Before implementing complex solutions like agentic loops, a highly effective first step for improving RAG performance is simply increasing the number of retrieved chunks (k). This simple change fixed nearly half of the initial flagged query failures by preventing relevant notes with similar chunks from consuming the entire context budget.
Implementing an agentic loop, where a model can search multiple times, is not a universal solution and is highly model-dependent. While Anthropic's Haiku model used the extra searches to improve recall, Amazon's Nova Light failed to reformulate its queries effectively, performed slightly worse, and wasted its budget, highlighting significant performance trade-offs.
The process of converting an existing knowledge base to a formal specification like Google's Open Knowledge Format (OKF) serves as a powerful data audit. It forces validation of internal structures, revealing previously unnoticed data quality issues like dead links, ambiguous references, and duplicated content that were invisible in the original, less-structured system.
Knowledge graph-based retrieval is not a replacement for deep vector search but a complement that solves different failure modes. While a larger context window in vector search yielded better overall results, the graph walk succeeded in connecting documents linked by human logic but missed by semantic similarity, proving that the two methods are not mutually exclusive.
Vector embeddings can fail to connect related documents if they lack sufficient semantic similarity. A knowledge graph, by following explicit, human-created links, can fix these specific structural misses. It successfully retrieves relevant context that even a deep vector search (k=15) consistently fails to find, proving its unique value for structurally related data.