gpt4all/gpt4all-chat
Karthik Nair 0a45dd384e
add fedora command for QT and related packages (#1871)
Signed-off-by: Karthik Nair <realkarthiknair@gmail.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
2024-01-24 18:00:49 -05:00
..
cmake fix references to old backend implementations 2023-10-30 10:37:05 -04:00
flatpak-manifest appdata: update software description 2023-10-05 10:12:43 -04:00
hnswlib LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
icons Add a nicer message. 2023-07-09 15:51:59 -04:00
metadata Add the new 2.6.1 release notes and bump the version. 2024-01-12 11:10:16 -05:00
qml Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
build_and_run.md add fedora command for QT and related packages (#1871) 2024-01-24 18:00:49 -05:00
chat.cpp Some cleanps 2024-01-03 08:41:40 -06:00
chat.h Some cleanps 2024-01-03 08:41:40 -06:00
chatgpt.cpp Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
chatgpt.h Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
chatlistmodel.cpp Some cleanps 2024-01-03 08:41:40 -06:00
chatlistmodel.h Some cleanps 2024-01-03 08:41:40 -06:00
chatllm.cpp chatllm: fix deserialization version mismatch (#1859) 2024-01-22 10:01:31 -05:00
chatllm.h MPT: use upstream llama.cpp implementation (#1515) 2023-10-19 15:25:17 -04:00
chatmodel.h Restore state from text if necessary. 2023-10-11 09:16:02 -04:00
CMakeLists.txt Add the new 2.6.1 release notes and bump the version. 2024-01-12 11:10:16 -05:00
database.cpp LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
database.h LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
download.cpp Fix bug with install of online models. 2024-01-22 14:16:09 -05:00
download.h Networking retry on download error for models. 2023-11-21 16:30:18 -05:00
embeddings.cpp Update gpt4all-chat/embeddings.cpp 2023-11-17 11:59:31 -05:00
embeddings.h LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
embllm.cpp Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
embllm.h LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
LICENSE Moving everything to subdir for monorepo merge. 2023-05-10 10:26:55 -04:00
llm.cpp restore network.h #include 2024-01-12 09:27:48 -05:00
llm.h chat: set search path early 2024-01-11 12:04:18 -05:00
localdocs.cpp LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
localdocs.h LocalDocs version 2 with text embeddings. 2023-11-17 11:59:31 -05:00
localdocsdb.h Begin implementing the localdocs ui in earnest. 2023-05-25 11:28:06 -04:00
localdocsmodel.cpp Reduce copied code. 2023-11-17 11:59:31 -05:00
localdocsmodel.h Reduce copied code. 2023-11-17 11:59:31 -05:00
logger.cpp Logger should also output to stderr 2023-06-01 14:15:11 -04:00
logger.h Implemented logging mechanism (#785) 2023-06-01 16:50:42 +02:00
main.cpp chat: set search path early 2024-01-11 12:04:18 -05:00
main.qml Add a button to the collections dialog. Fix close button. 2023-11-22 09:10:44 -05:00
modellist.cpp Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
modellist.h Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
mysettings.cpp Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
mysettings.h Implement configurable context length (#1749) 2023-12-16 17:58:15 -05:00
network.cpp Always save chats to disk, but save them as text by default. This also changes 2023-10-12 07:52:11 -04:00
network.h Always save chats to disk, but save them as text by default. This also changes 2023-10-12 07:52:11 -04:00
README.md Updated chat wishlist (#1351) 2023-10-12 14:01:44 -04:00
responsetext.cpp fixed issue of text color changing for code blocks in light mode (#1299) 2023-07-31 12:18:19 -04:00
responsetext.h Add code blocks and python syntax highlighting. 2023-06-11 14:20:05 -07:00
server.cpp Update server.cpp to return valid created timestamps (#1763) 2023-12-18 14:06:25 -05:00
server.h Start working on more thread safety and model load error handling. 2023-06-20 14:39:22 -03:00

gpt4all-chat

Cross platform Qt based GUI for GPT4All versions with GPT-J as the base model. NOTE: The model seen in the screenshot is actually a preview of a new training run for GPT4All based on GPT-J. The GPT4All project is busy at work getting ready to release this model including installers for all three major OS's. In the meantime, you can try this UI out with the original GPT-J model by following build instructions below.

image

Install

One click installers for macOS, Linux, and Windows at https://gpt4all.io

Features

  • Cross-platform (Linux, Windows, MacOSX)
  • Fast CPU based inference using ggml for GPT-J based models
  • The UI is made to look and feel like you've come to expect from a chatty gpt
  • Check for updates so you can always stay fresh with latest models
  • Easy to install with precompiled binaries available for all three major desktop platforms
  • Multi-modal - Ability to load more than one model and switch between them
  • Supports both llama.cpp and gptj.cpp style models
  • Model downloader in GUI featuring many popular open source models
  • Settings dialog to change temp, top_p, top_k, threads, etc
  • Copy your conversation to clipboard
  • Check for updates to get the very latest GUI

Feature wishlist

  • Multi-chat - a list of current and past chats and the ability to save/delete/export and switch between
  • Text to speech - have the AI response with voice
  • Speech to text - give the prompt with your voice
  • Plugin support for langchain other developer tools
  • chat gui headless operation mode
  • Advanced settings for changing temperature, topk, etc. (DONE)
    • Improve the accessibility of the installer for screen reader users
  • YOUR IDEA HERE

Building and running

Getting the latest

If you've already checked out the source code and/or built the program make sure when you do a git fetch to get the latest changes and that you also do git submodule update --init --recursive to update the submodules.

Manual download of models

Terminal Only Interface with no Qt dependency

Check out https://github.com/kuvaus/LlamaGPTJ-chat which is using the llmodel backend so it is compliant with our ecosystem and all models downloaded above should work with it.

Contributing

  • Pull requests welcome. See the feature wish list for ideas :)

License

The source code of this chat interface is currently under a MIT license. The underlying GPT4All-j model is released under non-restrictive open-source Apache 2 License.

The GPT4All-J license allows for users to use generated outputs as they see fit. Users take responsibility for ensuring their content meets applicable requirements for publication in a given context or region.