ReMe/reme2/config/obsidian.md
jinli.yl 42a3343cb5 feat(core): add core components and application framework
- Introduce Application class for managing application lifecycle
- Add base component classes for LLM formatters and token counters
- Implement embedding model base with caching and batching support
- Create file watcher base with watchfiles integration
- Add job and step base components for workflow execution
- Update base component with async locks and improved lifecycle management
- Register new component types in component registry
- Add application context and runtime context for dependency injection
2026-04-23 16:25:31 +08:00

89 lines
1.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# all @jinli
reme help
reme start
reme restart
reme version
reme vault="My Vault"
# daily
daily:path
reme daily:xxx
# crud
reme create file="New Note" content="# Hello" title="xxx" tags="[]" status=""
reme read file=Recipe/path="Templates/Recipe.md"
reme edit file=Recipe/path="Templates/Recipe.md" old="xxx" new="xxx"
reme append file="My Note" content="New line"
reme prepend file="My Note" content="New line"
reme delete file="My Note"/path
# reme
reme stat file/path
reme list file/path
# search
reme search query="search term" limit=10 tag="[]" score=0.1 copy=true
# property
reme property:read
reme property:update file="My Note" status=done xx=xxx
reme property:delete keys="[xxxx, xxxx]"
# 全局所有标签
reme tags
# show link
reme backlinks file="My Note"
reme links file="My Note"
[[Algorithm Notes#Sorting]]
记忆的类型
1. daily -> daily/xxxx-mm-dd/overview.md -> xxxx.md
2. topic -> topic/personal(agent)/xxxx.md
记忆的被动总结
1. 是否需要:是需要,不会主动触发
2. 什么时候调用:
- freq (every_n_turn、compact) -> daily_summarizer
- topic (/dream ) -> topic_summarizer(daily_xx -> topic_xx)
- proactive -> proactive_summarizer(personal_xxx -> proactive_query)
- pre_query
记忆的搜索
file watch
- start 全量扫描 -> 文件变化结果
- 增量扫描 -> 文件变化结果
如果有变化,检测 增加、删除、修改 cud
1. file -> metadata 存json
- path
- mtime
- header: tags/kv/title/desc
2. file -> link 存json
- 读全量修改的文件的全量识别link
3. file -> chunk 存db/json
- 切片 -> file+start+end: preview(100)