step1
get the web
download from release page and unzip it
or
clone this repository, and then:
npm install
npm run build
and you will get a out/
dir.
step2
get llama.cpp server
if you are windows user, go to https://github.com/ggerganov/llama.cpp/releases to download a server.
or if you are not windows user, go to https://github.com/ggerganov/llama.cpp, clone, and make
.
step3
run
for windows
.\server.exe --model /PATH_TO_MODEL --path THE_OUT_DIR_YOU_JUST_BUILD
or else
./server --model /PATH_TO_MODEL --path THE_OUT_DIR_YOU_JUST_BUILD
and go to your browser: http://localhost:8080
change the language: in next-i18next.config.js, change defaultLocale
add more model: types/openai.ts
Chatbot UI 2.0 will launch on Monday January 8th, 2024.
See a preview.
This repo will be completely overhauled with the updated codebase.
The old codebase will be available in a new repo.
There will be several hours of downtime on ChatbotUI.com while the new version is deployed.
We recommend exporting your data before the update!
Chatbot UI is an open source chat UI for AI models.
See a demo.
Chatbot UI will be updated over time.
Expect frequent improvements.
Next up:
- Sharing
- "Bots"
Vercel
Host your own live version of Chatbot UI with Vercel.
Docker
Build locally:
docker build -t chatgpt-ui .
docker run -e OPENAI_API_KEY=xxxxxxxx -p 3000:3000 chatgpt-ui
Pull from ghcr:
docker run -e OPENAI_API_KEY=xxxxxxxx -p 3000:3000 ghcr.io/mckaywrigley/chatbot-ui:main
1. Clone Repo
git clone https://github.com/mckaywrigley/chatbot-ui.git
2. Install Dependencies
npm i
3. Provide OpenAI API Key
Create a .env.local file in the root of the repo with your OpenAI API Key:
OPENAI_API_KEY=YOUR_KEY
You can set
OPENAI_API_HOST
where access to the official OpenAI host is restricted or unavailable, allowing users to configure an alternative host for their specific needs.
Additionally, if you have multiple OpenAI Organizations, you can set
OPENAI_ORGANIZATION
to specify one.
4. Run App
npm run dev
5. Use It
You should be able to start chatting.
When deploying the application, the following environment variables can be set:
Environment Variable | Default value | Description |
---|---|---|
OPENAI_API_KEY | The default API key used for authentication with OpenAI | |
OPENAI_API_HOST | https://api.openai.com |
The base url, for Azure use https://<endpoint>.openai.azure.com |
OPENAI_API_TYPE | openai |
The API type, options are openai or azure |
OPENAI_API_VERSION | 2023-03-15-preview |
Only applicable for Azure OpenAI |
AZURE_DEPLOYMENT_ID | Needed when Azure OpenAI, Ref Azure OpenAI API | |
OPENAI_ORGANIZATION | Your OpenAI organization ID | |
DEFAULT_MODEL | gpt-3.5-turbo |
The default model to use on new conversations, for Azure use gpt-35-turbo |
NEXT_PUBLIC_DEFAULT_SYSTEM_PROMPT | see here | The default system prompt to use on new conversations |
NEXT_PUBLIC_DEFAULT_TEMPERATURE | 1 | The default temperature to use on new conversations |
GOOGLE_API_KEY | See Custom Search JSON API documentation | |
GOOGLE_CSE_ID | See Custom Search JSON API documentation |
If you do not provide an OpenAI API key with OPENAI_API_KEY
, users will have to provide their own key.
If you don't have an OpenAI API key, you can get one here.
If you have any questions, feel free to reach out to Mckay on Twitter.