Merge pull request #262147 from PatrickFarley/openai-gptnext

change output format

Author: prmerger-automator[bot]

articles/ai-services/openai/how-to/gpt-with-vision.md

@@ -101,10 +101,7 @@ The API response should look like the following.
     ],
     "choices": [
         {
-            "finish_details": {
-                "type": "stop",
-                "stop": "<|fim_suffix|>"
-            },
+            "finish_reason":"stop",
             "index": 0,
             "message": {
                 "role": "assistant",
@@ -138,13 +135,11 @@ The API response should look like the following.
 }
 ```
 
-Every response includes a `"finish_details"` field. The subfield `"type"` has the following possible values:
+Every response includes a `"finish_reason"` field. It has the following possible values:
 - `stop`: API returned complete model output.
-- `max_tokens`: Incomplete model output due to the `max_tokens` input parameter or model's token limit.
+- `length`: Incomplete model output due to the `max_tokens` input parameter or model's token limit.
 - `content_filter`: Omitted content due to a flag from our content filters.
 
-If `finish_details.type` is `stop`, then there is another `"stop"` property that specifies the token that caused the output to end.
-
 ## Detail parameter settings in image processing: Low, High, Auto  
 
 The detail parameter in the model offers three choices: `low`, `high`, or `auto`, to adjust the way the model interprets and processes images. The default setting is auto, where the model decides between low or high based on the size of the image input. 
@@ -239,11 +234,7 @@ The chat responses you receive from the model should now include enhanced inform
     "choices":
     [
         {
-            "finish_details":
-            {
-                "type": "stop",
-                "stop": "<|fim_suffix|>"
-            },
+            "finish_reason":"stop",
             "index": 0,
             "message":
             {
@@ -283,13 +274,11 @@ The chat responses you receive from the model should now include enhanced inform
 }
 ```
 
-Every response includes a `"finish_details"` field. The subfield `"type"` has the following possible values:
+Every response includes a `"finish_reason"` field. It has the following possible values:
 - `stop`: API returned complete model output.
-- `max_tokens`: Incomplete model output due to the `max_tokens` input parameter or model's token limit.
+- `length`: Incomplete model output due to the `max_tokens` input parameter or model's token limit.
 - `content_filter`: Omitted content due to a flag from our content filters.
 
-If `finish_details.type` is `stop`, then there is another `"stop"` property that specifies the token that caused the output to end.
-
 ## Use Vision enhancement with video
 
 GPT-4 Turbo with Vision provides exclusive access to Azure AI Services tailored enhancements. The **video prompt** integration uses Azure AI Vision video retrieval to sample a set of frames from a video and create a transcript of the speech in the video. It enables the AI model to give summaries and answers about video content.
@@ -377,11 +366,7 @@ The chat responses you receive from the model should include information about t
     "choices":
     [
         {
-            "finish_details":
-            {
-                "type": "stop",
-                "stop": "<|fim_suffix|>"
-            },
+            "finish_reason":"stop",
             "index": 0,
             "message":
             {
@@ -399,13 +384,11 @@ The chat responses you receive from the model should include information about t
 }
 ```
 
-Every response includes a `"finish_details"` field. The subfield `"type"` has the following possible values:
+Every response includes a `"finish_reason"` field. It has the following possible values:
 - `stop`: API returned complete model output.
-- `max_tokens`: Incomplete model output due to the `max_tokens` input parameter or model's token limit.
+- `length`: Incomplete model output due to the `max_tokens` input parameter or model's token limit.
 - `content_filter`: Omitted content due to a flag from our content filters.
 
-If `finish_details.type` is `stop`, then there is another `"stop"` property that specifies the token that caused the output to end.
-
 ### Pricing example for Video prompts
 The pricing for GPT-4 Turbo with Vision is dynamic and depends on the specific features and inputs used. For a comprehensive view of Azure OpenAI pricing see [Azure OpenAI Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).