Today we’re excited to announce Capella AI Services to help developers to streamline the prototyping, building, testing, and deployment of AI agents without the latencies and high operational costs that usually come with new technologies and workflows.
Capella AI Services include:
- Model Services – Provides managed endpoints for the leading LLMs and embedding models, supports RAG and agentic workflows, and offers additional value-added capabilities
- Unstructured Data Services – Extracts, cleans, chunks, and transforms unstructured documents into JSON, preparing them for vectorization and querying
- Vectorization Services – Automates vectorization and indexing of data stored in Capella and helps developers quickly build RAG pipelines with fewer tools
- AI Agent Catalog Services – Provides a centralized repository for tools, metadata, prompts, and audit information for LLM flow, traceability, and governance
- Capella AI Functions – Enhances developer productivity by embedding AI-driven data analysis directly into application workflows using familiar SQL++ syntax
We have set up a private preview program to allow early access and insights into this new offering. As a valued community member, we would love for you to be a part of this and to get your valuable feedback. Click here to sign up. Additionally you can join our AI Services webcast - Learn how AI agents will impact your applications, to get a deeper explanation of our AI Services, and see demos of the core capabilities. Save your spot.
If you have any questions, please let us know.