wiki-ingest

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Personal Wiki — Ingest

个人Wiki — 导入处理

Process raw source documents into structured, interlinked wiki pages.

将原始源文档处理为结构化、相互关联的Wiki页面。

Identify Sources to Process

确定待处理的源文档

Determine which files need ingestion:

If the user specifies a file or files, use those
If the user says "process new sources", "ingest", or similar without specifying files — run batch detection:
- List all files in
```
raw/
```
  (excluding
```
raw/assets/
```
  )
- Read
```
wiki/log.md
```
  and extract all previously ingested source filenames from
```
ingest
```
  entries
- Any file in
```
raw/
```
  not listed in the log is unprocessed
- Show the user the list of unprocessed files found
If no unprocessed files are found, tell the user

确定需要导入的文件：

如果用户指定了某个或某些文件，使用这些文件
如果用户说“处理新源文档”“导入”或类似表述但未指定文件——执行批量检测：
- 列出
```
raw/
```
  目录下的所有文件（排除
```
raw/assets/
```
  ）
- 读取
```
wiki/log.md
```
  并从
```
ingest
```
  条目提取所有已导入的源文件名
- ```
raw/
```
  目录中未在日志里列出的文件即为未处理文件
- 向用户展示找到的未处理文件列表
如果未找到未处理文件，告知用户

Process Each Source

处理每个源文档

For each source file, process autonomously — read, create pages, and report results. No confirmation step between sources.

对每个源文档自主进行处理——读取内容、创建页面并报告结果。源文档之间无需确认步骤。

1. Read the source completely

1. 完整读取源文档

Read the entire file. If the file contains image references, note them — read the images separately if they contain important information.

For books: support both chapter-by-chapter and whole-book ingestion. When ingesting a chapter, create or update a parent book page in

wiki/sources/

that links to all chapter summaries. When ingesting a whole book, create a single comprehensive source page.

完整读取整个文件。如果文件包含图片引用，记录下来——如果图片包含重要信息，需单独读取图片内容。

对于书籍：支持按章节导入和整本书导入。导入单章节时，在

wiki/sources/

目录下创建或更新一个父级书籍页面，链接到所有章节摘要。导入整本书时，创建一个单一的综合源页面。

2. Create source summary page

2. 创建源文档摘要页面

Create a new file in

wiki/sources/

named after the source (slugified). Include:

---
tags: [relevant, tags]
sources: [original-filename.md]
created: YYYY-MM-DD
updated: YYYY-MM-DD
---

# Source Title

**Source:** original-filename.md
**Date ingested:** YYYY-MM-DD
**Type:** article | paper | transcript | notes | book | chapter | etc.

## Summary

Structured summary of the source content.

## Key Claims

- Claim 1
- Claim 2
- ...

## Entities Mentioned

- [[Entity Name]] — brief context
- ...

## Concepts Covered

- [[Concept Name]] — brief context
- ...

在

wiki/sources/

目录下创建一个以源文档名称（slug化）命名的新文件。内容包含：

---
tags: [relevant, tags]
sources: [original-filename.md]
created: YYYY-MM-DD
updated: YYYY-MM-DD
---

# 源文档标题

**来源：** original-filename.md
**导入日期：** YYYY-MM-DD
**类型：** 文章 | 论文 | 文字记录 | 笔记 | 书籍 | 章节 | 等

## 摘要

源文档内容的结构化摘要。

## 核心主张

- 主张1
- 主张2
- ...

## 提及的实体

- [[实体名称]] — 简要背景
- ...

## 涵盖的概念

- [[概念名称]] — 简要背景
- ...

3. Update entity and concept pages

3. 更新实体与概念页面

For each entity (person, organization, product, tool) and concept (idea, framework, theory, pattern) mentioned in the source:

If a wiki page already exists:

Read the existing page
Add new information from this source
Add the source to the
```
sources:
```
frontmatter list
Update the
```
updated:
```
date
Flag any contradictions with existing content using a callout block:

> [!warning] Contradiction
> Source A claims X, but Source B claims Y.
> Sources: [[Source A]], [[Source B]]

If no wiki page exists and the topic is substantive enough:

Create a new page in the appropriate subdirectory:
- ```
wiki/entities/
```
  for people, organizations, products, tools
- ```
wiki/concepts/
```
  for ideas, frameworks, theories, patterns
Include YAML frontmatter with tags, sources, created, and updated fields
Write a focused summary based on what this source says about the topic

If the topic is only mentioned in passing:

Use a
```
[[wikilink]]
```
without creating a page — the lint pass will flag frequently-mentioned-but-missing pages later

