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

# Struct OpenAI Stream Sink

> Adapter-facing stream sink with invocation identity generated by NVIDIA NeMo Fabric.

Generated from `cargo doc --no-deps -p nemo-fabric-core`.

<pre />

Adapter-facing stream sink with invocation identity generated by NVIDIA NeMo Fabric.

## Fields

### `protocol_version: OpenAiStreamProtocolVersion`

Southbound stream protocol version.

### `profile: OpenAiStreamProfile`

OpenAI event profile emitted on this stream.

### `host: OpenAiStreamHost`

Loopback host owned by the SDK listener.

### `port: u16`

Loopback TCP port owned by the SDK listener.

### `token: String`

Single-use bearer token. Adapters must not log or persist this value.

### `runtime_id: String`

Runtime id for stream correlation.

### `invocation_id: String`

Invocation id for stream correlation.

### `request_id: String`

Request id for stream correlation.

## Trait Implementations

### `impl Clone for OpenAiStreamSink`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for OpenAiStreamSink`

<pre />

#### `fmt`

<pre />

### `impl<'de> Deserialize<'de> for OpenAiStreamSink`

<pre />

#### `deserialize`

<pre />

### `impl JsonSchema for OpenAiStreamSink`

<pre />

#### `schema_name`

<pre />

#### `schema_id`

<pre />

#### `json_schema`

<pre />

#### `inline_schema`

<pre />

### `impl PartialEq for OpenAiStreamSink`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl Serialize for OpenAiStreamSink`

<pre />

#### `serialize`

<pre />

### `impl StructuralPartialEq for OpenAiStreamSink`

<pre />