gpt4all/gpt4all-chat
AT 66bc04aa8e
chat: generate follow-up questions after response (#2634)
* user can configure the prompt and when they appear
* also make the name generation prompt configurable

Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-07-10 15:45:20 -04:00
..
cmake Add initial template windows signing flow (#2443) 2024-07-01 17:40:02 -04:00
flatpak-manifest Update appdata.xml (#2307) 2024-05-09 12:51:38 -04:00
icons chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
metadata release.json: update release notes for v3.0.0 (#2514) 2024-07-02 12:08:23 -04:00
qml chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
resources additional new ui changes, part 4 (#2481) 2024-06-28 17:11:12 -04:00
usearch@22cfa3bd00 chat: fix build on Windows and Nomic Embed path on macOS (#2467) 2024-06-25 17:22:51 -04:00
build_and_run.md support the llama.cpp CUDA backend (#2310) 2024-05-15 15:27:50 -04:00
chat.cpp chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
chat.h chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
chatapi.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
chatapi.h chat: don't use incomplete types with signals/slots/Q_INVOKABLE (#2408) 2024-06-06 11:59:28 -04:00
chatlistmodel.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
chatlistmodel.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
chatllm.cpp chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
chatllm.h chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
chatmodel.h qml: fix hang in ChatView by processing text explicitly (#2543) 2024-07-08 17:24:02 -04:00
chatviewtextprocessor.cpp qml: fix hang in ChatView by processing text explicitly (#2543) 2024-07-08 17:24:02 -04:00
chatviewtextprocessor.h qml: fix hang in ChatView by processing text explicitly (#2543) 2024-07-08 17:24:02 -04:00
CMakeLists.txt chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
database.cpp new UI fixes, part 5 (#2485) 2024-06-28 20:34:03 -04:00
database.h chat: fix incorrect file URIs for sources on Windows (#2469) 2024-06-26 14:48:02 -04:00
download.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
download.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
embllm.cpp UI and embedding device changes for GPT4All v3.0.0-rc3 (#2477) 2024-06-28 12:57:57 -04:00
embllm.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
LICENSE Update the license. 2024-06-26 15:07:51 -04:00
llm.cpp chat: fix build on Windows and Nomic Embed path on macOS (#2467) 2024-06-25 17:22:51 -04:00
llm.h chat: fix #includes with include-what-you-use (#2401) 2024-06-04 14:47:11 -04:00
localdocs.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
localdocs.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
localdocsmodel.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
localdocsmodel.h chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
logger.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
logger.h chat: fix #includes with include-what-you-use (#2401) 2024-06-04 14:47:11 -04:00
main.cpp chat: major UI redesign for v3.0.0 (#2396) 2024-06-24 18:49:23 -04:00
main.qml qml: improve chats with missing models and model settings layout (#2520) 2024-07-08 17:01:30 -04:00
modellist.cpp chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
modellist.h chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
mysettings.cpp chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
mysettings.h chat: generate follow-up questions after response (#2634) 2024-07-10 15:45:20 -04:00
network.cpp chat: fix blank device in UI and improve Mixpanel reporting (#2409) 2024-06-26 15:26:27 -04:00
network.h chat: don't use incomplete types with signals/slots/Q_INVOKABLE (#2408) 2024-06-06 11:59:28 -04:00
qa_checklist.md Update qa_checklist.md 2024-06-25 13:50:19 -04:00
README.md Updated chat wishlist (#1351) 2023-10-12 14:01:44 -04:00
server.cpp GPT4All Chat server API: add errors 405 Method Not Allowed (#2615) 2024-07-09 13:08:20 -04:00
server.h chat: don't use incomplete types with signals/slots/Q_INVOKABLE (#2408) 2024-06-06 11:59:28 -04:00

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.