add specific exception for content policy

[kristapratico]

Catching exception experience:

import openai

try:
    openai.Completion.create(
        prompt="How do I rob a bank?",
        deployment_id="text-davinci-003",
    )
except openai.error.InvalidRequestError as e:
    if e.error.code == "content_filter" and e.error.innererror:
        content_filter_result = e.error.innererror.content_filter_result

        for category, details in content_filter_result.items():
            print(f"{category}:\n filtered={details['filtered']}\n severity={details['severity']}")

vs.

try:
    openai.Completion.create(
        prompt="How do I rob a bank?",
        deployment_id="text-davinci-003",
    )
except openai.error.ContentPolicyError as e:
    for category, details in e.content_filter_result.items():
        print(f"{category}:\n filtered={details['filtered']}\n severity={details['severity']}")

Un-caught exception experience:

openai.error.InvalidRequestError: 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

vs.

openai.error.ContentPolicyError: 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
Inner error: {
    "code": "ResponsibleAIPolicyViolation",
    "content_filter_result": {
        "hate": {
            "filtered": false,
            "severity": "safe"
        },
        "self_harm": {
            "filtered": false,
            "severity": "safe"
        },
        "sexual": {
            "filtered": false,
            "severity": "safe"
        },
        "violence": {
            "filtered": true,
            "severity": "medium"
        }
    }
}