In this video, Kaz Sato shows Martin Omander how to add smart semantic search to an app using Agent Retrieval (previously known as Vector Search 2.0).
If a user searches your store for "something warm to wear in the snow" but your database only contains "heavy winter jacket," traditional keyword search fails and returns zero results. This will cost you users and revenue. Unlike traditional keyword search which breaks on simple synonyms and exact string matches, Agent Retrieval maps the actual meaning and intent behind a query, handling synonyms automatically with zero manual embedding pipeline overhead.
?️ *What we cover:*
* The problem: Why keyword search isn't enough for modern user expectations.
* Agent retrieval: How to generate vector embeddings automatically.
* Hybrid search: How to combine keyword and vector search for the best of both worlds.
? *Code & resources:*
* Kaz’s blog post with more details and code → https://goo.gle/4wAXyCH
* Kaz’s notebook that lets you play with semantic search → https://goo.gle/3TyXBAE
* Agent Retrieval documentation → https://goo.gle/4vuaGsr
Chapters:
0:00 Intro
0:45 Why use Semantic search?
2:12 Agent Retrieval can help you
2:28 Code walkthrough
4:14 Demo: Results from Agent Retrieval
4:50 Takeaways
Watch more Serverless Expeditions → https://goo.gle/ServerlessExpeditions
? Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
#ServerlessExpeditions #GoogleCloud
Speakers: Martin Omander, Kaz Sato
Products Mentioned: Agent Retrieval, Vector Search 2.0