Just trying to follow a basic langchain tutorial: https://python.langchain.com/v0.2/docs/tutorials/local_rag/ Super simple code: from langchain_ollama import ChatOllama import logging logging.basicConfig( level=logging.DEBUG, format='%(asctime)s.%(msecs)03d [%(levelname)s]: %(message)s', datefmt='%H:%M:%S' ) logging.info("### Starting up") llm = ChatOllama( model="llama3.1", ) response_message = llm.invoke( "What are you?" )...
Originally asked by Kam on Stack Exchange (stackoverflow) (CC BY-SA 4.0).
