> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# Configuring Custom Initialization

> Use config.py to register custom LLM providers, embedding providers, and shared resources at startup.

The `config.py` file contains initialization code that runs once at startup, before the `LLMRails` instance is fully initialized. Use it to register custom providers and set up shared resources.

## When to Use config.py or actions.py

| Use Case                           | File         | Reason                                     |
| ---------------------------------- | ------------ | ------------------------------------------ |
| Register custom LLM provider       | `config.py`  | Must happen before LLMRails initialization |
| Register custom embedding provider | `config.py`  | Must happen before LLMRails initialization |
| Initialize database connection     | `config.py`  | Shared resource, initialized once          |
| Validate user input                | `actions.py` | Called during request processing           |
| Call external API                  | `actions.py` | Called during request processing           |
| Custom guardrail logic             | `actions.py` | Called from Colang flows                   |

## Configuration Sections

#### [Init Function](/configure-guardrails/custom-initialization/init-function)

Define the init() function to initialize resources and register action parameters at startup.

How To

#### [LLM Providers](/configure-guardrails/custom-initialization/custom-llm-providers)

Register custom text completion and chat models. Use the `LLMModel` Protocol for the built-in client, or LangChain `BaseLLM`/`BaseChatModel` when running with `NEMOGUARDRAILS_LLM_FRAMEWORK=langchain`.

How To

#### [Custom LLM Model](/configure-guardrails/custom-initialization/custom-llm-model)

Implement the LLMModel protocol to connect a non-OpenAI-compatible backend to the NVIDIA NeMo Guardrails library without depending on LangChain.

How To

#### [Custom LLM Framework](/configure-guardrails/custom-initialization/custom-llm-framework)

Replace the LLM framework layer to connect LiteLLM, an in-house orchestrator, or any non-default LLM stack to the NVIDIA NeMo Guardrails library.

How To

#### [Embedding Providers](/configure-guardrails/custom-initialization/custom-embedding-providers)

Register custom embedding providers for vector similarity search in the NVIDIA NeMo Guardrails library.

How To

#### [Custom Data](/configure-guardrails/custom-initialization/custom-data)

Pass and access custom data from config.yml in your initialization code and actions.

How To

## Related Topics

* [Custom Actions](/configure-guardrails/actions) - Define callable actions in `actions.py`
* [Model Configuration](/configure-guardrails/yaml-schema/model-configuration) - Configure LLM models in `config.yml`

> Use config.py to register custom LLM providers, embedding providers, and shared resources at startup.

## Docs

- [The Init Function for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/init-function.md): Define the init() function to initialize resources and register action parameters at startup.
- [Custom LLM Providers for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/custom-llm-providers.md): Register LangChain BaseLLM and BaseChatModel providers under the LangChain framework path (requires NEMOGUARDRAILS_LLM_FRAMEWORK=langchain).
- [Custom LLM Models for the NVIDIA NeMo Guardrails library](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/custom-llm-model.md): Implement the LLMModel protocol to connect a non-OpenAI-compatible backend to the NVIDIA NeMo Guardrails library without depending on LangChain.
- [Testing Your Guardrails Configuration](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/testing-your-config.md): Write fast, deterministic tests for your NeMo Guardrails configuration using the public testing surface.
- [Custom LLM Frameworks for the NVIDIA NeMo Guardrails library](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/custom-llm-framework.md): Replace the LLM framework layer to connect LiteLLM, an in-house orchestrator, or any non-default LLM stack to the NVIDIA NeMo Guardrails library.
- [Custom Embedding Providers for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/custom-embedding-providers.md): Register custom embedding providers for vector similarity search in NeMo Guardrails.
- [Custom Configuration Data for NeMo Guardrails](https://docs.nvidia.com/nemo/guardrails/v0.24.1/configure-guardrails/custom-initialization/custom-data.md): Pass and access custom data from config.yml in your initialization code and actions.