[janchorowski]

Sure: when a new response is produced because some source documents have changed we ask an LLM to compare the responses and tell if they are significantly different. Even a simplistic prompt, like the one used in the example would do:

    Are the two following responses deviating?
    Answer with Yes or No.

    First response: "{old}"

    Second response: "{new}"

(used in https://github.com/pathwaycom/llm-app/blob/69709a2cf58cdf6ea...)

[pstorm]

Couldn't you just compare the similarity of the embeddings? I imagine that would work in the vast majority of cases and save a lot of LLM calls.

[janchorowski]

That's a good idea, the deduplication criterion is easy to change, using an llm is faster to get started, but after a while a corpus of decisions is created and can be used to either select another mechanism, or e.g. train one on top of bert embeddings.