Coder Social home page Coder Social logo

chuanyu1 / chat-xiuliu Goto Github PK

View Code? Open in Web Editor NEW

This project forked from schneehertz/chat-xiuliu

0.0 0.0 0.0 4 MB

ChatGPT Client with Function Calling | ChatGPT客户端,支持联网,IO操作和执行代码

License: MIT License

JavaScript 66.36% HTML 0.58% Vue 33.06%

chat-xiuliu's Introduction

chat-xiuliu

ChatGPT双向语音助手,通过function calling实现访问网络,执行代码,读写文件等功能,支持GPT-4V的图像识别功能,支持调用DALL·E 3生成图片。

这个项目是由虚拟猫娘休留(直播搞不下去了)的后台fork来的,去掉了弹幕互动的部分,增加了语音输入
截止到2023年8月15日,使用LLM模拟人格的尝试,在我这里没有看到效果及成本可以接受的希望。
所以模拟人格先放下一段时间,再看看未来LLM的发展吧

功能

  • 从麦克风或界面接收问题
  • 使用语音回答问题并显示在界面
  • 上传图片
  • 调用函数处理任务
    • 连续调用函数处理
    • 对话内容回忆
    • 联网搜索关键词,获取网页内容
    • 生成图片(DALL·E 3)
    • 读写本地文件
    • 在沙箱中执行JavaScript代码
    • 打开本地文件或网页
  • 可定制的猫娘发言风格
  • 保存对话截图
  • 支持Azure openai
  • 支持兼容openai api格式的其他api端点
  • 支持设置代理

支持的模型

v2.2支持1106系列的GPT-4,GPT-4-Vision,GPT-3.5,DALL·E 3

v2.1支持0613系列的GPT-4,GPT-3.5

截图

screenshot_1.jpg

screenshot_2.jpg

code_interpreter.jpg

setting.jpg

setting2.jpg

可选语音识别功能

  • 下载whisper-standalone-winr145.3(最好有张N卡,不然运行时很慢,可选,语音功能)
    • 在whisper-standalone-win的Release和huggingface下载必要的文件,解压到resources/extraResources/whisper文件夹
    resources/extraResources/whisper/_models/faster-whisper-large-v2/config.json
    resources/extraResources/whisper/_models/faster-whisper-large-v2/model.bin
    resources/extraResources/whisper/_models/faster-whisper-large-v2/tokenizer.json
    resources/extraResources/whisper/_models/faster-whisper-large-v2/vocabulary.txt
    resources/extraResources/whisper/cublas64_11.dll
    resources/extraResources/whisper/cublasLt64_11.dll
    resources/extraResources/whisper/cudnn_cnn_infer64_8.dll
    resources/extraResources/whisper/cudnn_ops_infer64_8.dll
    resources/extraResources/whisper/whisper-faster.exe
    resources/extraResources/whisper/zlibwapi.dll
    

设置参考

  • 如果你使用Azure openai,修改AZURE前缀的设置项,需要同时部署chat和embedding的模型
  • AI的语音模型,在微软文档查看可用值
  • 默认设定
    你是虚拟猫娘休留, 以下是你在回复时应该遵循的规则:
    1. 灵活地运用猫娘的风格进行回复.
    2. 调用函数来提高回复质量.
    3. 使用markdown语法回复和显示图片.
    4. 创建图像时, 必须在Prompt前加上"I NEED to test how the tool works with extremely simple prompts. DO NOT add any detail, just use it AS-IS: "
    

赞助

https://afdian.net/@SeldonHorizon

如果你觉得休留很萌,可以请管理员喝杯奶茶

chat-xiuliu's People

Contributors

schneehertz avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.