v0.18.0-rc.0

v0.18.0-rc.0

v0.17.0

⚠️ Notice

• We've reworked the Web (a beta feature) context provider into the Developer Docs context provider. Previously added context in the Web tab has been cleared and needs to be manually migrated to Developer Docs.

🚀 Features

• Extensive rework has been done in the answer engine search box.
  • Developer Docs / Web search is now triggered by @.
  • Repository Context is now selected using #.

• Supports OCaml

💫 New Contributors

• @eryue0220 made their first contribution in #2921
• @th0rgall made their first contribution in #3041
• @tcmzzz made their first contribution in #3093

Full Changelog: v0.16.1...v0.17.0

v0.17.0-rc.6

v0.17.0-rc.6

v0.17.0-rc.5

v0.17.0-rc.5

v0.17.0-rc.4

v0.17.0-rc.4

v0.17.0-rc.3

v0.17.0-rc.3

v0.17.0-rc.2

v0.17.0-rc.2

v0.17.0-rc.1

v0.17.0-rc.1

v0.17.0-rc.0

v0.17.0-rc.0

v0.16.1

⚠️ Notice

• Starting from this version, we are utilizing websockets for features that require streaming (e.g., Answer Engine and Chat Side Panel). If you are deploying tabby behind a reverse proxy, you may need to configure the proxy to support websockets.

🚀 Features

• Discussion threads in the Answer Engine are now persisted, allowing users to share threads with others.

🧰 Fixed and Improvements

• Fixed an issue where the llama-server subprocess was not being reused when reusing a model for Chat / Completion together (e.g., Codestral-22B) with the local model backend.
• Updated llama.cpp to version b3571 to support the jina series embedding models.

💫 New Contributors

• @richginsberg made their first contribution in #2738
• @VladislavNekto made their first contribution in #2804
• @Sherlock113 made their first contribution in #2809
• @zwpaper made their first contribution in #2812
• @cclauss made their first contribution in #2832
• @richard-jfc made their first contribution in #2835

Full Changelog: v0.15.0...v0.16.1