Does GPTCache support storing retrived documents as well as LLM answers?

[renuka010]

I understood how we store query and LLM responses in GPTCache. I want to cache retrieved documents along this. I saw similar example here https://gptcache.readthedocs.io/en/latest/bootcamp/langchain/question_answering.html

llm = LangChainLLMs(llm=OpenAI(temperature=0))
chain = load_qa_chain(llm, chain_type="stuff")
query = "What did the president say about Justice Breyer"
chain.run(input_documents=docs, question=query)

But I had to perform similarity search only for query and able to get answer along with documents in response. Is that possible with GPTCache?

[SimFG]

It is recommended to set cache through langchain, because LangChainLLMs cannot keep up with the update of langchain.
refer to: #585 (comment)

[renuka010]

Got it. Thanks.