Morphik provides a graphical user interface so that you can interact directly with your ingested data. This includes support for ingesting documents, retrieving relevant information, chatting with your documents, and visualizing/creating knowledge graphs. In this guide, we’ll walk you through how you can set up the Morphik UI and start ingesting!

Prerequisites

Morphik Server

Before you begin, ensure that you have the Morphik server running. You can do this by following the instructions in the Getting Started guide. To verify that the Morphik server is running, check the [api] header in the databridge.toml file (found in the root of the morphik-core repository). If you see the server options when you open http://<host>:<port>/docs, then the server is live! By default, the heading should look like:

[api]
host = "localhost" # Needs to be "0.0.0.0" for docker
port = 8000

So, if the configuration is the same as above, we can navigate to http://localhost:8000/docs to access the Morphik UI. Here’s what it should look like:

Excuse the additional tabs on Chrome - who knew running an open-source repo full-time required so much context switching? (No seriously, I’m asking 🤣)

In case you don’t see this, and have followed all the steps in the Getting Started guide, feel free to contact us.

Node and NPM

In order to launch the UI, ensure that you have node and npm installed. A good way to check this is just by running node -v and npm -v in your terminal. If you don’t have node installed, you can view installation instructions here.

Running the UI

You’re ready to launch the UI once you have the server running and npm installed. In a new terminal (ensure that the server is running and not stopped), navigate to the root of the morphik-core repository that you launched the server from. From here change directory into the ui-component folder:

cd ui-component

Now, install the required node dependencies:

npm i

Finally, you’re ready to run the UI component:

npm run dev

You should see the following output (or something similar):

(base) arnav@Arnavs-MacBook-Air ui-component % npm run dev

> @databridge/ui@0.1.0 dev
> next dev

  ▲ Next.js 14.2.26
  - Local:        http://localhost:3000

 ✓ Starting...
 ✓ Ready in 1560ms

If that’s the case, you’ve done it! Navigate to http://localhost:3000, and you should be greeted with Morphik’s UI! It should look something like this:

Clicking on a file should get you some of its information on the right.

Using the UI - Features we ❤️

Morphik has support for automatic metadata extraction at file ingestion time. You can define a json schema, and then Morphik will automatically extract the metadata from the file:

Chunk searching - perfect for testing and iterating on retrieval strategies:

Visualize your knowledge graphs to better understand the relationships between your data: