Commit Graph

71 Commits

Author SHA1 Message Date
Adam Treat
f291853e51 First attempt at providing a persistent chat list experience.
Limitations:

1) Context is not restored for gpt-j models
2) When you switch between different model types in an existing chat
   the context and all the conversation is lost
3) The settings are not chat or conversation specific
4) The sizes of the chat persisted files are very large due to how much
   data the llama.cpp backend tries to persist. Need to investigate how
   we can shrink this.
2023-05-04 15:31:41 -04:00
Adam Treat
4a09f0f0ec More extensive usage stats to help diagnose errors and problems in the ui. 2023-05-02 20:31:17 -04:00
Adam Treat
118e0bdc44 Allow removing chats. 2023-05-01 20:56:53 -04:00
Adam Treat
a48226613c Turn the chat list into a model. 2023-05-01 17:13:20 -04:00
Adam Treat
8f80f8e3a2 Break out the drawer into own component. 2023-05-01 13:51:46 -04:00
Adam Treat
4d87c46948 Major refactor in prep for multiple conversations. 2023-05-01 09:10:05 -04:00
Adam Treat
d1e3198b65 Add new C++ version of the chat model. Getting ready for chat history. 2023-04-30 20:28:43 -04:00
Adam Treat
13401fc52f Bump the version. 2023-04-29 21:04:47 -04:00
Adam Treat
727a74de6c Make an offline installer option. 2023-04-29 12:13:11 -04:00
Adam Treat
9ebf2537fa Bump the version. 2023-04-29 08:56:53 -04:00
Adam Treat
22441a460b Fix the icons more. 2023-04-28 21:48:10 -04:00
Adam Treat
1df4035679 Fix icons. 2023-04-28 21:40:45 -04:00
Adam Treat
3f7852f384 Correct the macOS symlink. 2023-04-28 21:26:38 -04:00
Adam Treat
a9bbe3f949 Fix icons and try to make macOS experience happier. 2023-04-28 21:19:12 -04:00
Aaron Miller
af83056a4f put chat.exe in 'bin' folder of build tree
because this is also in llama.cpp's CMakeLists:
https://github.com/ggerganov/llama.cpp/blob/master/CMakeLists.txt#L11
this is where libllama.dll winds up, causing attempts to run the chat UI
from Qt Creator on Windows to fail due to not finding libllama.dll - I've been
working around this by copying libllama.dll *out* of bin/ but have been
bitten a few times by forgetting to keep doing that and the build getting
out of sync.
2023-04-28 20:45:02 -04:00
Adam Treat
43eef81ca8 New startup dialog features. 2023-04-28 11:03:16 -04:00
Adam Treat
fbce5f2078 Unnecessary after all. 2023-04-26 18:35:53 -04:00
Adam Treat
aadeb47026 Put this before. 2023-04-26 13:54:25 -04:00
Adam Treat
8f913c382c Signing ident. 2023-04-26 13:33:33 -04:00
Adam Treat
74c611b49a Add back option. 2023-04-26 11:02:05 -04:00
Adam Treat
3c9139b5d2 Move the backend code into own subdirectory and make it a shared library. Begin fleshing out the C api wrapper that bindings can use. 2023-04-26 08:22:38 -04:00
Aaron Miller
cd03c5b7d5 Add QuickDialogs2 to CMake component list 2023-04-25 16:24:55 -04:00
Adam Treat
c9888a285e Force avx2 off if avx_only is checked. 2023-04-24 17:44:57 -04:00
Adam Treat
f456756ba8 Make clear this is optional and bump the version. 2023-04-24 13:40:10 -04:00
Adam Treat
e6a8681dbe Always download to a local directory outside of the binary directory otherwise
models will be deleted when updates occur. Update version.
2023-04-24 11:31:41 -04:00
Adam Treat
e1159cd997 Make it easier to test and build installers for localhost and avx only. 2023-04-24 01:08:13 -04:00
Adam Treat
76e5b85128 Try again with macOS icon. 2023-04-24 00:44:02 -04:00
Adam Treat
57276d3520 See if we can get the icon for macOS associated with bundle. 2023-04-24 00:33:57 -04:00
Adam Treat
e974b41b2b Change this back on linux/windows. 2023-04-23 23:42:55 -04:00
Adam Treat
cd352b958d Working on macos now. 2023-04-23 23:38:12 -04:00
Adam Treat
1d37ebc826 Change name of exe. 2023-04-23 22:57:37 -04:00
Adam Treat
f8dc47e796 Need a subdir. 2023-04-23 22:48:27 -04:00
Adam Treat
134b4dd286 macOS specific cmake changes experiment. 2023-04-23 22:43:30 -04:00
Adam Treat
93f54742b9 Small fixes. 2023-04-23 22:05:24 -04:00
Adam Treat
e06cff8b48 Consolidate all colors to a central theme object. 2023-04-23 09:42:35 -04:00
Adam Treat
c366fc8054 Move the popup dialog into own file and disable network for now. 2023-04-23 07:05:43 -04:00
Adam Treat
889d7d8563 Move settings dialog into own file. 2023-04-23 06:58:07 -04:00
Adam Treat
1f65e381ee New thumbs up/down support for gpt4all-datalake. 2023-04-22 22:09:14 -04:00
Adam Treat
cca2a88e47 Getting ready for next update. 2023-04-21 23:23:57 -04:00
Adam Treat
bec8072fe1 Fix logic. 2023-04-21 13:46:50 -04:00
eachadea
116f740fb5 Don't build test_hw on apple silicon 2023-04-21 11:25:03 -04:00
Adam Treat
14831cd1c0 Add a small program that tests hardware. 2023-04-20 19:34:56 -04:00
eachadea
b09ca009c5 Don't build a universal binary
unless -DBUILD_UNIVERSAL=ON
2023-04-20 06:37:54 -04:00
Adam Treat
55084333a9 Add llama.cpp support for loading llama based models in the gui. We now
support loading both gptj derived models and llama derived models.
2023-04-20 06:19:09 -04:00
Adam Treat
e6cb6a2ae3 Add a new model download feature. 2023-04-18 21:10:06 -04:00
Adam Treat
bbf838354e Don't add version number to the installer or the install location. 2023-04-17 15:59:14 -04:00
Adam Treat
9f4e3cb7f4 Bump the version for the context bug fix. 2023-04-17 15:37:24 -04:00
Adam Treat
42fb215f61 Bump version to 2.1 as this has been referred to far and wide as
GPT4All v2 so doing this to decrease confusion. Also, making the version
number visible in the title bar.
2023-04-17 07:50:39 -04:00
Adam Treat
1dcd4dce58 Update the bundled model name. 2023-04-16 22:10:26 -04:00
Adam Treat
7ea548736b New version. 2023-04-16 19:20:43 -04:00