dvcrn / chatgpt-ui Goto Github PK
View Code? Open in Web Editor NEWChatGPT UI with auth, OpenAI, Claude, Gemini support, written in Elixir + LiveView
License: MIT License
ChatGPT UI with auth, OpenAI, Claude, Gemini support, written in Elixir + LiveView
License: MIT License
Absolutely love the idea of this application so kudos to you. I'm just having a play round with the code and from initial clone I receive the following error:
`[ERROR] Could not resolve "highlight.js"
js/app.js:24:17:
24 │ import hljs from "highlight.js";
╵ ~~~~~~~~~~~~~~
You can mark the path "highlight.js" as external to exclude it from the bundle, which will remove this error.
1 error
[watch] build finished, watching for changes...
Error: Failed to find '../../node_modules/highlight.js/styles/googlecode.css'
in [
/Users/g/code/elixir/chatgpt-ui/assets/css
]
at /snapshot/tailwindcss/node_modules/postcss-import/lib/resolve-id.js:35:13
at async LazyResult.runAsync (/snapshot/tailwindcss/node_modules/postcss/lib/lazy-result.js:396:11)
at async Object.watch (/snapshot/tailwindcss/lib/cli/build/plugin.js:359:13)
at async build (/snapshot/tailwindcss/lib/cli/build/index.js:40:9)
`
Am I missing something obvious here? Apologies if so - still learning.
Thanks for the awesome project!
Any thoughts on allow chaining similar to langchain as well as persistence?
There's a demo here that includes what I think is a pretty good approach to persistence: https://github.com/brainlid/langchain_demo
Maybe Scenarios here could pull it's settings from a scenarios database table and "conversations" saved under a "History" section?
Also related: #6
Thank you for the nice work!
I faced a problem in running via docker.
I followed the setup procedure
# Clone the project
git clone https://github.com/dvcrn/chatgpt-ui
cd chatgpt-ui
# Install Elixir
mix deps.get
# Install node dependencies
yarn install # or npm install
mix assets.setup
mix assets.build
# Start the dev server
export OPENAI_API_KEY=<api-key>
export OPENAI_ORGANIZATION_KEY=<org-key>
mix phx.server
and successfully running.
but when I follow the docker procedure,
docker build . -t chatgpt
docker run -e SECRET_KEY_BASE=<keybase here> -e HOST="localhost" -p 4000:4000 chatgpt
it's stuck at
05:30:11.447 [info] Running ChatgptWeb.Endpoint with cowboy 2.9.0 at :::4000 (http)
05:30:11.447 [info] Access ChatgptWeb.Endpoint at https://localhost
05:30:11.447 [info] downloading tokenizer model: bert-base-multilingual-uncased
Is there any missing step?
chatgpt-ui/lib/chatgpt/openai.ex
Line 16 in 04b5854
I have a question regarding
defp new_msg(m) do
%ExOpenAI.Components.ChatCompletionRequestMessage{
content: m,
role: :user,
name: "user"
}
end
@spec role(String.t()) :: atom()
defp role(r) when is_binary(r), do: String.to_atom(r)
@spec role(atom()) :: atom()
defp role(r) when is_atom(r), do: r
@spec to_domain(ExOpenAI.Components.ChatCompletionResponseMessage.t()) :: Message.t()
defp to_domain(msg) do
%Message{
content: msg.content,
sender: role(msg.role),
id: 0
}
end
@spec from_domain(Message.t()) :: ExOpenAI.Components.ChatCompletionRequestMessage.t()
defp from_domain(msg) do
%ExOpenAI.Components.ChatCompletionRequestMessage{
content: msg.content,
role: role(msg.sender)
}
end
It should now be using either ChatCompletionRequestUserMessage
or ChatCompletionRequestAssistantMessage
instead of ChatCompletionRequestMessage
right?
Hi, I'm trying to deploy it to a free Gigalixir account and I get a Segmentation fault error. Is it possible to deploy on Gigalixir?
[debug] NIF cached at /app/.cache/rustler_precompiled/precompiled_nifs/libex_tokenizers-v0.3.0-nif-2.15-x86_64-unknown-linux-gnu.so.tar.gz and extracted to /tmp/build/_build/prod/lib/tokenizers/priv/native/libex_tokenizers-v0.3.0-nif-2.15-x86_64-unknown-linux-gnu.so
remote: /tmp/buildpackKbgln/lib/app_funcs.sh: line 89: 651 Segmentation fault (core dumped) mix compile --force
remote: 2024/03/05 09:05:52 exit status 1
remote: Deploy aborted
I wasn't able to find a license for this repo. Is there a license already? If not I would suggest MIT. I'm happy to add one and send a PR
Something I've discovered through use that is a great feature is persistence of chats (i.e. chat history). Have you considered adding storage of chat history in postgres or something beyond the browser?
Just thinking through it a bit, it may require some UI changes since it wouldn't take long until the history was cluttered so might not be a trivial addition, but figured it was worth bringing up.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.