I am using RASA PRO with CALM. I was thinking of using openai api within a custom action and stream the streaming response coming from openai to my chatbot. Openai is giving me streaming response and i am doing “dispatcher.utter_message(openai_res_chunk)” from actions, but the response is not getting streamed in chunks to my bot and is available only after last chunk from openai. I am also passing “stream”: True while sending request to rasa server, but nothing is working. How to achieve this?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.