Skip to content

Commit ca25115

Browse files
authored
Merge pull request #110 from VectifyAI/fix-readme-2
update readme
2 parents 8ab9a33 + 3dcbf88 commit ca25115

1 file changed

Lines changed: 26 additions & 24 deletions

File tree

README.md

Lines changed: 26 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -43,7 +43,7 @@ pip install openkb
4343
```
4444

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

4848
- **Latest from GitHub:**
4949

@@ -89,7 +89,7 @@ openkb skill new my-expert "Reason like an expert on <your-topic>"
8989

9090
OpenKB comes with [multi-LLM support](https://docs.litellm.ai/docs/providers) (e.g., OpenAI, Claude, Gemini) via [LiteLLM](https://github.com/BerriAI/litellm) (pinned to a [safe version](https://docs.litellm.ai/blog/security-update-march-2026)).
9191

92-
Set your model during `openkb init`, or in [`.openkb/config.yaml`](#configuration), using `provider/model` LiteLLM format (like `anthropic/claude-sonnet-4-6`). OpenAI models can omit the prefix (like `gpt-5.4`).
92+
Set your model during `openkb init`, or in [`.openkb/config.yaml`](#configuration), using the `provider/model` LiteLLM format (like `anthropic/claude-sonnet-4-6`). OpenAI models can omit the prefix (like `gpt-5.4`).
9393

9494
Create a `.env` file with your LLM API key:
9595

@@ -162,14 +162,14 @@ OpenKB commands fall into two layers: the **wiki foundation** (compile + manage
162162
| Command | Description |
163163
|---|---|
164164
| `openkb init` | Initialize a new knowledge base (interactive) |
165-
| <code>openkb&nbsp;add&nbsp;&lt;file_or_dir_or_URL&gt;</code> | Add files, directories, or URLs and compile to wiki. URLs auto-detect content type (PDF or HTML) |
165+
| <code>openkb&nbsp;add&nbsp;&lt;file_or_dir_or_URL&gt;</code> | Add files, directories, or URLs and compile to wiki. URL content type (PDF or HTML) is auto-detected |
166166
| `openkb list` | List indexed documents and concepts |
167167
| `openkb status` | Show knowledge base stats |
168168
| `openkb watch` | Watch `raw/` and auto-compile new files |
169169
| `openkb lint` | Run structural + knowledge health checks |
170170

171171
<details>
172-
<summary><i>More wiki commands:</i></summary>
172+
<summary><b><i>More wiki commands:</i></b></summary>
173173

174174
| Command | Description |
175175
|---|---|
@@ -193,7 +193,7 @@ A "generator" reads from the compiled wiki and produces something usable: an ans
193193
| <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 |
194194

195195
<details>
196-
<summary><i>More skill commands:</i></summary>
196+
<summary><b><i>More skill commands:</i></b></summary>
197197

198198
| Command | Output |
199199
|---|---|
@@ -203,9 +203,9 @@ A "generator" reads from the compiled wiki and produces something usable: an ans
203203

204204
</details>
205205

206-
### Query & Chat — ask the wiki
206+
### 💬 Query & Chat — *Ask the wiki*
207207

208-
`openkb query "..."` answers a single question. `openkb chat` is interactive; each turn carries history, so you can dig into a topic without re-typing context. Both use the same underlying wiki and the same retrieval primitives (PageIndex for long docs, direct concept reads for short).
208+
`openkb query "..."` answers a single question. `openkb chat` is interactive; each turn carries history, so you can dig into a topic without re-typing context. Both use the same underlying wiki and retrieval primitives.
209209

210210
```bash
211211
openkb query "What does the literature say about attention scaling?"
@@ -217,10 +217,10 @@ openkb chat --list # list all sessions
217217
openkb chat --delete <id> # delete a session
218218
```
219219

220-
Inside a chat, type `/` to access slash commands (Tab to complete):
220+
Inside a chat, type `/` to access slash commands (Tab to complete).
221221

222222
<details>
223-
<summary><i>Slash commands</i></summary>
223+
<summary><i>Slash commands:</i></summary>
224224

225225
- `/help` — list available commands
226226
- `/status` — show knowledge base status
@@ -234,7 +234,7 @@ Inside a chat, type `/` to access slash commands (Tab to complete):
234234

235235
</details>
236236

237-
### 🛠 Skill Factory — *Drop in a book. Out comes a digital expert.*
237+
### 🛠 Skill Factory — *Drop in a book; out comes a digital expert.*
238238

239239
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.
240240

@@ -244,7 +244,7 @@ openkb skill new karpathy-thinking \
244244
```
245245

246246
<details>
247-
<summary><i>Output</i></summary>
247+
<summary><i>Output:</i></summary>
248248

249249
```
250250
<kb>/output/skills/karpathy-thinking/
@@ -260,7 +260,7 @@ openkb skill new karpathy-thinking \
260260
</details>
261261

262262
<details>
263-
<summary><i>Install locally</i></summary>
263+
<summary><i>Install locally:</i></summary>
264264

265265
```bash
266266
cp -r output/skills/karpathy-thinking ~/.claude/skills/
@@ -269,7 +269,7 @@ cp -r output/skills/karpathy-thinking ~/.claude/skills/
269269
</details>
270270