对于源文档中提及的每个实体（人物、组织、产品、工具）和概念（想法、框架、理论、模式）：

如果Wiki页面已存在：

读取现有页面
添加来自此源文档的新信息
将该源文档添加到
```
sources:
```
前置元数据列表中
更新
```
updated:
```
日期
使用提示框标记与现有内容的矛盾之处：

> [!warning] Contradiction
> Source A claims X, but Source B claims Y.
> Sources: [[Source A]], [[Source B]]

如果Wiki页面不存在且主题足够重要：

在合适的子目录中创建新页面：
- ```
wiki/entities/
```
  用于人物、组织、产品、工具
- ```
wiki/concepts/
```
  用于想法、框架、理论、模式
包含带有tags、sources、created和updated字段的YAML前置元数据
根据此源文档中关于该主题的内容撰写聚焦的摘要

如果主题只是被顺带提及：

使用
```
[[wikilink]]
```
语法但不创建页面——后续的检查步骤会标记频繁提及但缺失的页面

4. Add wikilinks

4. 添加Wiki链接

Ensure all related pages link to each other using

[[wikilink]]

syntax. Every mention of an entity or concept that has its own page should be linked.

确保所有相关页面使用

[[wikilink]]

语法相互链接。每个提及的实体或概念只要有对应的页面，都应添加链接。

5. Update wiki/index.md

5. 更新wiki/index.md

For each new page created, add an entry under the appropriate category header:

- [[Page Name]] — one-line summary (under 120 characters)

对于每个创建的新页面，在合适的分类标题下添加条目：

- [[页面名称]] — 一行摘要（不超过120字符）

6. Update wiki/log.md

6. 更新wiki/log.md

Append:

## [YYYY-MM-DD] ingest | Source Title
Processed source-filename.md. Created N new pages, updated M existing pages.
New entities: [[Entity1]], [[Entity2]]. New concepts: [[Concept1]].

追加内容：

## [YYYY-MM-DD] ingest | 源文档标题
处理了source-filename.md。创建了N个新页面，更新了M个现有页面。
新增实体：[[Entity1]], [[Entity2]]。新增概念：[[Concept1]]。

7. Report results

7. 报告处理结果

Tell the user what was done:

Pages created (with links)
Pages updated (with what changed)
New entities and concepts identified
Any contradictions found with existing content

When processing multiple sources (batch), report aggregate results at the end:

Total sources processed
Total pages created and updated
Summary of new entities and concepts across all sources

告知用户已完成的操作：

创建的页面（附带链接）
更新的页面（以及变更内容）
识别出的新实体和概念
发现的与现有内容的矛盾之处

当处理多个源文档（批量处理）时，在最后报告汇总结果：

处理的源文档总数
创建和更新的页面总数
所有源文档中新增实体和概念的汇总

Conventions

约定规则

Tags are organic — let them emerge naturally from content. Don't force a domain taxonomy. When a source spans multiple domains, tag with all relevant domains.
Source summary pages are factual only. Save interpretation and synthesis for concept and synthesis pages.
A single source typically touches 10-15 wiki pages. This is normal and expected.
When new information contradicts existing wiki content, add a
> [!warning] Contradiction
callout with both sources cited.
Prefer updating existing pages over creating new ones. Only create a new page when the topic is substantive enough to warrant it.
Use
```
[[wikilinks]]
```
for all internal references. Never use raw file paths.

标签是自然生成的——从内容中自然衍生，不要强行套用领域分类体系。当源文档涉及多个领域时，标记所有相关领域的标签。
源文档摘要页面仅包含事实内容。将解读和综合内容留到概念与综合页面中。
单个源文档通常会关联10-15个Wiki页面，这是正常且预期的情况。
当新信息与现有Wiki内容矛盾时，添加
> [!warning] Contradiction
提示框并引用两个来源。
优先更新现有页面而非创建新页面。仅当主题足够重要值得单独成页时才创建新页面。
所有内部引用使用
```
[[wikilinks]]
```
语法，绝不使用原始文件路径。

What's Next

后续操作

After ingesting sources, the user can:

Ask questions with
```
/wiki-query
```
to explore what was ingested
Ingest more sources — clip another article and run
```
/wiki-ingest
```
again
Health-check with
```
/wiki-lint
```
after every 10 ingests to catch gaps
Discover connections with
```
/wiki-explore
```
to find cross-domain patterns
Get inspired with
```
/wiki-spark
```
to generate creative prompts

导入源文档后，用户可以：

使用
```
/wiki-query
```
提问，探索已导入的内容
导入更多源文档——截取另一篇文章并再次运行
```
/wiki-ingest
```
每导入10次后使用
```
/wiki-lint
```
进行健康检查，排查内容缺口
使用
```
/wiki-explore
```
发现关联，找到跨领域的模式
使用
```
/wiki-spark
```
获取灵感，生成创意提示词