📢April 2023 release
This latest april release includes several UX changes, new general project settings, new filters for tasks and validation queues and customizable parsing logic and OCR score moved to preview stage.
Last updated
This latest april release includes several UX changes, new general project settings, new filters for tasks and validation queues and customizable parsing logic and OCR score moved to preview stage.
Last updated
We introduced a new "General settings" section in the project settings that will allow you to manage more general project settings.
⚙️General SettingsYou can now easily modify the name of your project right from the "General Settings" section.
To change the name of your project, simply click on the text field within the "General Settings" section, enter the new name you'd like to use, and then click the save button. That's it! Your project will now display the new name you've chosen.
We are giving you more control over the upload status of your projects.
Previously, Metamaze would automatically decide whether an upload was processed or failed. But now, we're opening up that black box and giving you the power to decide how the processed and failed status is determined on a project-by-project basis. This means that you can better manage your projects and ensure that they're running as smoothly as possible.
In this latest release of the Metamaze platform, we're excited to introduce a new feature that will make manual annotations even easier to manage. You can now edit the value for manual annotations directly from the tooltip, without having to navigate to a separate screen.
This streamlines the process of editing manual annotations and makes it more intuitive and user-friendly. You'll be able to make changes to your annotations more quickly and efficiently, which will save you time and effort.
We're excited to announce a new feature that will make it easier for you to create unique tasks. With the new "Documents in Tasks" filter, you can now exclude documents from existing tasks when creating new tasks.
This new filter will help you avoid overlap of documents between tasks and ensure that your tasks are completely unique. It's a great way to keep your workflow organized and avoid any potential issues that can arise when working on multiple tasks at once.
📋TasksYou can now filter the document classification and entity extraction queues based on a date range, making it easier to find your uploads.
In addition, we've added a new filter that allows you to filter the document classification queue based on document type. This feature is particularly useful for teams with multiple validators who specialize in handling specific document types.
We expanded the tooltip so you can use the "Copy without spaces" button to quickly copy values without any spaces in between.
This feature is particularly useful for users who need to copy a value from the document without needing an entity for it. For example, copy an email address from a document to send an email.
We've made significant improvements to the way the threshold settings work in the project settings. We've redesigned the interface to make it more intuitive and easier to work with.
With these changes, you'll find it easier than ever to fine-tune the threshold settings for your projects. We're confident that this new approach will help you get the most out of the Metamaze platform and improve your overall user experience.
We're always looking for ways to improve the Metamaze platform and make it more useful for our users. If you have any feedback or suggestions on how we can further improve the threshold settings or any other aspect of the platform, please don't hesitate to let us know. We value your input and are committed to providing you with the best possible user experience.
👤Human validationThe customizable parsing logic has moved to the preview stage. If you want to use this new and vastly improved parser you can enable the feature flag in the project settings. You can fine-tune the parsing logic for each of your projects. We understand that the default parser may not always be sufficient when it comes to handling numbers and dates in your documents. That's why we've exposed the entire parsing logic, so you can customize it to better fit your needs.
📃ParsingThe latest update will move the OCR score inclusion option in the confidence scores to the preview stage. This feature helps to measure the accuracy of the extracted text, allowing you to consider the quality of the text extraction process when determining the confidence level of an entity's prediction. However, it's important to note that adding the OCR score might lead to a lower overall confidence score.
👤Human validation
