Adding a Private Knowledge Base to My VCF PAIS Llama Agent
I prepare my S3 document library for retrieval in VCF PAIS, with the indexing procedure, agent configuration, and validation checks for my Llama agent.
Tag: Llama
Deploying a Read-Only MCP Service for My VCF PAIS Llama Agent
I deploy a read-only MCP service in my application VKS cluster, connect it to my PAIS Llama agent, and verify live workload status through browser chat.
Creating a Llama Agent with VCF Private AI Services
In my lab, I create a PAIS agent using my Llama endpoint, add clear instructions, configure conversation history, and test responses and capability boundaries in the Playground.
Deploying Llama 3.1 on a GPU Model Endpoint with VCF PAIS
In my lab, I deploy Llama 3.1 8B from Harbor to a PAIS GPU endpoint, configure vLLM for my 20 GiB GPU, validate chat and tool-call parsing, and retain a rollback path.
Preparing Harbor and Uploading Models for VCF Private AI Services
In my lab, I prepare a private Harbor project, create separate upload and pull-only accounts, download pinned model revisions, verify the files, and upload model artifacts for VCF Private AI Services.