Merge pull request #248 from openai/brianz/stream-options-2

Add stream_options param; add usage in ChatCompletionChunk

Author: brianz-openai

openapi.yaml

@@ -7212,6 +7212,8 @@ components:
           type: boolean
           nullable: true
           default: false
+        stream_options:
+          $ref: "#/components/schemas/ChatCompletionStreamOptions"
         suffix:
           description: |
             The suffix that comes after a completion of inserted text.
@@ -7697,6 +7699,18 @@ components:
         - tool
         - function
 
+    ChatCompletionStreamOptions:
+      description: |
+        Options for streaming response. Only set this when you set `stream: true`.
+      type: object
+      nullable: true
+      default: null
+      properties:
+        include_usage:
+          type: boolean
+          description: |
+            If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value.
+
     ChatCompletionResponseMessage:
       type: object
       description: A chat completion message generated by the model.
@@ -7891,6 +7905,8 @@ components:
           type: boolean
           nullable: true
           default: false
+        stream_options:
+          $ref: "#/components/schemas/ChatCompletionStreamOptions"
         temperature:
           type: number
           minimum: 0
@@ -8150,7 +8166,9 @@ components:
           description: A unique identifier for the chat completion. Each chunk has the same ID.
         choices:
           type: array
-          description: A list of chat completion choices. Can be more than one if `n` is greater than 1.
+          description: |
+            A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the
+            last chunk if you set `stream_options: {"include_usage": true}`.
           items:
             type: object
             required:
@@ -8191,6 +8209,25 @@ components:
           type: string
           description: The object type, which is always `chat.completion.chunk`.
           enum: [chat.completion.chunk]
+        usage:
+          type: object
+          description: |
+            An optional field that will only be present when you set `stream_options: {"include_usage": true}` in your request.
+            When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request.
+          properties:
+            completion_tokens:
+              type: integer
+              description: Number of tokens in the generated completion.
+            prompt_tokens:
+              type: integer
+              description: Number of tokens in the prompt.
+            total_tokens:
+              type: integer
+              description: Total number of tokens used in the request (prompt + completion).
+          required:
+            - prompt_tokens
+            - completion_tokens
+            - total_tokens
       required:
         - choices
         - created