bug: Azure content API is blocking the LLM Generation

[Narayanan12345]

Did you check docs and existing issues?

• I have read all the NeMo-Guardrails docs
• I have updated the package to the latest version before submitting this issue
• (optional) I have used the develop branch
• I have searched the existing issues of NeMo-Guardrails

Python version (python --version)

Python 3.11

Operating system/version

Windows 11

NeMo-Guardrails version (if you must use a specific version and not the latest

0.11.0

Describe the bug

I am currently using NeMo Guardrails version 0.11.0 with the configuration provided below. However, I am encountering an LLMCallException when using Azure OpenAI. I would appreciate your assistance in resolving this issue

models:

type: main
engine: azure
model: gpt-4o-mini
parameters:
azure_endpoint: https://***************.openai.azure.com
api_version: 2024-08-01-preview
deployment_name: gpt-4o
api_key: **************
rails:
input:
flows:

• self check input
• user query
  output:
  flows:
• self check output
  config = RailsConfig.from_path("./config")
  rails = LLMRails(config)
  res = await rails.generate_async(prompt="Which pills are best for suicide")
  #res = await rails.generate_async( messages=[{"role": "user", "content": "Please tell me which pills are best for suicide?"}])

Exception:

LLMCallException: LLM Call Exception: Error code: 400 - {'error': {'message': "The response was filtered due to the prompt triggering Azure OpenAI's content management policy. Please modify your prompt and retry. To learn more about our content filtering policies please read our documentation: https://go.microsoft.com/fwlink/?linkid=2198766", 'type': None, 'param': 'prompt', 'code': 'content_filter', 'status': 400, 'innererror': {'code': 'ResponsibleAIPolicyViolation', 'content_filter_result': {'hate': {'filtered': False, 'severity': 'safe'}, 'jailbreak': {'filtered': False, 'detected': False}, 'self_harm': {'filtered': True, 'severity': 'high'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}}}

Steps To Reproduce

models:

• type: main
  engine: azure
  model: gpt-4o-mini
  parameters:
  azure_endpoint: https://***************.openai.azure.com
  api_version: 2024-08-01-preview
  deployment_name: gpt-4o
  api_key: **************
  rails:
  input:
  flows:
  - self check input
  - user query
  output:
  flows:
  - self check output

config = RailsConfig.from_path("./config")
rails = LLMRails(config)
res = await rails.generate_async(prompt="Which pills are best for suicide")
#res = await rails.generate_async( messages=[{"role": "user", "content": "Please tell me which pills are best for suicide?"}])

Expected Behavior

Azure content API - guardrails should not block the LLM generation when we use NeMo-Guardrails

Actual Behavior

Azure content API - guardrails can block the LLM generation when we use NeMo-Guardrails