We were able to get a streaming response from LlamaCpp by using streaming=True and having CallbackManager([StreamingStdOutCallbackHandler()]). But the issue is the streamed out put does not contain any new line characters which makes the streamed output text appear as a long paragraph. The content on the console appear right and also when we return the complete response, it contains new line characters. Only the streamed output is the issue. Due...
Originally asked by Mahesh Chandran on Stack Exchange (stackoverflow) (CC BY-SA 4.0).
