Draft PR: Add Guardrails Support to NeMo Agent Toolkit

[ronjer30]

Description

This PR attempts to address guardrails implementation/integration in NeMo Agent toolkit. Currently support for NeMo Guardrails is provided in the React agent. There are several examples that demonstrate usage. To get started, a simple config to add guardrails looks like below

guardrails:
  basic_rails:
    _type: nemo_guardrails
    enabled: true
    input_rails_enabled: true
    output_rails_enabled: false
    llm_name: nim_llm
    fallback_on_error: true
    rails:
      input:
         flows:
            - self check input

self check input uses a built-in default prompt to apply rails on user input. The prompt can be customized in the config. Additionally, ability to load NeMo Guardrails configuration folder and flows is provided.

Pending tasks:

• Support for other agents (ReWoo, etc)
• Support for NeMo Guardrails server
• Integration with RAG/Memory/Embedder for applying rails to fact check and detect hallucination

By Submitting this PR I confirm:

• I am familiar with the Contributing Guidelines.
• We require that all contributors "sign-off" on their commits. This certifies that the contribution is your original work, or you have rights to submit it under the same license, or a compatible license.
  • Any contribution which contains commits that are not Signed-Off will not be accepted.
• When the PR is ready for review, new or existing tests cover these changes.
• When the PR is ready for review, the documentation is up to date with these changes.