> 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.

# Struct LlmJson Stream

> Stream of JSON chunks produced by the managed streaming LLM pipeline.

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`.

```rust
pub struct LlmJsonStream { /* private fields */ }
```

Stream of JSON chunks produced by the managed streaming LLM pipeline.

In addition to ordinary stream polling, managed streams provide an explicit asynchronous close operation. A successful close means the producer has released its resources; subsequent polls return no more chunks.

## Implementations

### `impl LlmJsonStream`

<pre />

#### `new`

<pre />

Wrap a stream whose producer has no asynchronous teardown work.

#### `from_closeable`

<pre />

Wrap a stream that implements explicit asynchronous teardown.

#### `close`

<pre />

Stop the producer and wait for its cleanup to complete.

## Trait Implementations

### `impl Stream for LlmJsonStream`

<pre />

#### `Item`

<pre />

#### `poll_next`

<pre />

#### `size_hint`

<pre />