Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PoC with LangChain wrapper and a webapp to chat with vector store #216

Open
wants to merge 9 commits into
base: main
Choose a base branch
from

Conversation

AlexZhangji
Copy link

@AlexZhangji AlexZhangji commented Mar 24, 2023

新的webapp demo! 稍微功能复杂些的版本.

  • 增加了一个实验版的ChatGLM LangChain wrapper. (用custom llm让ChatGLM能用在各类LangChain里)

  • 增加了一个用Streamlit写的vectorstore based Chat. (搜索和选取wiki article作为context来chat)

    • 用的数据是英文维基百科中, 所有与OpenAI wiki在两个链接之内的页面 (2 degree of separation)
    • 数据储存在FAISS
    • 整体偏proof of concept, 希望能作为一个有用的例子.

运行后如图
(提供两个模式, 正常聊天的 Chat 和 与wiki source聊天的 AI Wikipedia Agent)
vectorstore_chat

@AlexZhangji
Copy link
Author

chatglm_with_book

  • 增加了一个Chat with Books. (How to Avoid a Climate Disaster) 和与其对应的FAISS embeddings.
  • 针对LangChain的 VectorDB Chat进行了些针对中文的Prompt优化.

@YIZXIY
Copy link
Contributor

YIZXIY commented Mar 27, 2023

虽然可以联网了,这很好,但是我要是有买openaiapikey的钱也不至于用chatglm还得int4

@YIZXIY
Copy link
Contributor

YIZXIY commented Mar 27, 2023

后续可不可以出在百度 or bing这种不要key的上面检索

@imClumsyPanda
Copy link
Contributor

@zx2021 langchain是可以用huggingface model作embedding的

@l15y
Copy link

l15y commented Mar 28, 2023

@imClumsyPanda
Copy link
Contributor

@zx2021 需要基于全开源模型的实现可以看一下这个 imClumsyPanda/langchain-ChatGLM 受这个 pull request 启发搞出来的

@l15y
Copy link

l15y commented Mar 31, 2023

基于这个思路实现的平台:https://github.com/l15y/wenda
采用开源模型替代

@ZanoZ
Copy link

ZanoZ commented Mar 31, 2023

可以不可以爬一下github或者gitee,充实模型的代码能力,作为代码辅助工具可以更强?

@hardworkinglearningcodelong

很好

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants