AI / Apache Burr Interview questions
What is Parallelism used for in Burr?
Parallelism lets a single Burr action expand into many actions or subgraphs that run concurrently and are then joined back into one result — a map-reduce pattern applied to state machines.
Common use cases include trying several prompts against the same LLM, trying the same prompt against several different LLMs, running multiple retrieval tools (e.g. semantic search and web search) at once, or doing a full cartesian product of prompts and models. Burr offers a higher-level API (MapStates, MapActions, MapActionsAndStates) for the common cases, and a lower-level task-based API for full control.
More Related questions...