Nemo/Langchain with Chainlit

[BWardell15]

Hello, I am building a RAG bot that utilizes Langchain and Nemo Guardrails. I currently have the chain portion of the code configured as the following:

from langchain.chains import ConversationalRetrievalChain

chatbot_chain = ConversationalRetrievalChain.from_llm(
    llm,
    retriever=retriever,
    memory=memory,
    combine_docs_chain_kwargs={"prompt": custom_prompt}
)

guardrails = RunnableRails(config)

@cl.on_chat_start
def quey_llm():
    llm
    conversation_memory = memory
    llm_chain = guardrails | chatbot_chain
        cl.user_session.set("llm_chain", llm_chain)

@cl.on_message
async def query_llm(message: cl.Message):
    llm_chain = cl.user_session.get("llm_chain")
        response = await llm_chain.acall(message.content, 
                                     callbacks=[
                                         cl.AsyncLangchainCallbackHandler()])
      await cl.Message(response["answer"]).send()

However, when I run this I get the following error: AttributeError: 'RunnableRails' object has no attribute 'acall'

Is there a different attribute that I should be using there? I haven't been able to figure this out on my own so was hoping I could get a nudge in the right direction here.

[drazvan]

@BWardell15 : can you try to use llm_chain.invoke? See the example at the bottom here: https://docs.nvidia.com/nemo/guardrails/user_guides/langchain/runnable-rails.html.

[Pouyanpi]

@BWardell15, have you tried the above suggestion? Did it resolve your issue?

[BWardell15]

Hi, yes, the issue has been resolved, thanks!

…

On Thursday, August 15, 2024, Pouyan ***@***.***> wrote: @BWardell15 <https://github.com/BWardell15>, have you tried the above suggestion? Did it resolve your issue? — Reply to this email directly, view it on GitHub <#659 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BHX43VE3CZCKGA573QL6VBLZRR6RBAVCNFSM6AAAAABL3L4D7CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEOJRGAZTCMJSGE> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- *Brian Wardell* *Senior Product Manager, AI* [image: Mitratech] <http://www.mitratech.com> +44 (0) 1628 600 900 [image: LinkedIn] <https://www.linkedin.com/company/165007/>

-- The information contained in this communication is confidential and is intended only for the use of the addressee. It is the property of Mitratech Holdings, Inc. Any unauthorized use, disclosure or copying of this communication or any part thereof is strictly prohibited and may be unlawful. If you have received this communication in error, please notify us immediately and destroy this communication and all copies thereof, including all attachments.