护对话历史记录,支持连续的多轮对话。
  • reaction 表情, 表示任务开始。
  • OneBot 优化:针对 OneBot 11 协议深度优化,支持解析 JSON 卡片、引用消息等特殊元素。

📦 安装

基础安装

pip install entari-plugin-hyw

搜索

默认通过 HTTP 请求搜索引擎(DuckDuckGo,可在配置中自定义完整搜索链接,如 https://duckduckgo.com/?q={query})。

⚙️ 配置

请在 entari.yml 中添加以下配置:

plugins:
  entari_plugin_hyw:
    # --- 基础设置 ---
    # 触发机器人的命令列表
    command_name_list: ["zssm", "hyw"]
    
    # 主 LLM 模型配置(必需), 如 x-ai/grok-4.1-fast:online、perplexity/sonar
    model_name: "gx-ai/grok-4.1-fast:free"
    api_key: "your-api-key"

    # 默认 https://openrouter.ai/api/v1
    base_url: "openai-compatible-url"  
    
    # --- 浏览器与搜索 ---
    headless: true
    
    # --- 视觉配置 (可选) ---
    # 如果未设置,将回退使用主模型
    vision_model_name: "qwen-vl-plus"
    vision_api_key: "your-vision-api-key"
    vision_base_url: "your-vision_base_url"
    
    # --- openai extra_body ---
    extra_body:
      reasoning:
        effort: low
    
    # --- 交互体验 ---
    # 是否开启表情反应 (默认: true)
    reaction: true

    # --- 调试 ---
    save_conversation: false

📖 使用方法

基础指令

使用配置的命令前缀与机器人交互:

hyw 最近LLM有啥新闻, 是不是claude又被秒了
hyw [图片消息] 里面这人写代码怎么我一句都看不懂
hyw https://koishi.chat/ 怎么安装
[回复消息] hyw 
[回复消息<[图片消息]>] hyw -t
[回复消息] hyw 补充: 这个rf的意思是github用户RF-Tar-Railt
[回复消息(hyw插件的输出)] /1 详细点描述
[回复消息(hyw插件的输出>] /那谁有多余解释器?

选项参数

  • -t / --text: 强制纯文本模式(跳过图片分析,节省 Token 或时间)。
hyw -t 一大段话。

引用回复

支持引用消息进行追问,机器人会自动读取被引用的消息作为上下文:

  • 引用 + 命令:机器人将理解被引用消息的内容(包括图片)通过 MessageChain 操作拼接 TextImage 与部分 Custom

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-3.2.108.tar.gz (270.1 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-3.2.108-py3-none-any.whl (280.2 kB view details)

Uploaded Python 3

File details

Details for the file entari_plugin_hyw-3.2.108.tar.gz.

File metadata

  • Download URL: entari_plugin_hyw-3.2.108.tar.gz
  • Upload date:
  • Size: 270.1 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-3.2.108.tar.gz
Algorithm Hash digest
SHA256 4aa813d3bec61884b979f89674b7d4576d361cc9bb81f28db34546e3e91e5775
MD5 685b40702991324a9f7b7d774e8d9a23
BLAKE2b-256 12d58ef2fe655e840c3f4d8360bdd3a5b94d5eb74d1a269fb28dc61c2c378671

See more details on using hashes here.

Provenance

The following attestation bundles were made for entari_plugin_hyw-3.2.108.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-3.2.108-py3-none-any.whl.

File metadata

File hashes

Hashes for entari_plugin_hyw-3.2.108-py3-none-any.whl
Algorithm Hash digest
SHA256 e5d2c3f68dbe633bcab17004dc7888c5368e246701f78aea6da746144d5ce296
MD5 6694ff953f15f8537e33d140cb4bcc2e
BLAKE2b-256 61d583fb136bf07b58c81cbf9a5adc9c3305dfdc95308407fc97862f01324019

See more details on using hashes here.

Provenance

The following attestation bundles were made for entari_plugin_hyw-3.2.108-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