Merge pull request openai#109 from rattrayalex/patch-10

add system_fingerprint to chat completion chunks

Author: schnerd

openapi.yaml

@@ -6280,6 +6280,12 @@ components:
  model:
  type: string
  description: The model to generate the completion.
+ system_fingerprint:
+ type: string
+ description: |
+ This fingerprint represents the backend configuration that the model runs with.
+
+ Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.
  object:
  type: string
  description: The object type, which is always `chat.completion.chunk`.