> 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.integrations.langchain.helpers

## Module Contents

### Functions

| Name                                                                                                  | Description                                                            |
| ----------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- |
| [`get_llm_instance_wrapper`](#nemoguardrails-integrations-langchain-helpers-get_llm_instance_wrapper) | Wraps an LLM instance in a class that can be registered with LLMRails. |

### API

```python
nemoguardrails.integrations.langchain.helpers.get_llm_instance_wrapper(
    llm_instance: langchain_core.language_models.LLM,
    llm_type: str
) -> typing.Type[langchain_core.language_models.LLM]
```

Wraps an LLM instance in a class that can be registered with LLMRails.

This is useful to create specific types of LLMs using a generic LLM provider
from HuggingFace, e.g., HuggingFacePipelineCompatible or HuggingFaceEndpoint.