Class AzureOpenAiChatCompletionStreamChunkResponse

constructor

• new AzureOpenAiChatCompletionStreamChunkResponse(
      _data: AzureOpenAiCreateChatCompletionStreamResponse,
  ): AzureOpenAiChatCompletionStreamChunkResponse

  Parameters

  • _data: AzureOpenAiCreateChatCompletionStreamResponse

  Returns AzureOpenAiChatCompletionStreamChunkResponse

Readonly_data

findChoiceByIndex

• findChoiceByIndex(
      index: number,
  ):
      | {
          delta: AzureOpenAiChatCompletionStreamResponseDelta;
          finish_reason: | "stop"
          | "length"
          | "tool_calls"
          | "content_filter"
          | "function_call"
          | null;
          index: number;
          logprobs?: | {
              content: AzureOpenAiChatCompletionTokenLogprob[]
              | null;
              refusal: AzureOpenAiChatCompletionTokenLogprob[] | null;
          } & Record<string, any>
          | null;
      } & Record<string, any>
      | undefined

  Parses the chunk response and returns the choice by index.

  Parameters

  • index: number

    The index of the choice to find.

  Returns
      | {
          delta: AzureOpenAiChatCompletionStreamResponseDelta;
          finish_reason: | "stop"
          | "length"
          | "tool_calls"
          | "content_filter"
          | "function_call"
          | null;
          index: number;
          logprobs?: | {
              content: AzureOpenAiChatCompletionTokenLogprob[]
              | null;
              refusal: AzureOpenAiChatCompletionTokenLogprob[] | null;
          } & Record<string, any>
          | null;
      } & Record<string, any>
      | undefined

  An LLMChoiceStreaming object associated withe index.

  • {
        delta: AzureOpenAiChatCompletionStreamResponseDelta;
        finish_reason:
            | "stop"
            | "length"
            | "tool_calls"
            | "content_filter"
            | "function_call"
            | null;
        index: number;
        logprobs?: | {
            content: AzureOpenAiChatCompletionTokenLogprob[]
            | null;
            refusal: AzureOpenAiChatCompletionTokenLogprob[] | null;
        } & Record<string, any>
        | null;
    } & Record<string, any>

    • delta: AzureOpenAiChatCompletionStreamResponseDelta

    • finish_reason: "stop" | "length" | "tool_calls" | "content_filter" | "function_call" | null

      The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.

    • index: number

      The index of the choice in the list of choices.

    • Optionallogprobs?:
          | {
              content: AzureOpenAiChatCompletionTokenLogprob[]
              | null;
              refusal: AzureOpenAiChatCompletionTokenLogprob[] | null;
          } & Record<string, any>
          | null

      Log probability information for the choice.

  • undefined

getDeltaContent

• getDeltaContent(choiceIndex?: number): string | null | undefined

  Parses the chunk response and returns the delta content.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns string | null | undefined

  The message delta content.

getDeltaToolCalls

• getDeltaToolCalls(
      choiceIndex?: number,
  ): AzureOpenAiChatCompletionMessageToolCallChunk[] | undefined

  Gets the delta tool calls for a specific choice index.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns AzureOpenAiChatCompletionMessageToolCallChunk[] | undefined

  The delta tool calls for the specified choice index.

getFinishReason

• getFinishReason(
      choiceIndex?: number,
  ):
      | "stop"
      | "length"
      | "tool_calls"
      | "content_filter"
      | "function_call"
      | null
      | undefined

  Reason for stopping the completion stream chunk.

  Parameters

  • OptionalchoiceIndex: number

    The index of the choice to parse.

  Returns
      | "stop"
      | "length"
      | "tool_calls"
      | "content_filter"
      | "function_call"
      | null
      | undefined

  The finish reason.

getTokenUsage

• getTokenUsage(): AzureOpenAiCompletionUsage | null

  Usage of tokens in the chunk response.

  Returns AzureOpenAiCompletionUsage | null

  Token usage.

  Copyright Ⓒ 2026 SAP SE or an SAP affiliate company. All rights reserved.