Flowise – LangchainJS UI
Drag & drop UI to build your customized LLM flow using LangchainJS
β‘Quick Start
Download and Install NodeJS >= 18.15.0
-
Install Flowise
npm install -g flowise
-
Start Flowise
npx flowise start
With username & password
npx flowise start --FLOWISE_USERNAME=user --FLOWISE_PASSWORD=1234
π³ Docker
Docker Compose
- Go to
docker
folder at the root of the project - Create
.env
file and specify thePORT
(refer to.env.example
) docker-compose up -d
- Open http://localhost:3000
- You can bring the containers down by
docker-compose stop
Docker Image
-
Build the image locally:
docker build --no-cache -t flowise .
-
Run image:
docker run -d --name flowise -p 3000:3000 flowise
-
Stop image:
docker stop flowise
π¨βπ» Developers
Flowise has 3 different modules in a single mono repository.
server
: Node backend to serve API logicsui
: React frontendcomponents
: Langchain components
Prerequisite
- Install Yarn
npm i -g yarn
Setup
-
Clone the repository
git clone https://github.com/FlowiseAI/Flowise.git
-
Go into repository folder
cd Flowise
-
Install all dependencies of all modules:
yarn install
-
Build all the code:
yarn build
-
Start the app:
yarn start
You can now access the app on http://localhost:3000
-
For development build:
yarn dev
Any code changes will reload the app automatically on http://localhost:8080
π Authentication
To enable app level authentication, add FLOWISE_USERNAME
and FLOWISE_PASSWORD
to the .env
file in packages/server
:
FLOWISE_USERNAME=user
FLOWISE_PASSWORD=1234
π Documentation
π Self Host
Railway
Render
AWS
DigitalOcean
GCP
π» Cloud Hosted
Coming soon
π Support
Feel free to ask any questions, raise problems, and request new features in discussion
π Contributing
See contributing guide. Reach out to us at Discord if you have any questions or issues.
π License
Source code in this repository is made available under the MIT License.