You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/openai/how-to/completions.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,7 +7,7 @@ manager: nitinme
7
7
ms.service: cognitive-services
8
8
ms.subservice: openai
9
9
ms.topic: how-to
10
-
ms.date: 08/11/2023
10
+
ms.date: 08/15/2023
11
11
author: ChrisHMSFT
12
12
ms.author: chrhoder
13
13
recommendations: false
@@ -182,7 +182,7 @@ Although this demonstration uses a simple prompt, it highlights several guidelin
182
182
183
183
## Conduct conversations
184
184
185
-
Starting with the release of [gpt-35-turbo and gpt-4](/azure/ai-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions), we recommend that you create conversational generation and chatbots by using models that support the _chat completion endpoint_. The chat completion models and endpoint require a different input structure than the completion endpoint.
185
+
Starting with the release of [GPT-35-Turbo and GPT-4](/azure/ai-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions), we recommend that you create conversational generation and chatbots by using models that support the _chat completion endpoint_. The chat completion models and endpoint require a different input structure than the completion endpoint.
186
186
187
187
The API is adept at carrying on conversations with humans and even with itself. With just a few lines of instruction, the API can perform as a customer service chatbot that intelligently answers questions without getting flustered, or a wise-cracking conversation partner that makes jokes and puns. The key is to tell the API how it should behave and then provide a few examples.
188
188
@@ -311,7 +311,7 @@ Here are some helpful guidelines for using the API to generate text and code com
311
311
312
312
-**Raise the Temperature to allow the API to tangent**. Set higher values for the `Temperature` setting to allow the API to respond in a manner that's tangential to the intent described in your prompt.
313
313
314
-
-**Use the gpt-35-turboandgpt-4 Azure OpenAI models**. For tasks that involve understanding or generating code, Microsoft recommends using the `gpt-35-turbo`and`gpt-4` Azure OpenAI models. These models use the new [chat completions format](/azure/ai-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions).
314
+
-**Use the GPT-35-TurboandGPT-4 Azure OpenAI models**. For tasks that involve understanding or generating code, Microsoft recommends using the `GPT-35-Turbo`and`GPT-4` Azure OpenAI models. These models use the new [chat completions format](/azure/ai-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions).
315
315
316
316
## Generate factual responses
317
317
@@ -378,5 +378,5 @@ For more information about generating code completions, see [Codex models and Az
378
378
379
379
## Next steps
380
380
381
-
- Learn how to work with the [gpt-35-turboandgpt-4 models](/azure/ai-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions).
381
+
- Learn how to work with the [GPT-35-TurboandGPT-4 models](/azure/ai-services/openai/how-to/chatGPT-4?pivots=programming-language-chat-completions).
382
382
- Learn more about the [Azure OpenAI Service models](../concepts/models.md).
0 commit comments