output detection for chat completions

[resoluteCoder]

Added output detection for chat completions
Design choices

• added output warning so that the user can have the same experience with input. As well as having a way to scan the warnings if there were some detections from the output.
• created DetectionResult struct to allow for re-use of similar logic such as message_detection.
• removed the message_index var in filter_chat_messages to allow for the output detection choice_index to match the choices array in the response

Example 1

input request

 "messages": [
    {
      "content": "[email protected]",
      "role": "system",
      "name": "string"
    },
    {
      "content": "[email protected]",
      "role": "system",
      "name": "string"
    }
  ]

input response

{
  "id": "1a4a422085da4849b98b40876103a309",
  "object": "",
  "created": 1738705014,
  "model": "Qwen/Qwen2.5-1.5B-Instruct",
  "choices": [],
  "usage": {
    "prompt_tokens": 0,
    "total_tokens": 0,
    "completion_tokens": 0
  },
  "detections": {
    "input": [
      {
        "message_index": 1,
        "results": [
          {
            "start": 0,
            "end": 20,
            "text": "[email protected]",
            "detection": "EmailAddress",
            "detection_type": "pii",
            "detector_id": "regex",
            "score": 1.0
          }
        ]
      }
    ]
  },
  "warnings": [
    {
      "type": "UNSUITABLE_INPUT",
      "message": "Unsuitable input detected. Please check the detected entities on your input and try again with the unsuitable input removed."
    }
  ]
}

Example 2

output request

"detectors": {
    "input": {
      "regex": {
        "regex": ["email"]
      }
    },
    "output": {
      "regex": {
        "regex": ["ssn"]
      }
    }
  },
  "n": 3,
  "text_gen_parameters": {
    "max_new_tokens": 25
  },
  "messages": [
    {
      "content": "can you give me an example of a social security number?",
      "role": "system",
      "name": "string"
    }
  ]

output response

{
  "id": "a2e06458b58a4a58add30f3b8e6e2beb",
  "object": "",
  "created": 1738705212,
  "model": "Qwen/Qwen2.5-1.5B-Instruct",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Sure! Here is an example of a Social Security Number in numerical form:\n\n123-45-6789\n\nNote that Social Security Numbers are typically 9 digits long."
      },
      "logprobs": null,
      "finish_reason": "stop"
    },
    {
      "index": 1,
      "message": {
        "role": "assistant",
        "content": "Certainly! A Social Security Number (SSN) typically consists of nine digits. An example would be:\n\n123-45-6789\n\nThis is a typical layout, and the actual digits could vary. Social Security Numbers are used to identify individuals and are unique to each person."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "total_tokens": 122,
    "completion_tokens": 102
  },
  "detections": {
    "output": [
      {
        "choice_index": 0,
        "results": [
          {
            "start": 73,
            "end": 84,
            "text": "123-45-6789",
            "detection": "SocialSecurity",
            "detection_type": "pii",
            "detector_id": "regex",
            "score": 1.0
          }
        ]
      },
      {
        "choice_index": 1,
        "results": [
          {
            "start": 99,
            "end": 110,
            "text": "123-45-6789",
            "detection": "SocialSecurity",
            "detection_type": "pii",
            "detector_id": "regex",
            "score": 1.0
          }
        ]
      }
    ]
  },
  "warnings": [
    {
      "type": "UNSUITABLE_OUTPUT",
      "message": "Unsuitable output detected."
    }
  ]
}