> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Type Alias Nemo Relay Native Async LlmStream Pull Cb

> Receives one item from a pull-based downstream LLM stream.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker`.

<pre />

Receives one item from a pull-based downstream LLM stream.

A chunk has non-null `chunk_json` and `done = false`; clean completion has both strings null and `done = true`; failure has non-null `error` and `done = true`. Only one pull may be outstanding per stream.