mirascope.core.bedrock.call_response_chunk
This module contains the BedrockCallResponseChunk class.
Usage
Class BedrockCallResponseChunk
A convenience wrapper around the Bedrock ChatCompletionChunk streamed chunks.
When calling the Bedrock API using a function decorated with bedrock_call and
stream set to True, the stream will contain BedrockResponseChunk instances with
properties that allow for more convenient access to commonly used attributes.
Example:
from mirascope.core import prompt_template
from mirascope.core.bedrock import bedrock_call
@bedrock_call("anthropic.claude-3-haiku-20240307-v1:0", stream=True)
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str):
...
stream = recommend_book("fantasy") # response is an `BedrockStream`
for chunk, _ in stream:
print(chunk.content, end="", flush=True)Bases:
BaseCallResponseChunk[StreamOutputChunk | AsyncStreamOutputChunk, FinishReason]Attributes
| Name | Type | Description |
|---|---|---|
| chunk | SkipValidation[StreamOutputChunk | AsyncStreamOutputChunk] | - |
| content | str | Returns the content for the 0th choice delta. |
| finish_reasons | list[FinishReason] | Returns the finish reasons of the response. |
| model | str | Returns the name of the response model. |
| id | str | Returns the id of the response. |
| usage | TokenUsageTypeDef | None | Returns the usage of the chat completion. |
| input_tokens | int | None | Returns the number of input tokens. |
| cached_tokens | int | None | Returns the number of cached tokens. |
| output_tokens | int | None | Returns the number of output tokens. |
| cost_metadata | CostMetadata | Returns the cost metadata. |
| common_finish_reasons | list[types.FinishReason] | None | - |