Skip to content

Releases: MindWorkAI/AI-Studio

Release v0.9.31

03 Mar 15:50
@github-actions github-actions
v0.9.31
a66d88c
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.31

v0.9.31, build 206 (2025-03-03 15:33 UTC)

  • Added Helmholtz (aka "Blablador") as provider. This provider is available to all researchers and employees of the 18 Helmholtz Centers as well as all eduGAIN organizations worldwide.
  • Added GWDG SAIA as provider. This provider is available to all researchers and employees of the GWDG, the Max Planck Society, the 18 Helmholtz Centers, and most German universities.
  • Added DeepSeek as provider.
  • Added paths to log files in the "About" dialog for easier troubleshooting and support.

Virus scans

Loading

Release v0.9.30

24 Feb 23:01
@github-actions github-actions
v0.9.30
99dac52
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.30

v0.9.30, build 205 (2025-02-24 19:55 UTC)

  • Implemented the new models API for the Anthropic provider. This allows you to use the latest models, like Claude 3.7 Sonnet, which were released in the last hours.

Virus scans

Loading

Release v0.9.29

24 Feb 14:22
@github-actions github-actions
v0.9.29
5a077e1
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.29

v0.9.29, build 204 (2025-02-24 13:48 UTC)

  • Added the possibility to select data sources for chats. This preview feature is hidden behind the RAG feature flag, check your app options in case you want to enable it.
  • Added an option to all data sources to select a local security policy. This preview feature is hidden behind the RAG feature flag.
  • Added an option to preselect data sources and options for new chats. This preview feature is hidden behind the RAG feature flag.
  • Added an agent to select the appropriate data sources for any prompt. This preview feature is hidden behind the RAG feature flag.
  • Added an agent to validate whether a retrieval context makes sense for the given prompt. This preview feature is hidden behind the RAG feature flag.
  • Added a generic RAG process to integrate possibly any data in your chats. Although the generic RAG process is now implemented, the retrieval part is working only with external data sources using the ERI interface. That means that you could integrate your company's data from the corporate network by now. The retrieval process for your local data is still under development and will take several weeks to be released. In order to use data through ERI, you (or your company) have to develop an ERI server. You might use the ERI server assistant within AI Studio to do so. This preview feature is hidden behind the RAG feature flag.
  • Improved confidence card for small spaces.
  • Improved data security by enforcing provider filtering based on the chosen confidence level. To ensure this in the future, source code analyzers have been added to warn developers about insecure code.
  • Improved the readability of descriptions inside the ERI server assistant.
  • Fixed a bug in which APP_SETTINGS appeared as a valid destination in the "send to" menu.
  • Fixed a layout bug within the chat page, where the top part uses too much space.
  • Upgraded to Rust 1.85.0 and .NET 8.0.13.

Virus scans

Loading

Release v0.9.28

09 Feb 21:01
@github-actions github-actions
v0.9.28
e973b51
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.28

v0.9.28, build 203 (2025-02-09 16:33 UTC)

  • Added an information view to all data sources to the data source configuration page. The data source configuration is a preview feature behind the RAG feature flag.
  • Added a ERI ((E)xternal (R)etrieval (I)nterface) client for communication with any ERI server.
  • Added the option to select the default app provider in the assistant settings under provider selection. Thank you, Peer (peerschuett), for reporting the issue.
  • Added donework as financial supporter. Thank you, Dominic!
  • Added content contributors to the supporter page. We thank Luc (DevNullx64) for his build script contribution as well as Kerstin (KeSah001) for creating the Wiki pages.
  • Improved the resource handling when loading models.
  • Improved the build script to support Arch Linux and other Linux distributions, along with Rust nightly environments. Thanks SolsticeSpectrum for the contribution.
  • Upgraded the dependencies Rust, .NET, OpenSSL, MudBlazor, rand, rand_chacha, and others to the latest usable versions.

Virus scans

Loading

Release v0.9.27

21 Jan 21:34
@github-actions github-actions
v0.9.27
9d71978
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.27

v0.9.27, build 202 (2025-01-21 18:24 UTC)

  • Improved the inner content scrolling to use the entire space available.
  • Improved message process debugging. This helps to identify issues related to the message handling.
  • Fixed the hostname validation message for ERI v1 data sources.
  • Fixed a memory leak in the chat component.
  • Fixed an issue with the workspace title not being updated when a chat was moved to another workspace.
  • Fixed an issue with the chat component not loading the current workspace name when the component was refreshed.
  • Fixed an issue with tooltips at the bottom of the app not being displayed as expected.
  • Removed the "send to" button from the ERI server assistant, since it is not supported.