271271
<details>
272-
<summary><i>Share with others</i></summary>
272+
<summary><i>Share with others:</i></summary>
273273

274274
Push your KB to GitHub, then anyone runs:
275275

@@ -280,7 +280,7 @@ npx skills@latest add <your-org>/<your-repo>
280280
</details>
281281

282282
<details>
283-
<summary><i>Iterate from chat</i></summary>
283+
<summary><i>Iterate from chat:</i></summary>
284284

285285
Compilation is one-shot, but follow-up edits aren't. Inside `openkb chat`, you can refine without re-running the whole pipeline:
286286

@@ -294,7 +294,7 @@ Compilation is one-shot, but follow-up edits aren't. Inside `openkb chat`, you c
294294
</details>
295295

296296
<details>
297-
<summary><i>Quality gates</i></summary>
297+
<summary><i>Quality gates:</i></summary>
298298

299299
Structural validation, trigger-accuracy + body-coverage evaluation, and full history/rollback:
300300

@@ -317,7 +317,7 @@ openkb skill rollback karpathy-thinking --to 2
317317

318318
### Settings
319319

320-
Settings are initialized by `openkb init`, and stored in `.openkb/config.yaml`:
320+
OpenKB settings are initialized by `openkb init` and are stored in `.openkb/config.yaml`:
321321

322322
```yaml
323323
model: gpt-5.4 # LLM model (any LiteLLM-supported provider)
@@ -334,7 +334,7 @@ Model names use `provider/model` LiteLLM [format](https://docs.litellm.ai/docs/p
334334
| Gemini | `gemini/gemini-3.1-pro-preview` |
335335

336336
<details>
337-
<summary><i>Advanced options</i></summary>
337+
<summary><i>Advanced options:</i></summary>
338338

339339
`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`.
340340

@@ -350,13 +350,13 @@ Subscription-based providers that authenticate via OAuth device flow (e.g. `chat
350350

351351
</details>
352352

353-
### PageIndex
353+
### PageIndex Setup
354354

355-
Long-document retrieval is a [known challenge](https://x.com/karpathy/status/2039823314982744522) for LLMs. [PageIndex](https://github.com/VectifyAI/PageIndex) solves this with vectorless, reasoning-based retrieval, building a hierarchical tree index that lets LLMs reason over the index for context-aware retrieval.
355+
Long-document retrieval is a [known challenge](https://x.com/karpathy/status/2039823314982744522) for LLMs. [PageIndex](https://github.com/VectifyAI/PageIndex) solves this with vectorless, reasoning-based retrieval, by building a hierarchical tree index that lets LLMs reason over the index for context-aware retrieval.
356356

357357
PageIndex runs locally by default using the [open-source version](https://github.com/VectifyAI/PageIndex), with no external dependencies required.
358358

359-
#### Cloud Support (Optional)
359+
***Cloud Support*** *(Optional)*:
360360

361361
For large or complex PDFs, [PageIndex Cloud](https://docs.pageindex.ai/) can be used to access additional capabilities, including:
362362

@@ -392,7 +392,7 @@ OpenKB's wiki is a directory of Markdown files with `[[wikilinks]]`. Obsidian re
392392
OpenKB ships a `SKILL.md` so any agent CLI can read your compiled wiki. No extra runtime, no MCP setup, just install the skill once.
393393

394394
<details>
395-
<summary><b>Claude Code</b></summary>
395+
<summary><i>Claude Code:</i></summary>
396396

397397
```
398398
/plugin marketplace add VectifyAI/OpenKB
@@ -402,7 +402,9 @@ OpenKB ships a `SKILL.md` so any agent CLI can read your compiled wiki. No extra
402402
</details>
403403
404404
<details>
405-
<summary><b>OpenAI Codex CLI</b> <i>(no marketplace command yet; manual symlink)</i></summary>
405+
<summary><i>OpenAI Codex CLI:</i></summary>
406+
407+
*(no marketplace command yet; manual symlink)*
406408
407409
```bash
408410
git clone https://github.com/VectifyAI/OpenKB.git ~/openkb-src
@@ -413,7 +415,7 @@ ln -s ~/openkb-src/skills/openkb ~/.agents/skills/openkb
413415
</details>
414416

415417
<details>
416-
<summary><b>Gemini CLI</b></summary>
418+
<summary><i>Gemini CLI:</i></summary>
417419

418420
```bash
419421
gemini skills install https://github.com/VectifyAI/OpenKB.git --path skills/openkb --consent
@@ -473,7 +475,7 @@ Other [open-source projects](https://docs.pageindex.ai/open-source) from the Pag
473475

474476
### Support Us
475477

476-
If you find OpenKB useful, please give us a star 🌟 and check out [PageIndex](https://github.com/VectifyAI/PageIndex) too!
478+
If you find OpenKB useful, please give us a star 🌟 and check out [**PageIndex**](https://github.com/VectifyAI/PageIndex) too!
477479

478480
<div>
479481

0 commit comments

Comments
 (0)