Releases: nomic-ai/gpt4all
Releases · nomic-ai/gpt4all
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
v3.3.1
What's New
- Fixed a crash when attempting to continue a chat loaded from disk
- Fixed the local server rejecting min_p/top_p less than 1
Contributors
- Jared Van Bortel (Nomic AI)
Full Changelog: CHANGELOG.md
v3.3.0
What's New
- UI Improvements: The minimum window size now adapts to the font size. A few labels and links have been fixed. The Embeddings Device selection of "Auto"/"Application default" works again. The window icon is now set on Linux. The antenna icon now displays when the API server is listening.
- Single Instance: Only one instance of GPT4All can be opened at a time. This is now enforced.
- Greedy Sampling: Set temperature to zero to enable greedy sampling.
- API Server Changes: The built-in API server now responds correctly to both legacy completions, and chats with message history. Also, it now uses the system prompt configured in the UI.
- Translation Improvements: The Italian, Romanian, and Traditional Chinese translations have been updated.
Contributors
- Jared Van Bortel (Nomic AI)
- Adam Treat (Nomic AI)
- 3Simplex (
@3Simplex) - Riccardo Giovanetti (
@Harvester62) - Victor Emanuel (
@SINAPSA-IC) - Dominik (
@cosmic-snow) - Shiranui (
@supersonictw)
Full Changelog: CHANGELOG.md
v3.2.1
v3.2.0
Added
- Add Qwen2-1.5B-Instruct to models3.json (by @ThiloteE in #2759)
- Enable translation feature for seven languages: English, Spanish, Italian, Portuguese, Chinese Simplified, Chinese Traditional, Romanian (#2830)
Changed
- Add missing entries to Italian transltation (by @Harvester62 in #2783)
- Use llama_kv_cache ops to shift context faster (#2781)
- Don't stop generating at end of context (#2781)
Fixed
- Case-insensitive LocalDocs source icon detection (by @cosmic-snow in #2761)
- Fix comparison of pre- and post-release versions for update check and models3.json (#2762, #2772)
- Fix several backend issues (#2778)
- Make reverse prompt detection work more reliably and prevent it from breaking output (#2781)
- Disallow context shift for chat name and follow-up generation to prevent bugs (#2781)
- Explicitly target macOS 12.6 in CI to fix Metal compatibility on older macOS (#2846)
New Contributors
- @SINAPSA-IC made their first contribution in #2828
Full Changelog: CHANGELOG.md
Contributors
Harvester62, ThiloteE, and 2 other contributors
Assets 5
v3.1.1-web_search_beta_2
This is version 2 of the web search beta which contains some important fixes including upstream llama.cpp fixes for Llama 3.1.
Fixes
- Update to latest llama.cpp which includes RoPE fix
- Fix problem with only displaying one source for tool call excerpts
- Add the extra snippets to the source excerpts
- Fix the way we're injecting the context back into the model for web search
- Change the suggestion mode to turn on for tool calls by default
WARNING:
There was a problem with the synchronization between this beta release and the models.json. In order to make this work you have to perform the following steps:
- Rename the file
Meta-Llama-3.1-8B-Instruct-128k-Q4_0.gguftoMeta-Llama-3.1-8B-Instruct-Q4_0.gguf - Copy the following into the prompt template:
<|start_header_id|>user<|end_header_id|>
%1<|eot_id|><|start_header_id|>assistant<|end_header_id|>
%2
- Copy the following into the system prompt:
<|start_header_id|>system<|end_header_id|>
Environment: ipython
Tools: brave_search
Cutting Knowledge Date: December 2023
Today Date: 25 Jul 2024
You are a helpful assistant.<|eot_id|>
v3.1.1
v3.1.0-web_search_beta
This is the beta version of GPT4All including a new web search feature powered by Llama 3.1. To use this version you should consult the guide located here: https://github.com/nomic-ai/gpt4all/wiki/Web-Search-Beta-Release
For questions and feedback please join the discord channel: https://discord.com/invite/4M2QFmTt2k