You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

History

Jared Van Bortel fc1a281381 modellist: fix bad copy-paste in ModelList::clone (#2011 ) s/contextLength/gpuLayers/ Fixes #2010 Signed-off-by: Jared Van Bortel <jared@nomic.ai>		6 months ago
..
cmake	fix references to old backend implementations	10 months ago
flatpak-manifest	appdata: update software description	11 months ago
hnswlib	LocalDocs version 2 with text embeddings.	10 months ago
icons	Complete revamp of model loading to allow for more discreet control by	7 months ago
metadata	models.json: fix Mistral OpenOrca filename	7 months ago
qml	add min_p sampling parameter (#2014 )	6 months ago
CMakeLists.txt	Bump version and release notes for v2.7.1	7 months ago
LICENSE	Moving everything to subdir for monorepo merge.	1 year ago
README.md	Updated chat wishlist (#1351 )	11 months ago
build_and_run.md	add fedora command for QT and related packages (#1871 )	8 months ago
chat.cpp	Add comment to make this clear.	7 months ago
chat.h	Complete revamp of model loading to allow for more discreet control by	7 months ago
chatgpt.cpp	fix chat-style prompt templates (#1970 )	7 months ago
chatgpt.h	fix chat-style prompt templates (#1970 )	7 months ago
chatlistmodel.cpp	Some cleanps	8 months ago
chatlistmodel.h	Complete revamp of model loading to allow for more discreet control by	7 months ago
chatllm.cpp	add min_p sampling parameter (#2014 )	6 months ago
chatllm.h	add min_p sampling parameter (#2014 )	6 months ago
chatmodel.h	Restore state from text if necessary.	11 months ago
database.cpp	database: limit supported extensions to txt, pdf, md, rst	7 months ago
database.h	Add Nomic Embed model for atlas with localdocs.	7 months ago
download.cpp	Fix bug with install of online models.	8 months ago
download.h	Networking retry on download error for models.	10 months ago
embeddings.cpp	Add Nomic Embed model for atlas with localdocs.	7 months ago
embeddings.h	LocalDocs version 2 with text embeddings.	10 months ago
embllm.cpp	Make sure to use the search_query tag for nomic embed.	7 months ago
embllm.h	Add Nomic Embed model for atlas with localdocs.	7 months ago
llm.cpp	Don't show the download button if we are not connected to an online network.	7 months ago
llm.h	Don't show the download button if we are not connected to an online network.	7 months ago
localdocs.cpp	Add Nomic Embed model for atlas with localdocs.	7 months ago
localdocs.h	LocalDocs version 2 with text embeddings.	10 months ago
localdocsdb.h	Begin implementing the localdocs ui in earnest.	1 year ago
localdocsmodel.cpp	Add Nomic Embed model for atlas with localdocs.	7 months ago
localdocsmodel.h	Add Nomic Embed model for atlas with localdocs.	7 months ago
logger.cpp	Logger should also output to stderr	1 year ago
logger.h	Implemented logging mechanism (#785 )	1 year ago
main.cpp	Maxwell/Pascal GPU support and crash fix (#1895 )	7 months ago
main.qml	add min_p sampling parameter (#2014 )	6 months ago
modellist.cpp	modellist: fix bad copy-paste in ModelList::clone (#2011 )	6 months ago
modellist.h	add min_p sampling parameter (#2014 )	6 months ago
mysettings.cpp	add min_p sampling parameter (#2014 )	6 months ago
mysettings.h	add min_p sampling parameter (#2014 )	6 months ago
network.cpp	Always save chats to disk, but save them as text by default. This also changes	11 months ago
network.h	Always save chats to disk, but save them as text by default. This also changes	11 months ago
responsetext.cpp	fixed issue of text color changing for code blocks in light mode (#1299 )	1 year ago
responsetext.h	Add code blocks and python syntax highlighting.	1 year ago
server.cpp	add min_p sampling parameter (#2014 )	6 months ago
server.h	Start working on more thread safety and model load error handling.	1 year ago

README.md

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.

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

Follow the visual instructions on the build_and_run page

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

You can find a 'Model Explorer' on the official website where you can manually download models that we support: https://gpt4all.io/index.html

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.