Nippon India Mutual Fund improves AI assistant accuracy using advanced RAG methods on Amazon Bedrock
Nippon India Mutual Fund needed an AI assistant that could accurately retrieve information from a large volume of enterprise documents, but naive RAG fell short: similarity-based retrieval missed relevant chunks as document volumes grew, complex structures like nested tables were not parsed correctly, compound questions degraded accuracy, and models produced hallucinated responses.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Custom document parsing
Nippon uses custom parsing to extract relevant details from complex elements like tables, graphs, and images.
After implementing advanced RAG methods, Nippon saw accuracy increase by more than 95%, hallucination reduced by 90–95%, and report generation time drop from 2 days to approximately 10 minutes, with source citations added to improve user confidence.
What failed first
The naive RAG approach had documented limitations at scale: retrieval accuracy degraded with document volume, complex document structures were not parsed correctly, compound questions were handled poorly, and the approach was prone to hallucinations.
Results
Time savedreduced from 2 days to approximately 10 minutes