[Large Model Knowledge Base] (4): Run the ChatGLM3 model of dity+fastchat in the local environment. You can use the chat/completions interface to call the chatglm3 model.

1. Video demonstration address

https://www.bilibili.com/video/BV18i4y1a78u/?vd_source=4b290247452adda4e56d84b659b0c8a2

[Large Model Knowledge Base] (4): Run the ChatGLM3 model of dity+fastchat in the local environment. You can use the chat/completions interface to call the chatglm3 model.

2. About dify

https://github.com/langgenius/dify/blob/main/README_CN.md

Dify is an LLM application development platform, and more than 100,000 applications have been built based on Dify.AI. It combines the concepts of Backend as Service and LLMOps, covering the core technology stack required to build generative AI native applications, including a built-in RAG engine. With Dify, you can self-deploy capabilities like Assistants API and GPTs based on any model.

3. Project startup script

Publish gitee code:
https://gitee.com/fly-llm/dify-docker-compose

4. Start successfully configuring the local model:

Then you can chat:

You can also quickly configure prompt words, then test them, and publish them directly after the test is completed:

5. Summary

dify is already a very complete product that can be quickly configured to develop a chat application.
It also supports configuring prompt words. Very convenient. There is also a knowledge base that can be configured and used.