I shelved a project in March 2025 because it cost $360/month to run.
I rebuilt it in January 2026 for $1.12/month.
Same functionality. Better architecture. No vector database.
It's a RAG pipeline — API Gateway → Lambda → Amazon Bedrock → S3 embeddings → in-memory cosine similarity search. It lives on my site and answers questions about my experience and work history in real time, grounded in structured data I built and curated myself.
The interesting parts:
— Why I killed OpenSearch after less than a week
— How in-memory search outperformed a network call at this scale
— The Anthropic/Bedrock access issue I still haven't fully resolved (Llama works fine)
— Why I handcrafted every knowledge base chunk instead of automating it
I shelved a project in March 2025 because it cost $360/month to run.
I rebuilt it in January 2026 for $1.12/month.
Same functionality. Better architecture. No vector database.
It's a RAG pipeline — API Gateway → Lambda → Amazon Bedrock → S3 embeddings → in-memory cosine similarity search. It lives on my site and answers questions about my experience and work history in real time, grounded in structured data I built and curated myself.
The interesting parts: — Why I killed OpenSearch after less than a week — How in-memory search outperformed a network call at this scale — The Anthropic/Bedrock access issue I still haven't fully resolved (Llama works fine) — Why I handcrafted every knowledge base chunk instead of automating it