Add logprobs and top_logprobs to chat request model and logprobs to chat response choice model

[HillPhelmuth]

Feature Request

Add support for logprobs in chat request/response

OpenAI api has added support for logprobs to their Chat endpoint

Describe the solution you'd like

The Chat version of logprobs is a little different than the old Completions implementation, but it should be relatively straightforward to implement. In the request just adding the two additional properties to the model and corresponding optional parameters in the constructor would suffice.

The response would require an additional property in the Choice model with new models for logprobs and its member content array.
Here's an example of the logprobs part of the response for reference:

"logprobs": {
        "content": [
          {
            "token": "Hello",
            "logprob": -0.31725305,
            "bytes": [72, 101, 108, 108, 111],
            "top_logprobs": [
              {
                "token": "Hello",
                "logprob": -0.31725305,
                "bytes": [72, 101, 108, 108, 111]
              },
              {
                "token": "Hi",
                "logprob": -1.3190403,
                "bytes": [72, 105]
              }
            ]
          },
          {
            "token": "!",
            "logprob": -0.02380986,
            "bytes": [
              33
            ],
            "top_logprobs": [
              {
                "token": "!",
                "logprob": -0.02380986,
                "bytes": [33]
              },
              {
                "token": " there",
                "logprob": -3.787621,
                "bytes": [32, 116, 104, 101, 114, 101]
              }
            ]
          }
        ]
      }