ArxivRetriever Question

[monkeydust]

Maybe I am missing something but I was expecting this to return an answer given the paper (1903.0914) is about the topic in question - what am I doing wrong?

from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationalRetrievalChain
retriever = ArxivRetriever(load_max_docs=2)
docs = retriever.get_relevant_documents(query='1903.09140')
model = ChatOpenAI(model_name='gpt-4') # switch to 'gpt-4'
qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)

questions = [
    "How do you calculate TCA for corporate bonds? Include references to answer",
] 
chat_history = []

for question in questions:  
    result = qa({"question": question, "chat_history": chat_history})
    chat_history.append((question, result['answer']))
    print(f"-> **Question**: {question} \n")
    print(f"**Answer**: {result['answer']} \n")

-> Question: How do you calculate TCA for corporate bonds? Include references to answer

Answer: I'm sorry, but the information provided does not contain any details on calculating TCA (Total Cost Analysis) for corporate bonds. The context provided discusses a tailored CRC-aided SCL (TCA-SCL) decoding algorithm for polar codes in digital communication and signal processing. It is unrelated to finance or corporate bonds.