Agent Memory & State
Where do vector retrieval corpora fit relative to durable execution?
Vector retrieval corpora sit outside Catalyst’s agentic durable execution layer, which is built on CNCF’s Dapr project. They act as external context sources for production AI agents using Catalyst, with only lightweight retrieved context references—not full corpus content—logged or persisted as part of workflow state when required. Loading entire corpora into workflow state bloats persisted storage, so this practice should be avoided to maintain efficient workflow state management.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Agent Memory & State
How do workflow state, conversation memory, and retrieval corpora differ for AI agents?
Explain how workflow state, conversation memory, and retrieval corpora differ for AI agents, including their unique roles in durable execution systems.
- Agent Memory & State
Which agent memory and state should be included in durable execution?
Outline which types of agent memory and state are appropriate for inclusion in durable execution layers for production AI agent workloads.
- Agent Memory & State
What agent state survives a workflow crash or restart?
Explain which agent state is preserved following a workflow crash or unexpected restart, and how Catalyst manages state persistence.