w’re working on the exact same problem it seems 
has you search evolved since this message ? I’m leaning towards this approach:
- pre-processing: narrow the data set to be “searched” by GPT by starting the conversation with a “tag” selection of product ranges, and also keywords"
- feed only the remaining data to gpt through the prompt repeating it in every response
- if the dataset is still too large, cut the process in 2 or 4 (wizard) based on product categories or whatever splits your data
but we have not tested this yet, we are waiting for access to GPT4-32K