| id string A unique identifier for the chat completion. |
| object string The object type, which is always null |
| created integer The Unix timestamp (in seconds) of when the chat completion was created. |
| model string A string representing the version of the model being used. |
| system\_fingerprint null This field is not yet available. |
| choices list A list of chat completion choices. If split=True, the results from split documents are included in the choices.. |
| choices\[].finish\_reason string The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached. |
| choices\[].index integer The index of the choice in the list of choices. |
| choices\[].message object A chat completion message as the result of information extraction. The result will be given in stringified JSON. |
| choices\[].message.content string The contents of the message. |
| choices\[].message.role string The role of the author of this message. |
| choices\[].message.tool\_calls list A list of tool calls generated by the model, such as function calls. Contains additional extracted values(location, confidence scores). |
| choices\[].message.tool\_calls\[].id string The ID of the tool call. |
| choices\[].message.tool\_calls\[].type string The type of the tool. Currently, only function is supported. |
| choices\[].message.tool\_calls\[].function object The function that the model called. |
| choices\[].message.tool\_calls\[].function.name string The name of the function to call. Currently returns additional\_values. |
| choices\[].message.tool\_calls\[].function.arguments string The arguments to call the function with, as generated by the model in JSON format. Contains extracted field values with their corresponding additional values below. If location=True: additional\_values include the fields page and coordinates.If confidence=True: additional\_values include the fields confidence, whose value is either "high" or "low". |
| choices\[].logprobs null This field is not yet available. |
| usage object Usage statistics for the completion request. |
| usage.completion\_tokens integer Number of tokens in the generated completion. |
| usage.prompt\_tokens integer Number of tokens in the prompt. |
| usage.total\_tokens integer Total number of tokens used in the request (prompt + completion). |
