My first RAG had no vector store. On purpose. Mine was 8 agents arguing about SQL. No embeddings anywhere. It mostly worked. One gap kept me up at night.
in data/raw/ and produces a combined multi-scheme CSV. GET /mf/{scheme_code} → Full NAV history + metadata GET /mf/{scheme_code}/latest → Only the most recent NAV ...
Including 5-hop chains. Proof it works: BIRD Benchmark on a 60-table superhero database → Resolved a complex 5-hop query by automatically chaining through all intermediate tables 🏆 No more "valid SQL ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results