Skip to content

Commit ddbd10e

Browse files
authored
Merge pull request #111 from VectifyAI/fix-readme-3
update readme
2 parents ca25115 + f8e6935 commit ddbd10e

1 file changed

Lines changed: 28 additions & 14 deletions

File tree

README.md

Lines changed: 28 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -26,13 +26,13 @@ OpenKB has two layers: a **wiki foundation** that compiles and maintains your kn
2626

2727
### Features
2828

29-
- **Broad format support** PDF, Word, Markdown, PowerPoint, HTML, Excel, CSV, text, URLs, and more
30-
- **Scale to long documents** Long and complex documents are handled via [PageIndex](https://github.com/VectifyAI/PageIndex) tree indexing, enabling accurate, vectorless context-aware retrieval
31-
- **Native multi-modality** Retrieves and understands figures, tables, and images, not just text
32-
- **Compiled Wiki** LLM compiles your documents into summaries, concept pages, entity pages, and cross-links, all kept in sync
33-
- **Query & Chat** One-off questions or multi-turn conversations over your wiki, with persisted sessions you can resume
34-
- **Skill Factory** Distill redistributable agent skills from your wiki
35-
- **Obsidian compatible** Wiki is plain `.md` files with `[[wikilinks]]`. Open in Obsidian for graph view and browsing
29+
- **Broad format support:** PDF, Word, Markdown, PowerPoint, HTML, Excel, CSV, text, URLs, and more
30+
- **Scale to long documents:** Long and complex documents are handled via [PageIndex](https://github.com/VectifyAI/PageIndex) tree indexing, enabling accurate, vectorless context-aware retrieval
31+
- **Native multi-modality:** Retrieves and understands figures, tables, and images, not just text
32+
- **Compiled Wiki:** LLM compiles your documents into summaries, concept pages, entity pages, and cross-links, all kept in sync
33+
- **Query & Chat:** One-off questions or multi-turn conversations over your wiki, with persisted sessions you can resume
34+
- **Skill Factory:** Distill redistributable agent skills from your wiki
35+
- **Obsidian compatible:** Wiki is plain `.md` files with `[[wikilinks]]`. Open in Obsidian for graph view and browsing
3636

3737
# 🚀 Getting Started
3838

@@ -43,7 +43,7 @@ pip install openkb
4343
```
4444

4545
<details>
46-
<summary><i>Other install options:</i></summary>
46+
<summary><b><i>Other install options:</i></b></summary>
4747

4848
- **Latest from GitHub:**
4949

@@ -170,6 +170,7 @@ OpenKB commands fall into two layers: the **wiki foundation** (compile + manage
170170

171171
<details>
172172
<summary><b><i>More wiki commands:</i></b></summary>
173+
<br>
173174

174175
| Command | Description |
175176
|---|---|
@@ -190,10 +191,11 @@ A "generator" reads from the compiled wiki and produces something usable: an ans
190191
| <code>openkb&nbsp;query&nbsp;"question"</code> | A grounded answer with citations (use `--save` to persist to `wiki/explorations/`) |
191192
| <code>openkb&nbsp;chat</code> | Interactive multi-turn session over the wiki (use `--resume`, `--list`, `--delete` to manage sessions) |
192193
| | |
193-
| <code>openkb&nbsp;skill&nbsp;new&nbsp;&lt;name&gt;&nbsp;"&lt;intent&gt;"</code> | A redistributable agent skill — see [Skill Factory](#-skill-factory--drop-in-a-book-out-comes-a-digital-expert) below |
194+
| <code>openkb&nbsp;skill&nbsp;new&nbsp;&lt;skill-name&gt;&nbsp;"&lt;intent&gt;"</code> | Distill a redistributable agent skill from your wiki — see [Skill Factory](#-skill-factory--drop-in-a-book-out-comes-a-digital-expert) below |
194195

195196
<details>
196197
<summary><b><i>More skill commands:</i></b></summary>
198+
<br>
197199

198200
| Command | Output |
199201
|---|---|
@@ -221,19 +223,22 @@ Inside a chat, type `/` to access slash commands (Tab to complete).
221223

222224
<details>
223225
<summary><i>Slash commands:</i></summary>
226+
<br>
224227

225228
- `/help` — list available commands
226229
- `/status` — show knowledge base status
227230
- `/list` — list all documents
228231
- `/add <path>` — add a document or directory without leaving the chat
229-
- `/skill new <name> "<intent>"` — compile a skill from this chat (see below)
232+
- `/skill new <skill-name> "<intent>"` — compile a skill from this chat (see below)
230233
- `/save [name]` — export the transcript to `wiki/explorations/`
231234
- `/clear` — start a fresh session (the current one stays on disk)
232235
- `/lint` — run knowledge base lint
233236
- `/exit` — exit (Ctrl-D also works)
234237

235238
</details>
236239

240+
<a id="skill-factory"></a>
241+
237242
### 🛠 Skill Factory — *Drop in a book; out comes a digital expert.*
238243

239244
The newest generator. `openkb skill new` distills an [agent skill](https://docs.claude.com/en/docs/build-with-claude/skills) from any subset of your wiki, a portable folder that major agents (Claude Code, Codex, etc.) install and load natively. Drop in a book's worth of papers; out comes a specialist that other agents can call on.
@@ -245,6 +250,7 @@ openkb skill new karpathy-thinking \
245250

246251
<details>
247252
<summary><i>Output:</i></summary>
253+
<br>
248254

249255
```
250256
<kb>/output/skills/karpathy-thinking/
@@ -261,6 +267,7 @@ openkb skill new karpathy-thinking \
261267

