Flowise - Visual Building of LLM Applications

Flowise is a low-code/no-code drag-and-drop tool that helps people easily visualize and build LLM applications.

LLM applications have wide applications in many industries, from finance to healthcare, to retail and logistics. With FlowiseAI, even those without programming experience can create these applications without writing any code. This is also beneficial for organizations striving to quickly prototype and develop LLM applications in an agile way.

Let’s take a look at some of the standout features of Flowise AI:

Drag-and-drop UI: Flowise makes designing your own custom LLM workflows simple.
Open-source: As an open-source project, Flowise can be freely used and modified.
User-friendly: Flowise is easy to get started with, even for those without coding experience.
Versatile: Flowise AI can be used to create various LLM applications.

Installation and Setup

To install and start using Flowise, follow these steps:

Download and install NodeJS >= 18.15.0 (check your installed version using node -v; if it’s not high enough, I recommend resolving the issue directly on this page: https://nodejs.org/en/download)
Install Flowise using the following command: npm install -g flowise.
Start Flowise: npx flowise start, use username and password to start: npx flowise start --FLOWISE_USERNAME=user --FLOWISE_PASSWORD=1234.
Open http://localhost:3000 in your browser

If you have a Docker environment, it’s more convenient to start with Docker.

Docker Compose

Navigate to the docker folder in the project root directory
Create a .env file and specify PORT (refer to .env.example)
Run docker-compose up -d
Open http://localhost:3000
You can stop the container using docker-compose stop

Docker Image

Build the image locally: docker build --no-cache -t flowise .
Run the image: docker run -d --name flowise -p 3000:3000 flowise
Stop the image: docker stop flowise

Flowise supports a rich set of components.

Example 1: Building a Basic LLM Chain

On a blank canvas, click the + Add New button to bring up the left-side Add Nodes panel.

Select the following components from the Add Nodes panel, which will appear on the canvas.

Drag OpenAI from LLMs to the panel
Drag LLM chain from the Chains category
Drag Prompt Template from the Prompts category

Now, the canvas should look like this:

Connect the components

Link the output of OpenAI to the language model of LLM Chain
Link the output of Prompt Template to the Prompt of LLM Chain

Enter the necessary information

Enter your OpenAI key in the OpenAI field
Write the following prompt template in the Prompt Template Template field: What is a good name for a company that makes {product}?
Give a name to the LLM Chain
Click the save icon in the top right corner to save
Click the chat icon in the top right corner to start sending “product names”. Here, we got the expected answer

Example 2: Building a PDF Reader Bot

Now, let’s create a PDF reading bot using Flowise.

Add the following components to the blank canvas:

Select Recursive Character Text Splitter from Text Splitters
Select PDF file from Document Loaders
Select OpenAI Embeddings from Embeddings
Select In-memory Vector Store from Vector Stores
Select OpenAI from LLMs
Select Conversational Retrieval QA Chain from Chains

Now we have all the necessary components on the canvas.

Connect the components

Link the output of Recursive Character Text Splitter to the input of PDF file
Link the output of PDF file to the input of In-memory Vector Store
Link the output of OpenAI Embeddings to the input of In-memory Vector Store
Link the output of In-memory Vector Store to the input of Conversational Retrieval QA Chain
Link the output of OpenAI to the input of Conversational Retrieval QA Chain

Enter the necessary information

Click Upload File in PDF File, upload the sample PDF file titled Introduction to AWS Security.
Enter your OpenAI key in the OpenAI and OpenAI Embeddings fields
Click the save button and then click the chat button to start sending requests.

The response should be as expected, and the bot can now answer any questions related to this PDF document.

For more uses of Flowise, refer to the official documentation: https://docs.flowiseai.com/ for more information.

Reference Documentation

GitHub repository: https://github.com/FlowiseAI/Flowise

Flowise – Visual Building of LLM Applications