Release version 7.4.0
Release version 7.4.0 includes new features, improvements, and bug fixes.
- Feature updates
- Upcoming Product Enhancements
Skypoint AI
API Retriever support: This update facilitates scalable integration to add, modify, or remove API retrievers seamlessly on Skypoint AI Copilot. Users can specify retriever data sources and configure multiple API endpoints with strict API specifications. These enhancements empower users to leverage advanced capabilities like semantic search and specific filtering techniques, enhancing the quality and relevance of retrieved data.
Domain Grounding: This enhancement allows to easily add industry-specific terminologies and domain contexts, ensuring that Private Copilot provides contextually accurate and industry-relevant responses. This improvement enhances relevance, accuracy, and efficiency, delivering tailored, context-aware solutions that significantly improve user experience and decision-making.
Platform
Unstructured Deletion/Modification support: This update empowers users to delete and modify existing unstructured data connections, ensuring greater flexibility and efficiency in data management workflows. Users can modify connection setups, modify files, delete, make changes in the folder locations, and more. This enhancement streamlines data management processes, provides users with increased control and versatility over their data sources.
Enhanced User workflow for Scheduler: Improvements to the workflow and user experience for schedule creation. These enhancements aim to streamline the scheduling process, making it more intuitive and efficient, and providing a smoother and more user-friendly experience overall.
Unstructured Data Ingestion Type Support: This update enables users to choose the type of ingestion while configuring unstructured data in Skypoint AI Studio. Users can select either ColBERT or semantic similarity based on their requirements, allowing for tailored data ingestion methods that optimize accuracy and efficiency.
Bring Your Own Vector DB Integration: We are introducing the capability for tenants to bring their own Vector DB into the Skypoint AI ecosystem. This feature caters to mid and large-sized customers seeking greater control over their data storage infrastructure. With seamless integration and enhanced customization options, users can expect improved operational efficiency and data governance.
Skypoint AI
Unstructured-2-Structured Tabular Extraction: We are introducing a feature to extract data from PDFs into a structured lakehouse. This update allows configurable field extraction, modeling data as tables for advanced and analytical querying. The phased release starts with Fat Table extraction and ingestion, followed by star schema support. The user-friendly interface ensures efficient data handling and high performance, enhancing accuracy and customer satisfaction.
Improve Retrieval Accuracy - Advanced RAG Techniques : This enhancement promises a substantial boost in retrieval accuracy, ensuring users receive more precise and relevant responses to their queries. With this integration, we're ushering in a new era of smarter, more efficient retrieval experiences for our users.
Copilot UX/UI Improvement: In the future release, we're improving the Skypoint AI Copilot with a focus on user experience. Expect a simplified interface, smoother interactions, and efficient conversation history search. These updates aim to deliver a seamless, enjoyable user experience while maintaining high standards of performance and accessibility.
Platform : Upcoming Connectors
MRI PMX Connector: This API-based connector will seamlessly complement user BAK backup file, providing nightly updates to maintain 'live' data within the Skypoint AI platform.
Instructions Tuning via Studio: Enhance AI performance by tuning instructions within Skypoint AI Studio. Users can specify domain information, provide details about data sources, and input prompt examples to refine AI reasoning capabilities, tailoring AI responses to specific user requirements.