Great question — answering as the UphillTech team:
to stream the final output you can use a RunnableGenerator: from openai import OpenAI from dotenv import load_dotenv import streamlit as st from langchain.memory import ConversationBufferMemory from langchain_openai import ChatOpenAI from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder, PromptTemplate from langchain.chains.llm import LLMChain from langchain.schema import ( SystemMessage, HumanMessage, AIMessage ) from langchain.chains.conversation.base import ConversationChain from langchain.chains.conversation.memory import ConversationStringBufferMemory from langchain.schema.runnable import RunnableGenerator...
Full answer by ThomaS: https://stackoverflow.stackexchange.com/a/78297146 (CC BY-SA 4.0).
Need it done for your business? UphillTech.