AI / Apache Burr Interview questions
What is a Streaming Action in Burr?
A Streaming Action is an action that yields its result incrementally instead of returning it all at once — useful for showing LLM tokens to a user as they’re generated, or streaming metrics from a long-running training loop.
They can be written as functions (with @streaming_action) or classes (subclassing StreamingAction), and support both sync and async execution. When called through application.stream_result(...), the caller gets back a StreamingResultContainer that can be iterated for intermediate chunks and then queried with .get() for the final result and state.
Streaming Actions in Burr are primarily useful for:
Calling application.stream_result() on a streaming action returns a:
More Related questions...
