✨v0.4.0✨【书香茶话】【Bookish Tea Talk】

This release includes the following features:

1. Added a text iterator that outputs a portion of characters each time, safely splitting the text based on newline characters and chunk size without splitting in the middle of a text. chunk_overlap refers to how many characters overlap in the split text. This allows for batch input of long texts; just click mindlessly or enable loop execution in ComfyUI, and it will automatically execute. Remember to enable the is_locked attribute to automatically lock the workflow at the end of the input, preventing further execution. Example workflow: Text Iterative Input
2. Added the model name attribute to the local LLM loader, local llava loader, and local guff loader. If empty, it uses the various local paths in the node. If not empty, it will use the path parameters you filled in config.ini. If not empty and not in config.ini, it will download from Hugging Face or load from the Hugging Face model save directory. If you want to download from Hugging Face, please fill in the model name attribute in the format like THUDM/glm-4-9b-chat. Note! The model loaded this way must be compatible with the transformer library.
3. Adapted CosyVoice, now you can use TTS functionality without downloading any models or API keys. Currently, this interface only supports Chinese.
4. Added JSON file parsing node and JSON value extraction node, allowing you to get the value of a key from a file or text. Thanks to guobalove for the contribution!
5. Improved the tool invocation code, now LLMs without tool invocation functionality can also enable the is_tools_in_sys_prompt attribute (local LLMs do not need to enable it by default, automatically adapted). After enabling, tool information will be added to the system prompt, allowing LLM to call tools. Related paper on the implementation principle: Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning
6. Created a custom_tool folder for storing custom tool code. You can refer to the code in the custom_tool folder, place the custom tool code in the custom_tool folder, and then call the custom tool in LLM.
7. Added a knowledge graph tool, allowing LLM to interact perfectly with the knowledge graph. LLM can modify the knowledge graph based on your input and reason on the knowledge graph to get the answers you need. Example workflow reference: graphRAG_neo4j
8. Added the functionality to connect agents to Discord. (Still in testing)
9. Added the functionality to connect agents to Feishu, thanks a lot to guobalove for the contribution! Reference workflow Feishu Bot.
10. Added a universal API call node and many auxiliary nodes for constructing request bodies and capturing information from responses.
11. Added a model clearing node, allowing you to unload LLM from memory at any position!
12. Added the chatTTS node, thanks a lot to guobalove for the contribution! The model_path parameter can be empty! It is recommended to use the HF mode to load the model, which will automatically download from Hugging Face without manual download; if using local loading, please place the model's asset and config folders in the root directory. Baidu Cloud Address, extraction code: qyhu; if using custom mode loading, please place the model's asset and config folders in the model_path.

本次发行包含如下功能：

1. 新增了一个文本迭代器，可以每次只输出一部分的字符，是根据回车符号和chunk size来安全分割文本的，不会从文本中间分割。chunk_overlap是指分割的文本重叠多少字符。这样可以批量输入超长文本，只要无脑点击，或者开启comfyui里的循环执行就行了，就可以自动执行完了。记得开启is_locked属性，可以在输入结束时，自动锁住工作流，不会继续执行。示例工作流：文本迭代输入
2. 在本地LLM加载器、本地llava加载器、本地guff加载器上添加了model name属性，如果为空，则使用节点中的各类本地path加载。如果不为空，则会使用config.ini中你自己填写的路径参数加载。如果不为空且不在config.ini中，则会从huggingface上下载或则从huggingface的模型保存目录中加载。如果你想从huggingface上下载，请按照例如：THUDM/glm-4-9b-chat的格式填写model name属性。注意！这样子加载的模型必须适配transformer库。
3. 适配了CosyVoice，现在可以无需下载任何模型或者任何API key，直接使用TTS功能。目前该接口只适配了中文。
4. 新增了JSON文件解析节点和JSON取值节点，可以让你从文件或者文本中获取某一个键的值。感谢guobalove的贡献！
5. 改进了工具调用的代码，现在没有工具调用功能的LLM也可以开启is_tools_in_sys_prompt属性（本地LLM默认无需开启，自动适配），开启之后，工具信息会添加到系统提示词中，这样LLM就可以调用工具了。实现原理的相关论文：Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning
6. 新建了custom_tool文件夹，用于存放自定义工具的代码，可以参考custom_tool文件夹中的代码，将自定义工具的代码放入custom_tool文件夹中，即可在LLM中调用自定义工具。
7. 新增了知识图谱工具，让LLM与知识图谱可以完美交互，LLM可以根据你的输入修改知识图谱，可以在知识图谱上推理以获取你需要的答案。示例工作流参考：graphRAG_neo4j
8. 新增将智能体接入discord的功能。(还在测试中)
9. 新增将智能体接入飞书的功能，超级感谢guobalove的贡献！参考工作流
   飞书机器人。
10. 新增了万能API调用节点以及大量的辅助节点，用于构造请求体和抓取响应中的信息。
11. 新增了清空模型节点，可以在任意位置将LLM从显存中卸载！
12. 已添加了chatTTS节点，超级感谢guobalove的贡献！model_path参数可以为空！推荐使用HF模式加载模型，模型会自动从hugging face上下载，无需手动下载；如果使用local加载，请将模型的asset和config文件夹放到根目录下。百度云地址，提取码：qyhu；如果使用custom模式加载，请将模型的asset和config文件夹放到model_path下。

