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

# nemoguardrails.actions.retrieve_relevant_chunks

## Module Contents

### Functions

| Name                                                                                                    | Description                                                |
| ------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------- |
| [`retrieve_relevant_chunks`](#nemoguardrails-actions-retrieve_relevant_chunks-retrieve_relevant_chunks) | Retrieve relevant knowledge chunks and update the context. |

### Data

[`log`](#nemoguardrails-actions-retrieve_relevant_chunks-log)

### API

```python
nemoguardrails.actions.retrieve_relevant_chunks.retrieve_relevant_chunks(
    context: typing.Optional[dict] = None,
    kb: typing.Optional[nemoguardrails.kb.kb.KnowledgeBase] = None,
    is_colang_2: typing.Optional[bool] = False
)
```

async

Retrieve relevant knowledge chunks and update the context.

**Parameters:**

The context for the execution of the action. Defaults to None.

The KnowledgeBase to search for relevant chunks. Defaults to None.

**Returns:**

An action result containing the retrieved relevant chunks with context updates:

* "relevant\_chunks" -- the relevant chunks as a single string,
* "relevant\_chunks\_sep" -- the relevant chunks as a list of strings before concatenation,
* "retrieved\_for" -- the user message that the chunks were retrieved for.

```python
nemoguardrails.actions.retrieve_relevant_chunks.log = logging.getLogger(__name__)
```