From JSON to Vector Search: What I Learned Storing Structured User Data for AI

Описание и применение

В статье описывается, как в приложении SpendWise интегрировать структурированные данные пользователя в векторную базу для семантического поиска, сохраняя при этом SQL для точных запросов.

Задача

How to make structured user data retrievable and useful for an AI system during user interactions.

Результат

By separating structured storage from semantic search, SpendWise can retrieve relevant user context efficiently, improving AI answer relevance while keeping deterministic queries in SQL.

Рабочий процесс

• Collect structured user data during onboarding
• Store raw JSON in PostgreSQL as source of truth
• Convert relevant fields into natural‑language summaries
• Generate embeddings with an embedding model
• Index embeddings in a vector database with metadata
• When a user asks a question, determine if it requires semantic similarity or exact match
• If semantic, query vector database for relevant context
• If exact or range, query PostgreSQL via SQL
• Feed retrieved context to the LLM for response

Доказательства

"The AI might need context such as: ..."

Источник

"A vector database doesn’t magically understand JSON."

Источник

"If I need an exact value: What is my monthly income? A structured database is perfect."

Источник