The community member is asking about using Qdrant with Llama-index to store around 5 million data points, and how setting the top_k parameter to 3 or 4 during querying might impact the costs. Another community member responds that the higher the top_k, the higher the costs, but suggests trying to decrease the chunk size by setting the chunk_size_limit when building the index. The original community member acknowledges and thanks the other for the helpful information.
Hey anyone tried qdrant with llama-index while storing around 5 million of data? Also, wanted to know, in case during querying, if I set top_k to around 3 or 4 to go through 3 or 4 nodes, does it impact the costs by a lot?
