Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources

arXiv:2606.28370v1 Announce Type: cross Abstract: Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables. We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem, organized as four architectural layers. First, an indexing layer implements slide-adaptive chunking -- recursive chunking for plain-text slides, hierarchical chunking for structured content such as tables, charts, and key-value blocks - achieving 88.3% on our internal enterprise benchmark. Second, a routing layer built on a LoRA fine-tuned Qwen-2.5-1.5B-Instruct model that produces a dual output - modality decision and complexity assessment at 93.8% accuracy and approximately 7imes lower cost than frontier-model. Third, a retrieval layer executes complexity-adaptive pipelines: a self-correcting NL2SQL agent at 93.9% G-Eval, and Recursive Language Models reaching 91.0% on multi-hop synthesis queries. Finally, a caching layer validates query equivalence across multiple dimensions beyond embedding similarity, achieving zero false cache hits and 8.4imes latency reduction.

Source: arXiv cs.AI | 2026-06-30