Open AAlvAAro opened 8 months ago
To be able to receive the LLMs response by chunks instead of a giant block of text, the invoke_model_from_response_stream AWS gem method needs to be implemented. See reference:
invoke_model_from_response_stream
https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/BedrockRuntime/Client.html#invoke_model_with_response_stream-instance_method
To be able to receive the LLMs response by chunks instead of a giant block of text, the
invoke_model_from_response_stream
AWS gem method needs to be implemented. See reference:https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/BedrockRuntime/Client.html#invoke_model_with_response_stream-instance_method