> 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.

# OpenAI Streaming

> Consume adapter-native OpenAI Chat Completions chunks and terminal invocation results.

# <kbd>module</kbd> `nemo_fabric.openai_streaming`

Adapter-native OpenAI streaming for the NVIDIA NeMo Fabric Python SDK.



---


## <kbd>class</kbd> `OpenAIInvokeStream`

Async iterator of OpenAI chat-completion chunks for one invocation.

Await ``result()`` for the separate normalized terminal result. Call ``aclose()`` when iteration stops early; it drains the stream without cancelling the invocation.




---


### <kbd>method</kbd> `aclose`

```python
async def aclose() -> None
```

Discard unread chunks and wait without cancelling the invocation.

---


### <kbd>method</kbd> `result`

```python
async def result() -> RunResult
```

Drain the stream and return its separate normalized terminal result.




---

_This file was automatically generated via [lazydocs](https://github.com/ml-tooling/lazydocs)._