✨v0.3.0✨

This release includes the following features:

1. Added Knowledge Graph tool, so that LLM and Knowledge Graph can interact perfectly. LLM can modify Knowledge Graph according to your input, and can reason on Knowledge Graph to get the answers you need. Example workflow reference: Knowledge_Graph
2. Added personality AI function, 0 code to develop your own girlfriend AI or boyfriend AI, unlimited dialogue, permanent memory, stable personality. Example workflow reference: Mylover Personality AI
3. You can build your own interactive novel game, and go to different endings according to the user's choice! Example workflow reference: interactive_novel
4. Adapted to OpenAI's whisper and tts functions, voice input and output can be realized. Example workflow reference: voice_input&voice_output
5. Compatible with Omost!!! Please download omost-llama-3-8b-4bits to experience it now! Sample workflow reference: start_with_OMOST
6. Added LLM tools to send messages to WeCom, DingTalk, and Feishu, as well as external functions to call.

本次发行包含如下功能：

1. 新增了知识图谱工具，让LLM与知识图谱可以完美交互，LLM可以根据你的输入修改知识图谱，可以在知识图谱上推理以获取你需要的答案。示例工作流参考：知识图谱
2. 新增了人格AI功能，0代码开发自己的女友AI或男友AI，无限对话，永久记忆，人设稳定。示例工作流参考：麦洛薇人格AI
3. 可以搭建自己的互动小说游戏了，根据用户的选择，走向不同的结局！示例工作流参考：互动小说
4. 适配了openai的whisper和tts功能，可以实现语音输入和输出。示例工作流参考：语音输入+语音输出
5. 兼容Omost啦！！！请下载omost-llama-3-8b-4bits立即体验吧！示例工作流参考：start_with_OMOST
6. 新增了将消息发送到企业微信、钉钉和飞书的LLM工具以及可供调用的外部函数。

✨v0.2.0✨

This release includes the following features:

LLM

1. The LLM node has been split, separating the LLM loader and the LLM model chain for more flexible reuse of these models.
2. Adapted all models with an interface similar to OpenAI, such as: Tongyi Qianwen/qwen, Zhipu Qingyan/GLM, deepseek, kimi/moonshot. Please fill in the base_url, api_key, and model_name of these models into the LLM node to call them.
3. Added a new LVM loader, now you can call LVM models locally, supporting the llava-llama-3-8b-v1_1-gguf model. Other LVM models, if in GUFF format, should theoretically also be runnable.
4. MacOS and mps devices are now supported! Thanks to bigcat88 for their contribution!

Tools

1. Added Wikipedia tool, web summary tool, and arXiv paper tool.
2. Another workflow can now be used as a tool. However, this version is not yet perfected and is just barely usable.

Workflow

1. Wrote a fastapi.py file, if you run it directly, you will get an OpenAI interface at http://127.0.0.1:8817/v1/, any application that can call GPT can now use your comfyui workflow! I will produce a tutorial to demonstrate how to operate it in detail~
2. Wrote an Excel iterator, which can output your CSV table row by row to the next node.

本次发行包含如下功能：

LLM

1. 拆分了LLM节点，将LLM的加载器和LLM模型链拆分，方便更灵活的复用这些模型。
2. 适配了所有具有类似openai接口的模型，例如：通义千问/qwen、智谱清言/GLM、deepseek、kimi/moonshot。请将这些模型的base_url、api_key、model_name填入LLM节点以调用它们。
3. 新增了一个LVM加载器，现在可以本地调用LVM模型了，支持llava-llama-3-8b-v1_1-gguf模型，其他LVM模型如果是GUFF格式，理论上应该也可以运行。
4. 目前已经支持了macOS以及mps设备!感谢bigcat88对此的贡献！

工具

1. 新增了维基百科工具、网页总结工具、arxiv论文工具。
2. 可以将另一个工作流作为一个工具使用。不过目前这个版本还没有完善，只是勉强能用。

工作流

1. 写了一个fastapi.py文件，如果你直接运行它，你就获得了一个http://127.0.0.1:8817/v1/上的openai接口，任何可以调用GPT的应用都可以调用你的comfyui工作流了！详细怎么操作我会出一期教程来演示~
2. 写了一个Excel迭代器，可以将你的csv表格按行输出到下一个节点。

✨v0.1.0✨

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