Exciting Updates in 3.7

We are excited to share the details of our latest platform updates, which brings significant enhancements across various domains. 

Enhancing PrivateGPT and UI Experience

Our recent software update introduces significant enhancements, focusing on the PrivateGPT experience and user interface improvements. Here’s a summary of these updates:

Customizable Conversation Roles

We've added the functionality to define roles for conversations. Roles are text prompts injected into the beginning of all conversations. This feature allows for more tailored and effective responses, enhancing the overall user experience with PrivateGPT.

Administration and Configuration Ease

We are introducing an administration page in the Customer Portal. This addition is designed for admins who want to configure their PrivateGPT deployments with point-and-click. Take a look at this video overview for more information.

Cohere Support

PrivateGPT now supports Cohere LLM, offering users a broader choice of language models while maintaining our commitment to data privacy. 

UI Enhancements

We have implemented UI improvements as part of our commitment to providing a seamless and intuitive user experience. These enhancements are designed to improve front-end deployment, making the interface more user-friendly and responsive.

Image, Audio and ASR Processing Improvements

Configure Maximum Image Pixels

The container allows users to configure the maximum allowed pixels in images processed using the PAI_MAX_IMAGE_PIXELS environment variable. 

Improved Performance of Standard ASR

We have enhanced the Standard Automatic Speech Recognition (ASR) performance results to provide more accurate and efficient audio data processing.

New Audio Options

The platform now includes enhanced audio file processing capabilities, allowing users to customize bleep frequency and gain through two new parameters: bleep_frequency and bleep_gain. These adjustments are accessible under AudioOptions in the process_file routes, as detailed in our API specification.

Model Improvements Across Languages and Domains

Multi-Language Improvements

Japanese: Enhanced average recall of PII entity types, bolstering the identification and protection of sensitive personal information in Japanese.

Health Data Improvements

Spanish & Portuguese:  Advanced detection capabilities for NAME_MEDICAL_PROFESSIONAL and ORGANIZATION_MEDICAL_FACILITY, essential for accurately identifying personal and organizational information in healthcare contexts in Spanish and Portuguese.

MEDICAL_CODE Beta Support: Introduction of the MEDICAL_CODE entity type in beta, aiding in categorizing various medical classification codes from systems like ICD-10, NDC, and SNOMED.