7 docs tagged with "streaming"

Boost.Accumulators is a framework for incremental statistical computation. You push data

Hand-rolling a FastAPI app around a chain or graph gives you control LangServe doesn't: custom auth, arbitrary request/response shapes, and full ownership of streaming.

stream (sync) and astream (async) yield output incrementally instead of waiting for the whole result. For a chat model alone, that means tokens as they're generated:

Why this matters

DOM parsing — json::parse — builds the entire document in memory before you can look at any of

"Find the k largest" looks like a sorting problem, and sorting solves it — but sorting also computes

Why this matters