Dynamic Top-k Retrieval Chunks

[Malak-Alaabiad]

Suggest me a specific node or flow to reduce the number of tokens going into the LLM model, considering that my data is stored in a Qdrant collection, and I'm using a custom retriever node to pull only the necessary metadata. This custom retriever node is connected to the Conversational Retriever QA Chain, which then passes the data directly to the LLM.

Now, I want to implement a Dynamic Top-k Retrieval Chunks or a similar flow to achieve the same goal—reducing the tokens sent to the model, which would help minimize the associated costs.

[onestardao]

this sounds like ProblemMap No.10 (paired mapping / format drift).
i have a tiny "semantic firewall" snippet that normalizes the retriever output so you don't need infra changes. want me to paste the short snippet or share the link?