This website requires JavaScript.
Explore
Help
Register
Sign In
mmanningau
/
alice
Watch
1
Star
0
Fork
0
You've already forked alice
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
14
Commits
1
Branch
1
Tag
master
Go to file
Add File
New File
Upload File
Apply Patch
Code
Clone
HTTPS
Tea CLI
Open with VS Code
Open with VSCodium
Open with Intellij IDEA
Download ZIP
Download TAR.GZ
Download BUNDLE
mmanningau
2f9b00ae29
Have settled on testing and using the Qwen2.5:1.5b model as it plays much nicer with the JSON requirements - way better than the Gemma models did. Have refined the calls via LlmManager.kt and MediaPipeAdapter.kt and tested using battery, ping and a new weather skill. Half way through updating further to allow for SMS reading and updating the SkillManager.kt again to accommodate this with a two-pass bridge for python calling.
2026-03-05 15:13:56 +11:00
.idea
Check in before major engine ovberhaul to use the Google Mediapipe LLM framework.
2026-03-02 10:05:08 +11:00
app
Have settled on testing and using the Qwen2.5:1.5b model as it plays much nicer with the JSON requirements - way better than the Gemma models did. Have refined the calls via LlmManager.kt and MediaPipeAdapter.kt and tested using battery, ping and a new weather skill. Half way through updating further to allow for SMS reading and updating the SkillManager.kt again to accommodate this with a two-pass bridge for python calling.
2026-03-05 15:13:56 +11:00
gradle
Made the decision to initially stick to the Ollama LLM backend and not go down the whole c++ download and compile for MLC LLM usage. Update to the UI to now include the model downloaded for the Llamatik backend to use. Tested as working and downloading models successfully.
2026-02-28 12:58:04 +11:00
.gitignore
Initial empty project commit.
2026-02-25 11:21:42 +11:00
build.gradle.kts
Made the decision to initially stick to the Ollama LLM backend and not go down the whole c++ download and compile for MLC LLM usage. Update to the UI to now include the model downloaded for the Llamatik backend to use. Tested as working and downloading models successfully.
2026-02-28 12:58:04 +11:00
gradle.properties
Initial empty project commit.
2026-02-25 11:21:42 +11:00
gradlew
Initial empty project commit.
2026-02-25 11:21:42 +11:00
gradlew.bat
Initial empty project commit.
2026-02-25 11:21:42 +11:00
settings.gradle.kts
Initial empty project commit.
2026-02-25 11:21:42 +11:00
Description
My local and personal Android LLM assistant app
231
KiB
Languages
Kotlin
100%