Starstruk Logo MarkStarstruk

v0.5.9

janhq/janv0.5.9Nov 22, 2024by github-actions[bot]

AI Summary

Focuses on backend configuration capabilities (Proxy, HF Token) and UI enhancements for code blocks and remote model handling.

Key Highlights

  • Configured HTTP Proxy and HuggingFace API Token via Cortex
  • Improved code block UI with mid-stream copying
  • Enhanced remote model error handling and symlink import fallback

New Features

  • HTTP Proxy configuration via Cortex
  • HuggingFace API Token configuration
  • Cortex engine variants support
  • New UI code block with copying

Full Release Notes

## Changes

## 🚀 Features

- feat: configure HTTP Proxy via cortex.cpp @louis-jan (#4046)
- feat: configure HuggingFace API Token via cortex.cpp @louis-jan (#4068)
- enhancement: UX local server page @urmauur (#4045)
- chore: refactor re-render components @urmauur (#4040)
- feat: support cortex.cpp engine variants @louis-jan (#4022)
- feat: new UI code block and Enable copying of code blocks or plain text mid-stream @urmauur (#4010)

## 🐛 Fixes

- fix: model parameters settings local API server @urmauur (#4077)
- fix: factory reset hang on wiping data @louis-jan (#4079)
- fix: Phi 3 Mini Instruct model download URL replacement @louis-jan (#4075)
- fix: edge cases empty code block @urmauur (#4061)
- fix: correct download script to relocate DLL files properly @louis-jan (#4065)
- fix: temporary create a deps folder to have cortex.cpp work @louis-jan (#4064)
- fix: disable timeout on model load @louis-jan (#4058)
- fix: bump cortex.cpp to latest version - recursively scanning models folder should also include remote models @louis-jan (#4052)
- fix: correct OpenAI o1 model parameters @louis-jan (#4049)
- fix: inconsistent error handling @louis-jan (#4051)
- fix: handle symlink model import failure - fallback to legacy model run @louis-jan (#4050)
- fix: model import edge cases @louis-jan (#4044)
- fix: improper line break on response message @urmauur (#4042)
- fix: Jan 0.5.8 - Couldn’t upload documents to threads @louis-jan (#4031)
- fix: API local server max ctx_len not update when switch model @urmauur (#4027)
- fix: max tokens parameters - OpenRouter @urmauur (#4026)

## 🧰 Maintenance

- chore: version bump 0.5.9 @louis-jan (#4070)
- chore: remote models error handling @louis-jan (#4059)
- chore: refactor re-render components @urmauur (#4040)
- chore: correct discord message notification @hiento09 (#4018)

## Contributor

@hiento09, @louis-jan and @urmauur