Skip to content

(v0.1.0)【Party Invitation】The first release of comfyui_LLM_party！
Compare
Choose a tag to compare
@heshengtao heshengtao released this 05 May 02:45
· 1840 commits to main since this release
v0.1.0
0aa44ac
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.

✨v0.1.0✨【派对邀请】【Party Invitation】

This release includes the following features:

LLM

  1. Supports two modes of operation: API calls and local deployment
  2. Allows the LLM to be used as a tool attached to another larger model
  3. Supports the visual capabilities of GPT-4
  4. Can load word embedding models independently, or attach word embedding models as a tool to the LLM.

Tools

  1. Supports basic intelligent agent needs such as knowledge bases, code interpreters, and online queries
  2. Added practical tools for time, weather, Wikipedia, and academic paper queries
  3. Introduced a omnipotent interpreter tool that enables the LLM to perform any task by automatically installing the necessary libraries for the LLM-generated code in a virtual environment, essentially allowing any code-executable task to be performed automatically
  4. Added an API tool that allows the LLM to call user-defined APIs

Workflow

  1. Added start_dialog and end_dialog nodes, enabling workflows to create loopback links
  2. Added classify persona and classify function, allowing the workflow to execute different parts based on user input
  3. Introduced string logic nodes for quick construction of conditional judgments within workflows
  4. Added workflow transfer nodes that allow one workflow to be embedded within another, working in conjunction with string logic nodes to execute different large-scale workflows based on the LLM's output

Frontend Application

  1. Added the setup_streamlit_app.bat file for quick setup of your LLM workflow application

本次发行包含如下功能：

LLM

  1. 支持API调用和本地部署两种方式
  2. 可以将LLM也作为一个工具挂接到另一个大模型上
  3. 支持GPT4的视觉功能
  4. 可以单独加载词嵌入模型，也可以将词嵌入模型作为工具挂接到LLM上

工具

  1. 支持知识库、代码解释器、联网查询等基本智能体需求
  2. 新增了时间、天气、维基百科、论文查询等实用工具
  3. 新增了万能解释器工具，可以让LLM执行任何任务，原理是在一个虚拟环境中自动安装LLM生成代码所需的库，相当于只要是代码可以执行的任务都可以自动执行
  4. 新增了API工具，可以让LLM调用用户自定义API

工作流

  1. 新增了start_dialog和end_dialog节点，可以让工作流实现回环链接
  2. 新增了分类器面具和分类器函数，可以让工作流根据用户的输入，执行不同的部分
  3. 新增了字符串逻辑节点，可以快速构建工作流中的条件判断
  4. 新增了工作流中转器节点，可以将一个工作流嵌入另一个工作流，配合字符串逻辑节点，根据LLM的输出来执行不同的大型工作流

前端应用

  1. 新增了setup_streamlit_app.bat文件，用于快速搭建你的LLM工作流应用
Assets 2
Loading
0 Join discussion