Hello, dear community!
We are thrilled to announce Private AI’s final release of 2023 with Version 3.6. Let’s explore what’s new and enhanced in this version.
Improved Connectivity and Performance with WebSocket
Clients are now able to connect over WebSocket. WebSocket provides a full-duplex communication channel over a single TCP connection, improving large-volume data processing. This feature is now available in Beta. For more information, check out the WebSocket Guide.
Audio Processing with Voice Distortion
Audio redaction now includes the ability to perform Voice Distortion. Voice distortion makes it harder to identify the speaker. Take a look at the Audio Processing Guide for more information.
New Platform Accuracy Defaults
The platform now defaults to “high_automatic.” This enhancement implies that when users opt for the default settings, the platform will prioritize selecting higher-capability models.
Compared with previous versions, users employing default settings may observe different outcomes than previous versions.
Support for File Extension and MIME Type in Base64 Route
By supporting both file extensions and MIME types in base64-encoded data, the platform becomes more versatile and user-friendly for different data types.
Enhanced Private AI Documentation
Dive into our updated and improved documentation to better understand and utilize Private AI’s capabilities.
Model Improvements: Precision and Coverage
– AI Model Improvements: Enhanced detection of “spelled-out” entities: The platform better recognizes entities spelled out letter by letter, a common occurrence in call transcripts (e.g., “g as in golf, an as in apple, r for red, y for yellow,” “G-A-R-Y”).
– Healthcare Data Enhancements: The platform has improved the detection of Personally Identifiable Information (PII) and Protected Health Information (PHI) in healthcare data, particularly in single-word responses in patient forms and DICOM attributes.
– Regional Data Recognition: The platform now handles more regional and multi-language variations than ever. Examples include Irish eircode (postal code) detection in English text and enhanced PHI detection in Dutch, English, Italian, and Ukrainian.
The Private AI Product Team