Image by Author
The hype around large language models (LLMs) is continuing to grow, with more and more companies releasing tools to make people’s life easier. So what exactly are these tools that are helping build the world of LLMs? Well, one of them is Flowise AI
Flowise AI is an open-source UI visual tool used to help develop LangChain apps. Before we get into more about Flowise AI, let’s quickly define LangChain. LangChain is a framework/python library that helps you make use of LLMs to build your own custom NLP applications.
Flowise uses LangChain as its agent executor, Chroma as its vector store, OpenAI for embeddings, HuggingFace’s inference model, GitHub as a document loader, and SERP for query API. Its Graphic User Interface is very helpful in constructing LLM-based apps built on LangChain.js.
So what makes it so easy and helpful? The drag-and-drop tool. Everybody loves a drag-and-drop, especially when you are customizing your NLP application. The even bigger plus is that it does not require any coding experience!
Image by Flowise AI
You can build several apps with Flowise AI, such as:
- Virtual assistants
- Data analysis tools
- Educational tools
- Simplicity: The drag-and-drop tool makes it easy to construct your own LLM flows.
- No coding skills required: This is highly useful to new people in the industry and organizations that do not have developers on the team.
- Open source: Free to use and modify, allowing you to tailor it to your own requirements.
- Powerful: The tool can be used to develop a wide range of LLM applications.
- Community: Flowise is backed by a supportive development community, which can assist you in your process of making the most out of Flowise.
So how do I install this simple drag-and-drop customisable NLP tool? So there are 3 different ways you can install Flowise AI. Let’s go through all of them.
- First, you will need to download and install NodeJS >= 18.15.0.
- Once this is done, you need to install Flowise
- Your next step is to start Flowise
You will need to enter a username and password:
npx flowise start --FLOWISE_USERNAME=user --FLOWISE_PASSWORD=1234
- Once that is done, you can open it up on a webpage by opening:
If you prefer to use Docker, follow the next part.
- First, you need to go to docker folder at the root of the project
- Then you need to create .env file and specify the PORT (refer to .env.example)
- You will then need to execute: docker-compose up -d
- Then you will need to open http://localhost:3000
- You can bring the containers down by docker-compose stop
- First, you will need to build the image locally:
docker build --no-cache -t flowise .
- Then you will need to run the image:
docker run -d --name flowise -p 3000:3000 flowise
- To stop the image, you need to:
Local Setup for Developers
- First, you will need to Install Yarn v1 by:
- You will then need to clone the repository:
git clone https://github.com/FlowiseAI/Flowise.git
- Go into the repository folder:
- Make sure to install all the dependencies of all models:
- You will then need to build all the code:
- You can then start the app:
- You can access the app on:
- For development build, use:
So if you’re somebody new to the tech industry and have no coding experience or an organization that lacks a developer on your team – Flowise AI is the best option for you. If there are any current or previous users of Flowise reading this, let us know about your experience in the comments!
Nisha Arya is a Data Scientist, Freelance Technical Writer and Community Manager at KDnuggets. She is particularly interested in providing Data Science career advice or tutorials and theory based knowledge around Data Science. She also wishes to explore the different ways Artificial Intelligence is/can benefit the longevity of human life. A keen learner, seeking to broaden her tech knowledge and writing skills, whilst helping guide others.