Skip to content

ChatGPT Chat Completion XML

Tasks

This XML format represents a list of messages comprising a conversation, and the response that ChatGPT produces.

Tasks

Minimal XML Sample

<?xml version="1.0"?>
<ChatCompletions>
  <ChatCompletion>
    <Messages>
      <Message>Hello</Message>
    </Messages>
  </ChatCompletion>
</ChatCompletions>

In each of the following sections most of the XML has been omitted to make the samples easier to read. The whole structure of the ChatCompletions schema is used below as a reference of where fields should be in the object model.

ChatCompletions

The ChatCompletions element is the root of the XML document, and represents a list of chats and a common set of options to apply to all of them.

XML Field  Example  Field Type  Input  Description
Options See below Element Optional Common options to apply to all chats.
ChatCompletion See below Collection Required A collection of one or more ChatCompletion elements. 
<?xml version="1.0"?>
<ChatCompletions>
  <Options /> <!-- See below -->
  <ChatCompletion /> <!-- See below -->
</ChatCompletions>

ChatCompletion

The ChatCompletion element represents an individual chat session, which requires a response from ChatGPT. This element appears as a child of the root ChatCompletions element. The ChatCompletion element can appear one or more times.

XML Field  Example  Field Type  Input  Description
@Id 1 string Optional Used to provide an identifier for this chat.
Options See below Element Optional Options to apply to this specific chat alone.
Messages How do I cook rice Collection Required The collection of Message elements that make up the chat.
Responses Oh, you're asking about how to cook rice? Collection Read Only The collection of Response elements produced by ChatGPT. 
<?xml version="1.0"?>
<ChatCompletions>
  <ChatCompletion Id="1">
    <Options /> <!-- See below -->
    <Messages>
      <Message Role="User">Hello</Message>
      <Message Role="Assistant">Well, hello there! Finally, a breath of fresh air. What can I do for you? Hopefully, it's something worth my time.</Message>
      <Message Role="User">How do I cook rice</Message>   
    </Messages>
    <Responses>
      <Response>Oh, you're asking about how to cook rice? Are you serious? It's one of the most basic culinary tasks. Rice, my friend, should come out light and fluffy, not a clumpy mess like you've made in the past.</Response>
      <Response>Oh, dear me. You're asking for help with rice? Rice?! It's one of the simplest things to cook, yet people still manage to mess it up. Are you ready for a masterpiece worthy of my expertise? Or are you just eager</Response>
      <Response>Oh, dear. Cooking rice? You'd think something so simple would be hard to mess up, wouldn't you? But somehow, people still manage to do it with flying colors. Let me give you a few pointers so you don't embarrass yourself</Response>
    </Responses>
  </ChatCompletion>
</ChatCompletions>

Options

The Options element represents a set of options ChatGPT should to apply when generating it's response. This element can appear as a child of both the ChatCompletions and ChatCompletion element. When it is present at both levels, the options specified at the ChatCompletion will take precedence.

XML Field  Example  Field Type  Input  Description
@MaxTokens 50 integer Optional The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
@Model gpt-3.5-turbo string Optional Enter the ID of the model to use to generate the response. Please refer to the model endpoint compatibility table for details on which models work with the Chat API.
@NumberOfResults 5 integer Optional How many responses to generate for each input message.
@Prompt can you reply in the style of Gordon Ramsay string Optional An optional text to guide the model's style.
@Temperature 1 float Optional The sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. It is not recommended to specify values for both the Temperature and TopPercent.
@TopPercent 1 float Optional An alternative to sampling with temperature, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. It is not recommended to specify values for both the Temperature and TopPercent.
@User user12345 string Optional A unique identifier representing your end-user, which helps OpenAI to monitor and detect abuse, and provide more actionable feedback in the event of any policy violations. It is recommended to hash usernames or email addresses, in order to avoid sending any personally identifiable information. 
<Options MaxTokens="50" Model="gpt-3.5-turbo" NumberOfResults="5" Prompt="can you reply in the style of Gordon Ramsay" Temperature="1" TopPercent="1" User="user12345" />

Complete XML Sample

This sample shows all data that can be provided via our product pricing XML format.

<?xml version="1.0"?>
<ChatCompletions>
  <Options MaxTokens="50" Model="gpt-3.5-turbo" NumberOfResults="5" Prompt="can you reply in the style of Gordon Ramsay" Temperature="1" TopPercent="1" User="user12345" />
  <ChatCompletion Id="1">
    <Options MaxTokens="50" Model="gpt-3.5-turbo" NumberOfResults="5" Prompt="can you reply in the style of Gordon Ramsay" Temperature="1" TopPercent="1" User="user12345" />
    <Messages>
      <Message Role="User">Hello</Message>
      <Message Role="Assistant">Well, hello there! Finally, a breath of fresh air. What can I do for you? Hopefully, it's something worth my time.</Message>
      <Message Role="User">How do I cook rice</Message>   
    </Messages>
    <Responses>
      <Response>Oh, you're asking about how to cook rice? Are you serious? It's one of the most basic culinary tasks. Rice, my friend, should come out light and fluffy, not a clumpy mess like you've made in the past.</Response>
      <Response>Oh, dear me. You're asking for help with rice? Rice?! It's one of the simplest things to cook, yet people still manage to mess it up. Are you ready for a masterpiece worthy of my expertise? Or are you just eager</Response>
      <Response>Oh, dear. Cooking rice? You'd think something so simple would be hard to mess up, wouldn't you? But somehow, people still manage to do it with flying colors. Let me give you a few pointers so you don't embarrass yourself</Response>
    </Responses>
  </ChatCompletion>
</ChatCompletions>