nova
aa8fff2c0d
Integrates LiteRT-LM (Google) with Gemma 4 E2B-it for on-device spell/grammar correction in HeliBoard. After sentence-ending punctuation, the model checks the sentence and shows a correction in the suggestion strip. Tapping it replaces the original text — fully offline, no cloud API. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
140 lines
4.2 KiB
Markdown
140 lines
4.2 KiB
Markdown
# AIKeyboard — HeliBoard + Gemma 4 On-Device AI Correction
|
|
|
|
HeliBoard fork that adds on-device spell and grammar correction powered by
|
|
**Gemma 4 E2B-it** running locally via Google's **LiteRT-LM** SDK.
|
|
|
|
After you finish typing a sentence (`.`, `!`, `?`), the model silently checks
|
|
it and — if it finds an error — shows the corrected sentence in the suggestion
|
|
strip. Tap it once to replace the original text. Everything runs on-device,
|
|
no network, no cloud API.
|
|
|
|
---
|
|
|
|
## How it works
|
|
|
|
```
|
|
User types "guten rag."
|
|
↓
|
|
InputLogic detects sentence-ending punctuation
|
|
↓
|
|
AiTriggerHook (500 ms debounce) extracts last sentence
|
|
↓
|
|
AiCorrectionEngine.correctSentence()
|
|
→ LiteRT-LM Engine (GPU first, CPU fallback)
|
|
→ Gemma 4 E2B-it .litertlm model
|
|
↓
|
|
AiSuggestionManager.postSuggestion("Guten Tag.", "guten rag.")
|
|
↓
|
|
Suggestion strip shows "Guten Tag." in italic/accent color
|
|
↓
|
|
User taps → original text replaced with correction
|
|
```
|
|
|
|
### Components
|
|
|
|
| File | Role |
|
|
|------|------|
|
|
| `app/…/ai/AiCorrectionEngine.kt` | LiteRT-LM wrapper; GPU→CPU fallback |
|
|
| `app/…/ai/AiTriggerHook.kt` | Sentence detection + debounce |
|
|
| `app/…/ai/AiSuggestionManager.kt` | Posts corrected text to suggestion strip |
|
|
| `patches/0001-InputLogic-ai-hook.patch` | Hook in `InputLogic.java` after `commitCodePoint` |
|
|
| `patches/0002-LatinIME-ai-lifecycle.patch` | AI object lifecycle in `LatinIME.java` |
|
|
| `patches/0003-SuggestionStrip-ai-style.patch` | Italic + accent color for AI suggestions |
|
|
|
|
---
|
|
|
|
## Requirements
|
|
|
|
- Android device with **ARM64** (arm64-v8a), Android 11+ (API 31)
|
|
- Android Studio **Ladybug** or newer / Gradle 8+
|
|
- NDK **28.0.13004108**
|
|
- **Gemma 4 E2B-it** model in `.litertlm` format (~2.6 GB)
|
|
Download: <https://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm>
|
|
|
|
---
|
|
|
|
## Setup
|
|
|
|
### 1. Clone and prepare HeliBoard sources
|
|
|
|
```bash
|
|
git clone http://172.17.2.68:3001/nova/AIKeyboard.git
|
|
cd AIKeyboard
|
|
bash setup_heliboard.sh
|
|
```
|
|
|
|
`setup_heliboard.sh` clones HeliBoard from GitHub and applies the three AI
|
|
integration patches automatically.
|
|
|
|
### 2. Push the model to the device
|
|
|
|
```bash
|
|
adb push gemma-4-E2B-it.litertlm /data/local/tmp/gemma-4-E2B-it.litertlm
|
|
adb shell chmod 644 /data/local/tmp/gemma-4-E2B-it.litertlm
|
|
```
|
|
|
|
### 3. Build and install
|
|
|
|
```bash
|
|
./gradlew installDebug
|
|
```
|
|
|
|
Enable **AIKeyboard** as your input method in Android Settings → System →
|
|
Languages & input → On-screen keyboard.
|
|
|
|
---
|
|
|
|
## Patch details
|
|
|
|
The three patches modify HeliBoard source files in `heliboard/`:
|
|
|
|
**0001 — InputLogic hook**
|
|
After every committed code point, checks `AiTriggerHook.isSentenceEnder()`.
|
|
On a sentence-ender, reads up to 500 chars before the cursor and calls
|
|
`onSentenceEndDetected()`.
|
|
|
|
**0002 — LatinIME lifecycle**
|
|
Instantiates `AiCorrectionEngine`, `AiSuggestionManager`, and `AiTriggerHook`
|
|
in `onCreate()`, cleans them up in `onDestroy()`. Overrides
|
|
`showAiSuggestion()` to bypass the normal suggestions-enabled gate and
|
|
intercepts `pickSuggestionManually()` to do a clean sentence replacement
|
|
(finish composing → delete original → commit corrected text).
|
|
|
|
**0003 — SuggestionStrip styling**
|
|
Detects the `KIND_AI_FLAG` bit (`0x10000`) on a `SuggestedWordInfo` and
|
|
applies italic style + auto-correct accent color to visually distinguish AI
|
|
suggestions from normal word predictions.
|
|
|
|
---
|
|
|
|
## Model placement
|
|
|
|
The model must be at `/data/local/tmp/gemma-4-E2B-it.litertlm` on the device.
|
|
This path is configured in `AiCorrectionEngine.MODEL_PATH`.
|
|
|
|
The model file is **not** tracked in this repository (2.6 GB, `.litertlm` is
|
|
in `.gitignore`).
|
|
|
|
---
|
|
|
|
## Backend selection
|
|
|
|
`AiCorrectionEngine` tries **GPU** (WebGPU/Vulkan via LiteRT-LM) first.
|
|
If GPU initialization fails, it falls back to **CPU** immediately. If a GPU
|
|
inference error occurs at runtime, it permanently switches to CPU for the
|
|
session and recreates the engine.
|
|
|
|
Tested on:
|
|
- Google Pixel 7 (Tensor G2) — CPU backend (OpenCL not available)
|
|
- Devices with Mali-G710 — GPU via WebGPU/Vulkan
|
|
|
|
---
|
|
|
|
## License
|
|
|
|
The AI integration layer (`app/src/main/java/helium314/keyboard/latin/ai/`)
|
|
is original work added to this project.
|
|
|
|
HeliBoard itself is licensed under **GPL-3.0-only**. See
|
|
`heliboard/LICENSE` after running `setup_heliboard.sh`.
|