BridgePRAG tests smaller question-aware memory for RAG
BridgePRAG is an research tool for RAG that turns a question and a retrieved passage into compact K/V memory instead of feeding long passages directly to the model. That memory is injected into a frozen to help it answer. A small linear adapter adjusts the generated K/V memory before it is used by the model.
The project builds on ideas from MergePRAG and HyperKV, but its main change is that the retrieved memory is shaped by the question before it becomes memory. The repo includes an installable Python package, training and inference command tools, small runnable examples, an diagram, a comparison between passage-only and question-plus-passage memory, tests, docs, and a citation file. In a small setup, question-plus-passage memory scored better than passage-only memory on hit accuracy and F1.
The result is still early research, not a broad benchmark claim.
Key points
- BridgePRAG creates compact K/V memory from both the question and the retrieved passage.
- The memory is injected into a frozen instead of the whole model.
- A small test found better hit accuracy and F1 than passage-only memory.
- The repo includes package code, training and inference tools, examples, tests, docs, and a comparison setup.
- The cost-saving promise is plausible but still unproven at real-agent scale.