feat: enabling varargs for content filtering

[KavithaSiva]

Proposal:

client.chatCompletion(
{
  deploymentConfiguration: { deploymentId: 'id' },
  llmConfig: {
    model_name: 'gpt-35-turbo-16k',
    model_params: { max_tokens: 50, temperature: 0.1 }
  },
  prompt: {
    template: [{ role: 'user', content: 'Hello' }]
  }
},
undefined,
{
  type: Module.Filtering,
  filterConfig: {
    input: { azureContentSafety: { Hate: 0, SelfHarm: 2 } },
    output: {
      azureContentSafety: { Sexual: 4, Violence: 6 }
    }
  }
})

Issues:

• As the chatCompletion API already accepts an optional parameter (CustomRequestConfig), introducing varargs, forces us to either pass undefined or {} before we pass the actual module configuration as varargs which is awkward.
• Alternate option would be always to have only two parameters to the function, first one being an explicit type containing deployment information, mandatory orchestration config and request configuration and the second parameter is the varargs for optional module configuration.

client.chatCompletion(
{
  deploymentConfiguration: { deploymentId: 'id' },
  llmConfig: {
    model_name: 'gpt-35-turbo-16k',
    model_params: { max_tokens: 50, temperature: 0.1 }
  },
  prompt: {
    template: [{ role: 'user', content: 'Hello' }]
  }
requestConfig: {//applicable properties}
},
{
  type: Module.Filtering,
  filterConfig: {
    input: { azureContentSafety: { Hate: 0, SelfHarm: 2 } },
    output: {
      azureContentSafety: { Sexual: 4, Violence: 6 }
    }
  }
})

[KavithaSiva]

Closing this PR, as the proposal isn't very intuitive to use.