Datasets - Running AI tasks on files
Promptloop streamlines the process of applying AI models to your data. We do this with datasets. Upload a CSV or Excel file, select relevant inputs for the model to use, and launch AI tasks on hundreds to thousands of rows.
Datasets are where you will store, edit, and view data that you are processing with AI tasks.
Helpful Links
Getting Started
This video overview provides a guide of how to get started and take full advantage of datasets.
Files and Versions Datasets are where you can upload the data you are working with on the PromptLoop Platform.
Uploading You can upload data to launch a job, using an existing AI task, or upload a dataset to filter and analyze first before running.
Run an AI task on each row When you run an AI task on a dataset, the job will run in the background and save as a new version in the dataset when its complete. This will allow you to run tens of thousands of operations at once and freeing you up for other work.
If you have questions about limits, or have a task that requires a large amount of rows, reach out to the team here.
Reliable and Scalable Datasets are an extremely powerful feature available to all users and one of the core capabilities of how we think about leveraging AI models efficiently.
How to run an AI task on a spreadsheet file upload
Step 1: Upload a file with data
Datasets let you use any data table in an Excel or CSV file. Our systems automatically detect columns and let you select which you want to use.
- You can select the columns that you will use as inputs for the task - this is often a single column like a website or search term
- Results from your task - new columns or rows - will be added into the uploaded sheet and available to download as a new file
Step 2: Launch the Job
Select your task and launch the job with the correct input columns. Jobs are immediately added to the queue based on your account tier and capacity. You will see progress and results once the task is running. Even extremely large jobs usually complete within 90 minutes.
If you do not already have an AI task created, use the editor to create one or copy a template to edit from the template library. The task creation tool guides will help you get started.
Step 3: View results
Results are saved as a new dataset version for review. You can then search and filter data before exporting and using the results of the task. You can also run data on another task right from the datasets page.
For help setting up your first datasets, or questions about capacity and running large files, reach out the the team or book time with us to let us help you. Book a Session
Integrations
Hubspot
To connect to hubspot you need a team subscription. The connection is shared across the team, so only one team member will need to connect.
The Hubspot integration can be found under the Integration tab of the settings section.
Connecting to Hubspot
Promptloop uses a standard oauth connection with hubspot. From your logged in promptloop settings page select the orange 'Connect to Hubspot' button. This will bring you to hubspot where you will give Promptloop permission to view and edit your Company values. These values are never edited without user selection.
After accepting the connection you should be redirected to the Integrations page and should now see 'Connected' along with options to Import List from Hubspot and Set up Autosync.
Importing a list from Hubspot
Upon selection of this you can either choose an existing list to import, or select your entire list of companies. Once you select the source, you can choose which columns to import. We recommend only importing the needed columns, as otherwise the resulting dataset will be unnecessarily large. The unique hubspot identifier is always imported so that the records can be updated after you run a Promptloop task on them. After confirming which columns you want to import select Import. This can take anywhere from 1 - 5 minutes depending on the size of the list. If you reload the integrations page you will see your list import in progress. Once it says Synced you can click the link to go to the dataset. You can now run any task on this data. Be sure to not delete the hs_object_id column.
Updating a dataset to Hubspot
Whenever you are ready you can select Sync to Hubspot from the dataset page. You will be able to select which of the dataset columns you want to update into Hubspot and then select the corresponding Hubspot column. If you want to create a new column, you can toggle new. Then click Sync. This will update each record in the dataset, using the selected version.
Disconnecting Hubspot
To disconnect hubspot select the disconnect button and follow the prompts.