Quickstart
Build your first VolansDB Agent in under 5 minutes
Build an Image Extraction Agent
Each VolansDB Agent uses an Engine that defines which tasks this agent will tackle. Our built-in Engines are optimized for their respective functions. In this example, we will use our Image Extraction Engine to extract data from images.
Create an Agent
Click on the “Add Agent” button in the top right corner of the Agents page.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/add-agent.png)
Enter a name and an optional description of your Agent.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-config-basics.png)
Choose an Engine
Select the Image Extraction Engine.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-config-engine.png)
Configurations
Each engine comes with two default settings for your Agents:
- Agent Input Definition: Defines the inputs that your Agent must accept when running a job. You can define the input key and its type as well as add or remove inputs. All defined inputs must be passed in a value when running the Agent. Learn more about Input Definitions.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-config-inputs.png)
Agent Inputs
- Engine Configuration: Configurations specific to your selected Engine. This sets things like which AI model or prompt instructions the Agent will use when running jobs. You can also dyanmically define the Engine configurations at runtime by using template strings of the Agent input keys. Learn more about configuring Engines.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-config-dynamic-inputs.png)
Example of dynamic Engine configurations
In our example, let’s remove the model
Agent input, fix
gpt-4o
as our model for this Agent, and leave the other Engine configurations as is.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-config-remove-model-input.png)
Remove the model Agent input
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-config-choose-model.png)
Instead of setting the model dynamically at runtime using an Agent input, we fix it to always use gpt-4o in the configuration
Create the Agent
Hit the Create button. Woohoo, you just built your first Agent! Now, let’s run it.
Run Your Image Extraction Agent
There are three ways to run your Agent:
We will run the agent through the UI:
Go to the Agent's details page
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-view.png)
Create a new Agent job
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-new-job.png)
Fill in the Agent inputs
Paste in the following text for the instruction input field:
Describe the image in one sentence.
Output in the following structure:
```
{
"description": "<description of the image>"
}
```
Then pick an image to upload to the image input field. You can use the one below.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/san-francisco.jpg)
san-francisco.jpg
Here is the filled-in Agent inputs:
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-create-job.png)
Run the job
Hit the Create button at the bottom. Hell yeah, your first Agent job has been kicked off!
View Results
You can view the status of your Agent job in its details page.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-jobs-list.png)
Click view to check the job result.
![](https://mintlify.s3-us-west-1.amazonaws.com/roeai/images/agent-job-detail.png)