cd /news/artificial-intelligence/how-i-built-a-personal-ai-knowledge-… · home topics artificial-intelligence article
[ARTICLE · art-41449] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

How I Built a Personal AI Knowledge Base with Amazon Aurora pgvector and Next.js — AWS H0 Hackathon

A developer built ChatScroll for the AWS H0 Hackathon, an app that uses Amazon Aurora PostgreSQL with pgvector to create a personal AI knowledge base. The app saves AI answers as searchable 'Scrolls' with semantic search, combining pgvector embeddings, ltree for folder hierarchies, and tsvector for full-text search. The architecture separates structured data in Aurora from chat messages in DynamoDB.

read2 min views1 publishedJun 26, 2026

I built ChatScroll for the AWS H0 Hackathon — an app that

lets you save AI answers as searchable "Scrolls" using

Amazon Aurora PostgreSQL with pgvector for semantic search.

Every day people ask AI assistants valuable questions and

get great answers — then lose them forever. Chat history

is linear, unsearchable, and ephemeral. I kept re-Googling

the same questions knowing I had already found the answer

somewhere but couldn't find it again.

ChatScroll transforms AI conversations into a personal

knowledge library. Save any AI answer as a "Scroll",

organize it automatically, and find it later with

semantic search.

Making search understand MEANING not just keywords. When

you search "blood thinner medication" it should find your

warfarin scroll even though "blood thinner" doesn't appear

in the title.

Amazon Aurora PostgreSQL with the pgvector extension stores

3072-dimensional vector embeddings for every saved Scroll.

When a user saves a Scroll:

When a user searches:

-- Semantic search with threshold
WHERE 1 - (embedding <=> $queryVec) > 0.5
ORDER BY embedding <=> $queryVec
LIMIT 5

What makes Aurora special for this use case is three

extensions working together:

pgvector — stores 3072-dim embeddings, enables cosine

similarity search between vectors

ltree — stores folder paths as dot-separated label trees

(programming.containers

), enables subtree queries without

recursive CTEs

tsvector — powers full-text search with ranking via

ts_rank, combined with pgvector for hybrid search

I made a deliberate choice to use TWO AWS databases:

Amazon Aurora PostgreSQL for structured data:

Amazon DynamoDB for chat messages:

This separation keeps Aurora lean for complex queries

while DynamoDB handles the high-volume chat stream.

Searching "containerization technology" correctly surfaces

the Docker scroll. Searching "blood thinner medication"

finds warfarin — no programming results contaminating it.

Semantic search scoped to the same folder category

ensures results are always relevant.

Live app: https://chatscroll.vercel.app

AWS Architecture: https://chatscroll.vercel.app/aws-showcase

I created this content for the purposes of entering

the AWS H0 Hackathon.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @amazon aurora postgresql 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/how-i-built-a-person…] indexed:0 read:2min 2026-06-26 ·