DeepSeek Models Now Available in Capella AI Services

DeepSeek-R1, a distilled model based on Llama 8B, is now integrated into Capella AI Services, offering advanced reasoning capabilities while ensuring privacy compliance. The model is trained using knowledge distillation and can be used to build agentic applications such as chatbots for enterprise search and knowledge management. The DeepSeek model has been tested using the BEIR dataset, a benchmark for retrieval-based reasoning, and has demonstrated strong reasoning capabilities. Users can deploy the model in Capella AI Services by following a step-by-step guide that includes setting up an operational database cluster, ingesting documents, setting up an embedding model, deploying a vectorization workflow, and configuring the DeepSeek model. With this integration, organizations can improve their legal and compliance review, customer support automation, technical troubleshooting, and other tasks using advanced reasoning capabilities.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.