Agentic AI & LLM Applications
How to build AI agents, chatbots, and RAG applications on CAIP, using self-hosted or managed LLMs, and observe them with Langfuse.
Recipe: Create an Agent
Register agent metadata in the CAIP Portal, install the CAIP Agents SDK, and run your first agent.
Recipe: Attach the CAIP LLM API
How agent model calls route through the CAIP LLM API, choosing self-hosted vs. managed models, and calling the API directly.
Recipe: Add Conversation History
Threads and messages — persisting multi-turn conversations and passing context back to the agent.
Recipe: Add a Vector Store
Provisioning a vector store for RAG — embedding model, chunk size, and overlap choices.
Recipe: Create & Ingest Embeddings
Getting your documents into the vector store as embeddings, via the CAIP LLM API's embeddings endpoint.
Recipe: Search the Vector Store
Querying the vector store — vector, keyword, and hybrid search, and wiring it into an agent tool.