OpenAi response looks like---- { "id":"chatcmpl-abc123", "object":"chat.completion", "created":1677858242, "model":"gpt-3.5-turbo-0301", "usage":{ "prompt_tokens":13, "completion_tokens":7, "total_tokens":20 }, "choices":[ { "message":{ "role":"assistant", "content":"\n\nThis is a test!" }, "finish_reason":"stop", "index":0 } ] } I know that there is a new tokenizer implementation in llama-index, but can we get this kind of body straight in the response, or at least the same usage body in the response.
