v3.7.0

What's New

• Windows ARM Support: GPT4All now supports the Windows ARM platform, ensuring compatibility with devices powered by Qualcomm Snapdragon and Microsoft SQ-series processors.
  • NOTE: Support for GPU and/or NPU acceleration is not available at this time. Only the CPU will be used to run LLMs.
  • NOTE: You must install the new Windows ARM version of GPT4All from the website. The standard Windows version will not work due to emulation limitations.
• Fixed Updating on macOS: The maintenance tool no longer crashes when attempting to update or uninstall GPT4All on Sequoia.
  • NOTE: If you have installed the version from the GitHub releases as a workaround for this issue, you can safely uninstall it and switch back to the version from the website.
• Fixed Chat Saving on macOS: Chats now save as expected when the application is quit with Command-Q.
• Code Interpreter Improvements:
  • The behavior when the code takes too long to execute and times out has been improved.
  • console.log now accepts multiple arguments for better compatibility with native JavaScript.
• Chat Templating Improvements:
  • Two crashes and one compatibility issue have been fixed in the chat template parser.
  • The default chat template for EM German Mistral has been fixed.
  • Automatic replacements have been added for five new models as we continue to improve compatibility with common chat templates.

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)
• Riccardo Giovanetti (@Harvester62)

Full Changelog: CHANGELOG.md

Note: Please be careful when downloading an offline installer below. There is now a -win64-arm installer. If you have an ARM processor (e.g. Qualcomm Snapdragon or Microsoft SQ-series), use the -win64-arm one. If you have an Intel or AMD processor, or if unsure, use the -win64 one.

v3.6.1

What's New

• Fixes:
  • The stop generation button no longer working in v3.6.0.
  • The copy entire conversation button no longer working in v3.6.0.

Contributors

• Adam Treat (Nomic AI)

Full Changelog: CHANGELOG.md

v3.6.0

What's New

• Reasoner v1:
  • Built-in javascript code interpreter tool.
  • Custom curated model that utilizes the code interpreter to break down, analyze, perform, and verify complex reasoning tasks.
• Templates: Automatically substitute chat templates that are not compatible with Jinja2Cpp in GGUFs.
• Fixes:
  • Remote model template to allow for XML in messages.
  • Jinja2Cpp bug that broke system message detection in chat templates.
  • LocalDocs sources displaying in unconsolidated form after v3.5.0.

Contributors

• Adam Treat (Nomic AI)
• Jared Van Bortel (Nomic AI)

Full Changelog: CHANGELOG.md

v3.5.3

What's New

• LocalDocs Fix: A serious issue causing LocalDocs to not work properly in v3.5.2 has been fixed.

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)

Full Changelog: CHANGELOG.md

v3.5.2

What's New

• Model Search: There are now separate tabs for official and third-party models.
• Local Server Fixes: Several mistakes in v3.5's changes to the API server have been corrected.
• Cloned Model Fixes: The chat template and system message of cloned models now manage their defaults correctly.
• Translation Improvements: The Romanian and Italian translations have been updated.

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)
• Riccardo Giovanetti (@Harvester62)
• Victor Emanuel (@SINAPSA-IC)

Full Changelog: CHANGELOG.md

v3.5.1

What's New

• Chat template fixes: Llama 3.2 models, Nous Hermes 2 Mistral, Mistral OpenOrca, Qwen 2 and remote models
• Bugfix: Fix the default model button so it works again after 3.5.0

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)

Full Changelog: CHANGELOG.md

v3.5.0

What's New

• Message Editing:
  • You can now edit your any message you sent by clicking the pencil icon below it.
  • You can now redo earlier responses in the conversation.
• Templates: Chat templates have been completely overhauled! They now use Jinja-style syntax. You may notice warnings or errors in the UI. Read the linked docs, and if you have any questions, please ask on the Discord.
• File Attachments: Markdown and plain text files are now supported as file attachments.
• System Tray: There is now an option in Application Settings to allow GPT4All to minimize to the system tray instead of closing.
• Local API Server:
  • The API server now supports system messages from the client and no longer uses the system message in settings.
  • You can now send messages to the API server in any order supported by the model instead of just user/assistant pairs.
• Translations: The Italian and Romanian translations have been improved.

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)
• Benjamin Gallois (@bgallois)
• Riccardo Giovanetti (@Harvester62)
• Victor Emanuel (@SINAPSA-IC)

Full Changelog: CHANGELOG.md

v3.4.2

What's New

• LocalDocs Fixes: Several issues with LocalDocs, some of which were introduced in v3.4.0, have been fixed.
  • Fixed the possible use of references from unselected collections.
  • Fixed unnecessary reindexing of files with uppercase extensions.
  • Fixed hybrid search failure due to inconsistent database state.
  • Fully fixed the blank Embeddings Device selection in LocalDocs settings.
  • Fixed LocalDocs indexing of large PDFs making very slow progress or even stalling.

Contributors

• Adam Treat (Nomic AI)
• Jared Van Bortel (Nomic AI)

Full Changelog: CHANGELOG.md

v3.4.1

What's New

• LocalDocs Fixes: Several issues with LocalDocs in v3.4.0 have been fixed, including missing words and very slow indexing.
• Syntax Highlighting: Go code is now highlighted with the correct colors.
• Cache Fixes: The model list cache is now stored with a version number, and in a more appropriate directory.
• Translation Updates: The Italian translation has been improved.

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)
• John Parent (Kitware)
• Riccardo Giovanetti (@Harvester62)

Full Changelog: CHANGELOG.md

v3.4.0

What's New

• Attached Files: You can now attach a small Microsoft Excel spreadsheet (.xlsx) to a chat message and ask the model about it.
  • Read more here.
• LocalDocs Accuracy: The LocalDocs algorithm has been enhanced to find more accurate references for some queries.
• Word Document Support: LocalDocs now supports Microsoft Word (.docx) documents natively.
  • IMPORTANT NOTE: If .docx files are not found, make sure Settings > LocalDocs > Allowed File Extensions includes "docx".
• Forgetful Model Fixes: Issues with the "Redo last chat response" button, and with continuing chats from previous sessions, have been fixed.
• Chat Saving Improvements: On exit, GPT4All will no longer save chats that are not new or modified. As a bonus, downgrading without losing access to all chats will be possible in the future, should the need arise.
• UI Fixes: The model list no longer scrolls to the top when you start downloading a model.
• New Models: Llama 3.2 Instruct 3B and 1B models are now available in the model list.

Contributors

• Jared Van Bortel (Nomic AI)
• Adam Treat (Nomic AI)
• Andriy Mulyar (Nomic AI)
• Ikko Eltociear Ashimine (@eltociear)
• Victor Emanuel (@SINAPSA-IC)
• Shiranui (@supersonictw)

Full Changelog: CHANGELOG.md