I am trying to run a QA on a small document. The llm I am using is: gpt-3.5-turbo-instruct.

The retriever I am using is: FAISS

My langchain version is 0.2.6.

When I use RetrievalQA from langchain works:

from langchain.chains import RetrievalQA, RetrievalQAWithSourcesChain
qa = RetrievalQA.from_chain_type(
        llm=oaiConf.llm,  retriever=ret, chain_type="stuff"
    )
    resp = qa.invoke(testQuery)

This throws an error:

qa = RetrievalQAWithSourcesChain.from_chain_type(
        llm=llm, chain_type="stuff", retriever=ret
    )
    
    resp = qa(testQuery)

openai.BadRequestError: Error code: 400 – {‘error’: {‘message’: “This model’s maximum context length is 4097 tokens, however you requested 4586 tokens (4330 in your prompt; 256 for the completion). Please reduce your prompt; or completion length.”, ‘type’: ‘invalid_request_error’, ‘param’: None, ‘code’: None}}