Skip to content

Releases: TabbyML/tabby

nightly

08 Sep 01:39
171354e
Compare
Choose a tag to compare
nightly Pre-release
Pre-release
fix(agent): fix health chck request canceled error handler. (#3457)

* fix(agent): fix health chck request canceled error handler.

* fix(agent): fix health chck request canceled error handler.

v0.21.0-rc.1

21 Nov 12:12
Compare
Choose a tag to compare
v0.21.0-rc.1 Pre-release
Pre-release
v0.21.0-rc.1

v0.21.0-rc.0

19 Nov 04:53
Compare
Choose a tag to compare
v0.21.0-rc.0 Pre-release
Pre-release
v0.21.0-rc.0

intellij@1.8.6

14 Nov 04:49
Compare
Choose a tag to compare
chore(intellij): bump intellij plugin version to 1.8.6.

v0.20.0

10 Nov 06:19
Compare
Choose a tag to compare

πŸš€ Features

  • Search results can now be edited directly.
  • Allow switching backend chat models in Answer Engine.
  • Added a connection test button in the System tab to test the connection to the backend LLM server.

🧰 Fixes and Improvements

  • Optimized CR-LF inference in code completion. (#3279)
  • Bumped llama.cpp version to b3995.

Full Changelog: v0.19.0...v0.20.0

v0.20.0-rc.3

08 Nov 23:17
Compare
Choose a tag to compare
v0.20.0-rc.3 Pre-release
Pre-release
Release 0.20.0-rc.3

aim-downloader@0.20.0-rc.3
hash-ids@0.20.0-rc.3
http-api-bindings@0.20.0-rc.3
llama-cpp-server@0.20.0-rc.3
ollama-api-bindings@0.20.0-rc.3
tabby@0.20.0-rc.3
tabby-common@0.20.0-rc.3
tabby-crawler@0.20.0-rc.3
tabby-db@0.20.0-rc.3
tabby-db-macros@0.20.0-rc.3
tabby-download@0.20.0-rc.3
tabby-git@0.20.0-rc.3
tabby-index@0.20.0-rc.3
tabby-index-cli@0.20.0-rc.3
tabby-inference@0.20.0-rc.3
tabby-schema@0.20.0-rc.3
tabby-webserver@0.20.0-rc.3

Generated by cargo-workspaces

v0.20.0-rc.2

07 Nov 01:52
Compare
Choose a tag to compare
v0.20.0-rc.2 Pre-release
Pre-release
v0.20.0-rc.2

v0.20.0-rc.1

05 Nov 16:57
Compare
Choose a tag to compare
v0.20.0-rc.1 Pre-release
Pre-release
v0.20.0-rc.1

v0.20.0-rc.0

01 Nov 20:09
Compare
Choose a tag to compare
v0.20.0-rc.0 Pre-release
Pre-release
v0.20.0-rc.0

v0.19.0

31 Oct 17:05
Compare
Choose a tag to compare

πŸš€ Features

  • For Answer Engine, when the file content is reasonably short (e.g., less than 200 lines of code), include the entire file content directly instead of only the chunk (#3096).
  • Allowed adding additional languages through the config.toml file.
  • Allowed customizing the system_prompt for Answer Engine.

🧰 Fixed and Improvements

  • Redesigned homepage to make team activities (e.g., threads discussed in Answer Engine) discoverable.
  • Supported downloading models with multiple partitions (e.g., Qwen-2.5 series).

πŸ’« New Contributors

Full Changelog: v0.18.0...v0.19.0