Virus scans

Loading

Release v0.9.26

13 Jan 22:24
@github-actions github-actions
v0.9.26
ebe0081
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.26

v0.9.26, build 201 (2025-01-13 19:11 UTC)

  • Added the ability to configure local and remote (ERI) data sources in the settings as a preview feature behind the RAG feature flag.
  • Fixed the ERI server assistant to ask for confirmation before deleting a ERI server preset.
  • Fixed a bug in the ERI server assistant that allowed an empty directory as a base directory for the code generation.
  • Fixed the embedding dialog to store the selected embedding model when using LM Studio as host.

Virus scans

Loading

Release v0.9.25

04 Jan 21:35
@github-actions github-actions
v0.9.25
b9a65d9
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.25

v0.9.25, build 200 (2025-01-04 18:33 UTC)

  • Added xAI as a new provider. xAI provides their Grok models for generating content.
  • Improved the stop generation button behavior to ensure that the AI stops generating content immediately (which will save compute time, energy and financial resources).
  • Fixed the chat scrolling behavior after toggling the workspaces.
  • Fixed an issue when loading the today's bias chat, triggered by the bias assistant.
  • Restructured the streaming network code to be centralized out of the individual providers. This will allow for easier maintenance and updates in the future.

Virus scans

Loading

Release v0.9.24

04 Jan 14:40
@github-actions github-actions
v0.9.24
a54c0bd
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.24

v0.9.24, build 199 (2025-01-04 11:40 UTC)

  • Added a button to remove a message from the chat thread.
  • Added a button to regenerate the last AI response.
  • Added a button to edit the last user message.
  • Added a button to stop the AI from generating more tokens.
  • Improved the stream handling for all providers. The stream handling is now very resilient and handles all kinds of network issues.
  • Fixed a streaming bug that was particularly visible with self-hosted providers.

Virus scans

Loading

Release v0.9.23

02 Jan 23:26
@github-actions github-actions
v0.9.23
6f5aecd
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.23

v0.9.23, build 198 (2025-01-02 19:39 UTC)

  • Added an ERI server coding assistant as a preview feature behind the RAG feature flag. This helps you implement an ERI server to gain access to, e.g., your enterprise data from within AI Studio.
  • Improved dark mode: Code blocks are now displayed in a dark theme as well (previously, they were displayed in a light theme, no matter what).
  • Improved profile handling: Every chat remembers the last profile used.
  • Improved the chat UI: You can now set the aspect ratio between workspaces and chat as you like.
  • Improved provider requests by handling rate limits by retrying requests.
  • Improved the creation of the "the bias of the day" workspace; create that workspace only when the bias of the day feature is used.
  • Improved the save operation of settings by using a temporary file to avoid data loss in rare cases.
  • Improved the system prompt handling: Injection of profiles into system prompts happens right before sending the data. This way, the original system prompts are not modified.
  • Improved the navigation bar handling when configured as "never expands" with or without tooltips.
  • Fixed OpenAI o (aka omni, aka reasoning) models. The early preview versions (released before 17th December 2024) could not use any system prompts —- we translated the system prompts to be user prompts. Final versions of the OpenAI o models can now use system prompts, but they are named developer instead of system.
  • Fixed layout issues when selecting other items (e.g., programming languages).
  • Fixed a bug about the bias of the day workspace when the workspace component was hidden.
  • Upgraded dependencies to the latest versions.

Virus scans

Loading

Release v0.9.22

04 Dec 14:18
@github-actions github-actions
v0.9.22
7250b27
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Release v0.9.22

v0.9.22, build 197 (2024-12-04 10:58 UTC)

  • Added the possibility to configure preview feature visibility in the app settings. This is useful for users who want to test new features before they are officially released.
  • Added the possibility to configure embedding providers in the app settings as a prototype preview feature. Embeddings are necessary in order to integrate local data and files.
  • Added the writer mode as an experimental preview feature. This feature is just an experiment as we explore how to implement long text support in AI Studio.
  • Improved self-hosted LLM provider configuration by filtering embedding models.
  • Fixed a bug where you couldn't move a chat to (another) workspace when the workspaces were docked to the left side and were collapsed.
  • Fixed a bug when you replaced a chat with a new chat, and the workspaces were docked to the left and were collapsed; then, the previous chat was not removed from the workspace.

Virus scans

Loading