Tabby

This is an alpha version for Tabby dev, This is only intended to be used internally.

🚀 Features

• Add support for mistral/embedding api kind. #4380

• Add generic OAuth support. #4325

• Add support for indexing multiple branches. #4419

🧰 Fixed and Improvements

• Include email in invitation link and disable email editing when opening the link. #4417

⚠️ Notice

• This is a patch release, please also check the full release note for 0.31.

🧰 Fixed and Improvements

• Added environment variable TABBY_INDEX_REPO_IN_SHARD to enable hourly sharded indexing when repository count exceeds 20. #4366

⚠️ Notice

• This is a patch release, please also check the full release note for 0.31.

🧰 Fixed and Improvements

• Optimize the SQLite connection parameters to improve stability. #4350

🚀 Features

• Add support for custom branding with name and logo (Available Exclusively with an Enterprise License). #4334

⚠️ Notice

• This is a patch release, please also check the full release note for 0.30.

🧰 Fixed and Improvements

• Use 0.7.3 sqlx to avoid database pool timeout. #4328

• Bump llama.cpp to b6047. #4330

• Expose the Flash Attention LLAMA flag as an environment variable. #4323

⚠️ Notice

• This is a patch release, please also check the full release note for 0.30.

🧰 Fixed and Improvements

• Downgrade CUDA base image to version 12.4.1 to enhance compatibility. #4314

⚠️ Notice

• The Tabby Docker image now requires an NVIDIA GPU. For CPU-only environments, use the Linux binary.

🚀 Features

• Support indexing GitLab Merge Request as Context. #4227

🧰 Fixed and Improvements

• Use CUDA 12 image as base image by default. #4235

• Leverage the Answer Engine logic to enrich the context when generating new pages, improving page quality. #4237

• Improve the model configuration details on the System page. #4236

• Resolve the flickering of buttons within code snippets in a chat response during answer generation. #4233

• Set the member filter bar always fixed at the top of the Reports page.#4232

• Resolve the issue when loading a multi-part model from local.#4302

💫 New Contributors

• @petarjuki7 made their first contribution in #4265

🚀 Features

• Add RESTful APIs for ingesting custom documents and facilitating their removal. (#4171) (#4203) (#4196)

🧰 Fixed and Improvements

• Enhance error details in Notification Inbox. (#4184)

• Add support for Automatic Jobs status polling. (#4172)

• Bump llama.cpp to b2500. (#4200)

💫 New Contributors

📰 Highlight

🚀 Features

• Add support to convert Answer Engine messages into Pages. (#4194)

• Add support for Doc Query in Chat Panel, allowing Dev Docs to be included as context. (#4095)

🧰 Fixed and Improvements

• Enhance background task logging to boost performance and enrich user experience. (#4066) (#4145)

• Enhance the display of thinking processes in Answer Engine and Chat Panel. (#4091)