Hi HN, We built ReasonDB because vector databases break down when agents need to reason over structured relationships. ReasonDB combines: • knowledge graphs • reasoning queries • LLM-friendly APIs Example: agent.reason("Why did the refund fail?") which traces relationships across events, policies and logs. Repo: https://github.com/brainfish-ai/ReasonDB Would love feedback. |
We ran a small benchmark on a real-world insurance corpus: • 4 policy documents • ~1,900 hierarchical nodes • 100 queries across 6 complexity tiers
Comparing ReasonDB to a typical RAG pipeline (LangChain / LlamaIndex defaults):
Metric ReasonDB Typical RAG Pass rate 100% (12/12) 55–70% Context recall 90% avg 60–75% Median latency 6.1 s 15–45 s
The key difference is that ReasonDB performs BM25 candidate selection + LLM-guided traversal, rather than flat chunk similarity.
⸻
Example reasoning case
One query asked:
“What conditions define recurrent disability?”
The answer was split across two sections: • disability definition clause • policy schedule clause
Flat chunk retrieval returned only the first section.
ReasonDB followed the cross-reference extracted during ingestion, which raised recall from 67% → 100%.