Author

Tony Duan

Published

September 19, 2024

1 Download

Install Positron from our Releases page.

Currently, Positron is producing pre-release builds from a continuous integration (CI) system for macOS, Windows, and Linux. These pre-release builds are tagged with a version number here on our Github repository. Select the build you want to download, then click on Assets and download the .dmg (for Mac), .exe (for Windows), or .deb (for Linux) file.

https://github.com/posit-dev/positron

2 using Copilot with {chattr} R Package

https://github.com/mlverse/chattr

Code
remotes::install_github("mlverse/chattr")

2.1 using local model LlamaGPT-Chat

download instruction https://mlverse.github.io/chattr/articles/backend-llamagpt.html#installation

1 Download model

Code
git clone --recurse-submodules https://github.com/kuvaus/LlamaGPTJ-chat
cd LlamaGPTJ-chat

2 Download model file Vicuna 7b v1.1: ggml-vicuna-7b-1.1-q4_2.bin

https://github.com/kuvaus/LlamaGPTJ-chat?tab=readme-ov-file#gpt-j-llama-and-mpt-models

3 Build model

Code
brew install cmake
mkdir build
cd build
cmake ..
cmake --build . --parallel
Code
library(chattr)
chattr_use("llamagpt")
Code
chattr_defaults()
Code
chattr_test()
Code
chattr_app()

3 write a fuction call gogo that print out 10

3.1 using ChatGPT

3.2 using ChatGPT inside R

https://www.youtube.com/watch?v=nvTJyQFsgCc

4 Reference

https://reg.conf.posit.co/flow/posit/positconf24/publiccatalog/page/publiccatalog?search=&tab.day=20240813