We're excited to share the latest product updates and announcements designed to improve your experience with our products. This month's releases include...
- Tonic Ephemeral launches with free trials 🚀
- Expanded file-type support on Tonic Textual 📄
- New Database View in Tonic Structural 👀
- Enhanced Privacy Report 🔏
- and Tonic Validate integrates with LlamaIndex!
Tonic Ephemeral launches with free trials 🚀
Last month, we launched Tonic Ephemeral with a webinar and several articles addressing how it helps teams manage the costs of isolated data environments, as well as how it compares to what some call “data virtualization.” Ephemeral makes it easy for developers to spin up fully hydrated test and development databases for ephemeral test environments so you can work more efficiently while keeping costs under control. We're now offering free trials to get you up and running with the data you need today—sign up here.
Expanded file-type support in Tonic Textual 📄
Sensitive free-text data in need of redaction? We’ve got your data covered with Tonic Textual. Textual combines the power of Tonic’s data generator technology with the latest in named entity recognition (NER). Textual offers the data privacy and accessibility you know and love from Tonic by way of a new platform that's purpose-built for building and testing your data pipelines and preventing sensitive data leakage or model memorization.
We’ve been hard at work training our named entity recognition models to provide you with more accurate, faster, and context- and format-independent automatic sensitive entity recognition and redaction than open source models. Just connect your unstructured or semi-structured free-text data, configure your redaction and synthesis preferences, and let our models do the rest, at scale.
- Additional format support. Textual now supports the following file formats: .txt, .csv, .pdf, .doc, .docx, and .json.
- Additional entity support. Textual has recently added support for the following entity types: LOCATION_ADDRESS, LOCATION_CITY, LOCATION_STATE, LOCATION_ZIP, NAME_GIVEN, NAME_FAMILY
If you’re working with sensitive data in free-text files, we’d love to hear more about your needs in this space. Sign up to take the platform for a spin or book a demo with our engineers to explore Textual’s full capabilities.
New Database View in Tonic 👀
Our database view has a new look designed to make it easier to apply generator suggestions and get to high quality data faster. Check out the Search and Filtering capabilities which now offer more options and are easier to navigate. This update aligns the UI with recent changes we made to Tonic’s Bulk Apply feature to provide a more streamlined workflow for reviewing and configuring generators. Take a look, assign some generators, and let us know what you think!
Enhanced Privacy Report 🔏
If you’ve ever asked us, “How private is this generator?” this update is for you. We’ve rolled out a new privacy ranking in Tonic’s Privacy Report to give you the answer right where you need it. The ranking scores your configuration of Tonic’s generators on a scale of 1-6 to define how private your current configuration is. A ranking of 1 indicates that all traces of the original data have been deleted; a ranking of 6 indicates that you’re passing through the original data. Checking in on your generator configuration rankings can help you determine which generator to assign, to match the privacy needs of your data. You’ll find the privacy ranking for each of your columns in the revamped Privacy Report.
Need the Privacy Report on the go? You can now access a downloadable PDF that summarizes the state of de-identification in your database. It’s useful if you’re a Tonic user who wants to see how many columns are protected, but also if you need a report to send to executive stakeholders to give them peace of mind that all sensitive data has been protected.
Tonic Validate integrates with LlamaIndex
Tonic Validate, our recently released product for evaluating the performance of your RAG-enhanced LLMs, is now integrated with the popular LlamaIndex. We’re meeting you where you’re building your RAG systems by integrating our advanced benchmarking metrics directly into one of the most popular open-source RAG development frameworks. Tonic Validate’s advanced metrics are now available as a subclass of LlamaIndex’s BaseEvaluator class. Check out all the latest and sign up for an account to get started for free.
Small Updates; Big Impacts
Often it's the little things that matter most. Here's a round up of our smaller releases:
- You've been showing our BigQuery connector a lot of love, so we wanted to send the feels back your way with enhanced functionality:
- For those of you who only have access to BigQuery data via views, we’ve got your back. Tonic will now work on BigQuery views similar to how it would work on a BigQuery table.
- You can now use the preserve destination table mode in BigQuery
- When using table filters in BigQuery, you can now use sub-queries to provide more complex filters.
- For the Custom Categorical generator, you can now add a NULL value to the available custom category values. To indicate a NULL value, use the keyword {NULL}.
- We've updated the sensitivity scan to better identify company and organization names and suggest the appropriate generator—no more confusion between people and companies. 🏢
- The Conditional Generator is now supported on Databricks version 11.3+! 🎉
As always, we'd love to hear your feedback on our products. What do you need? What do you love? What could be better? Send us a note at hello@tonic.ai! And for all the latest updates, be sure to check out our complete release notes in our product docs.
.png)
