Closed photosssa closed 7 months ago
I have also supported Task/Todo management in workspace (this is a new component), so issue should be part of the state of workspace~ I think we need to discuss how to merge the implementation of this part. Regarding the parse email problem you raised, I also did a similar operation in the agent._llm_read_article function, you can refer to it. My idea is to treat email as a specific artic, and use the self-learning Agent of workflow to complete regular learn. Instead of completely based on knowledge pipline~
We still need to continue to discuss.
P.S: We recommend using English first, please use English as a priority for the next PR
[Translated by GPT]
Issue Tree
The core mechanism is a tree-based issue management system. An issue should contain the following attributes:
The
knowledge
maintains an issue tree, starting from a root issue (the root can be abstract, such as the existence of an organization, not a specific one); theknowledge environment
provides an interface for maintaining this issue tree:Parse Email
Assuming we start from a certain date, scan new emails daily. For each email:
Potential Out of Token in Reasoning:
Build Issue Tree Based on Knowledge Pipeline
issue tree
最核心的机制是树状的issue管理,一个issue应当包含以下属性:
knowledge维护一个issue tree,从一个root issue出发(root可以是抽象的,比如一个组织的存在,并不是具体的);knowledge env 提供对这个issue tree的维护接口:
parse email
假定从从某个起始日期开始,以每天为单位,扫描当天新增的email,对每封email:
推理部分可能的out of token:
基于knowledge pipeline build issue tree