refactor(deps)!: demote LangChain and LangChain-providers from core to dev (#1806)

Now that DefaultFramework handles OpenAI-compatible chat via httpx, LangChain is no longer needed for basic operation. Moving it out of core slims the mandatory install substantially and makes the LangChain integration genuinely opt-in.

Author: Pouyanpi

docs/getting-started/installation-guide.md

@@ -62,10 +62,10 @@ Use the following steps to install the NeMo Guardrails library in a virtual envi
 
    ::::
 
-1. Install the NeMo Guardrails library with support for NVIDIA-hosted models. Set `NVIDIA_API_KEY` to your personal API key generated on [build.nvidia.com](https://build.nvidia.com/).
+1. Install the NeMo Guardrails library. Set `NVIDIA_API_KEY` to your personal API key generated on [build.nvidia.com](https://build.nvidia.com/).
 
    ```bash
-   pip install "nemoguardrails[nvidia]"
+   pip install nemoguardrails
    ```
 
 1. Set up an environment variable for your NVIDIA API key.
@@ -101,7 +101,7 @@ git clone https://github.com/NVIDIA-NeMo/Guardrails.git nemoguardrails
 cd nemoguardrails
 python -m venv .venv
 source .venv/bin/activate
-poetry install --extras "nvidia"
+poetry install
 ```
 
 When using Poetry, prefix CLI commands with `poetry run`:
@@ -120,8 +120,6 @@ You can install the NeMo Guardrails library with optional extra packages to add
 
 | Extra | Description |
 |-------|-------------|
-| `nvidia` | NVIDIA-hosted model integration through [build.nvidia.com](https://build.nvidia.com/) |
-| `openai` | OpenAI-hosted model integration |
 | `server` | [Guardrails API server](../run-rails/using-fastapi-server/overview.md) dependencies (aiofiles for async file handling, openai for API schemas). FastAPI is a core dependency. Required to run `nemoguardrails server`. |
 | `sdd` | [Sensitive data detection](../configure-rails/guardrail-catalog/pii-detection.md#presidio-based-sensitive-data-detection) using Presidio |
 | `eval` | [Evaluation tools](../evaluation/evaluate-guardrails.md) for testing guardrails |

nemoguardrails/imports.py

@@ -145,11 +145,11 @@ def import_optional_dependency(
 
 # Commonly used optional dependencies with their extra groups
 OPTIONAL_DEPENDENCIES = {
-    "openai": "openai",
-    "langchain": None,  # Not in extras
-    "langchain_openai": "openai",
+    "openai": "server",
+    "langchain": None,
+    "langchain_openai": None,
     "langchain_community": None,
-    "langchain_nvidia_ai_endpoints": "nvidia",
+    "langchain_nvidia_ai_endpoints": None,
     "torch": None,
     "transformers": None,
     "presidio_analyzer": None,