Microsoft’s Semantic Kernel, an open-source software development kit (SDK) designed for integrating large language models (LLMs) with conventional programming languages, has unveiled its fall 2023 roadmap. The roadmap outlines plans to include features such as plugin testing, dynamic planners, and streaming capabilities.
The Semantic Kernel team at Microsoft has revealed that they will be adopting the OpenAI plugin standard, allowing plugins to seamlessly function across OpenAI, Semantic Kernel, and the Microsoft platform. This move aims to enhance the interoperability and compatibility of the software.
In addition to plugin support, the team plans to improve the planners within Semantic Kernel, enabling them to handle global-scale deployments. Planners are responsible for orchestrating the necessary steps to fulfill a user’s request. With the proposed enhancements, users can expect features like cold storage plans for consistency and dynamic planners that can automatically discover and utilize plugins.
Integration with vector databases, such as Pinecone, Redis, Weaviate, Chroma, Azure Cognitive Search, and Services, is also on the agenda for the fall 2023 release. Moreover, the team is developing a document chunking service and enhancing the Semantic Kernel Tools extension for Visual Studio Code.
Two crucial aspects highlighted in the roadmap are telemetry and AI safety. By providing end-to-end telemetry, developers will gain valuable insights into goal-oriented AI plan creation, token usage, and error analysis. Furthermore, the integration of Azure Content Safety hooks ensures a streamlined approach to maintaining AI safety.
Microsoft’s Semantic Kernel is an open-source project hosted on GitHub, and the team encourages community participation and collaboration.
Furthermore, Microsoft recently announced improvements to endpoint management in the Semantic Kernel Tools extension for Visual Studio Code. This enhancement allows developers to conveniently switch between different AI models, streamlining their workflow and productivity.
In conclusion, Microsoft’s Semantic Kernel is set to introduce several notable features and enhancements in its fall 2023 release. The adoption of the OpenAI plugin standard, improvements in planners, integration with vector databases, and advancements in telemetry and AI safety collectively promise to elevate the capabilities and usability of the Semantic Kernel SDK. Developers and users alike can look forward to more efficient and seamless integration of large language models into their projects.