262268
<details>
263269
<summary><i>Install locally:</i></summary>
270+
<br>
264271

265272
```bash
266273
cp -r output/skills/karpathy-thinking ~/.claude/skills/
@@ -270,6 +277,7 @@ cp -r output/skills/karpathy-thinking ~/.claude/skills/
270277

271278
<details>
272279
<summary><i>Share with others:</i></summary>
280+
<br>
273281

274282
Push your KB to GitHub, then anyone runs:
275283

@@ -281,6 +289,7 @@ npx skills@latest add <your-org>/<your-repo>
281289

282290
<details>
283291
<summary><i>Iterate from chat:</i></summary>
292+
<br>
284293

285294
Compilation is one-shot, but follow-up edits aren't. Inside `openkb chat`, you can refine without re-running the whole pipeline:
286295

@@ -295,6 +304,7 @@ Compilation is one-shot, but follow-up edits aren't. Inside `openkb chat`, you c
295304

296305
<details>
297306
<summary><i>Quality gates:</i></summary>
307+
<br>
298308

299309
Structural validation, trigger-accuracy + body-coverage evaluation, and full history/rollback:
300310

@@ -335,6 +345,7 @@ Model names use `provider/model` LiteLLM [format](https://docs.litellm.ai/docs/p
335345

336346
<details>
337347
<summary><i>Advanced options:</i></summary>
348+
<br>
338349

339350
`entity_types` (optional): a YAML list overriding the entity-type vocabulary used for entity pages; omit it to use the default `person`, `organization`, `place`, `product`, `work`, `event`, `other`.
340351

@@ -393,6 +404,7 @@ OpenKB ships a `SKILL.md` so any agent CLI can read your compiled wiki. No extra
393404

394405
<details>
395406
<summary><i>Claude Code:</i></summary>
407+
<br>
396408

397409
```
398410
/plugin marketplace add VectifyAI/OpenKB
@@ -403,6 +415,7 @@ OpenKB ships a `SKILL.md` so any agent CLI can read your compiled wiki. No extra
403415
404416
<details>
405417
<summary><i>OpenAI Codex CLI:</i></summary>
418+
<br>
406419
407420
*(no marketplace command yet; manual symlink)*
408421
@@ -416,6 +429,7 @@ ln -s ~/openkb-src/skills/openkb ~/.agents/skills/openkb
416429

417430
<details>
418431
<summary><i>Gemini CLI:</i></summary>
432+
<br>
419433

420434
```bash
421435
gemini skills install https://github.com/VectifyAI/OpenKB.git --path skills/openkb --consent
@@ -468,10 +482,10 @@ Apache 2.0. See [LICENSE](LICENSE).
468482

469483
Other [open-source projects](https://docs.pageindex.ai/open-source) from the PageIndex ecosystem:
470484

471-
- [PageIndex](https://github.com/VectifyAI/PageIndex) Vectorless, reasoning-based RAG framework for long documents
472-
- [ChatIndex](https://github.com/VectifyAI/ChatIndex) Tree indexing and retrieval for long conversational histories and memory
473-
- [ConDB](https://github.com/VectifyAI/ConDB) A KV-cache native context database for tree-based retrieval at scale
474-
- [PageIndex MCP](https://github.com/VectifyAI/pageindex-mcp) The MCP server for PageIndex
485+
- [PageIndex](https://github.com/VectifyAI/PageIndex): Vectorless, reasoning-based RAG framework for long documents
486+
- [ChatIndex](https://github.com/VectifyAI/ChatIndex): Tree indexing and retrieval for long conversational histories and memory
487+
- [ConDB](https://github.com/VectifyAI/ConDB): A KV-cache native context database for tree-based retrieval at scale
488+
- [PageIndex MCP](https://github.com/VectifyAI/pageindex-mcp): The MCP server for PageIndex
475489

476490
### Support Us
477491

0 commit comments

Comments
 (0)