# Semantic Product Search on AWS: HK Infosoft Case Study

> Natural-language search that understands intent, with budget-aware recommendations. How DevOps TechLab built it on AWS.

- Page: https://devopstechlab.com/resources/cases/hk-infosoft
- Last updated: 2026-11-14
- Contact: sales@devopstechlab.com · +91 90670 77200 (call or WhatsApp) · Monday to Friday, 10 AM to 7 PM IST
- This is a plain-text copy of the page above for AI tools. The page itself is the reference.

---
1. [Home](https://devopstechlab.com/)
2. [Resources](https://devopstechlab.com/resources/)
3. [Case studies](https://devopstechlab.com/resources/case-studies)
4. HK Infosoft

AI & GenAI AWS Client story

HK Infosoft

# Search the gift catalogue the way customers talk, with budget built in

DevOps TechLab built a semantic product discovery platform on Amazon Bedrock for HK Infosoft: employees search in natural language and find relevant, budget-aware products in seconds instead of reviewing large catalogues by hand.

By Janak Thakkar, Founder & CEO, DevOps TechLab Corporate gifting 3 min read

premium onboarding gifts under ₹2,500

Understands the intent: **welcome gifts for new joiners** , **premium** , **₹2,500 or less** .

- Relevance
- Budget limit
- Vendor preference
- Availability

Illustration of the difference, not client data

In short

HK Infosoft runs corporate gifting with a multi-vendor catalogue, where keyword search missed requests like “premium onboarding gifts under ₹2,500”. DevOps TechLab built semantic search on Amazon Bedrock with Titan Text Embeddings V2 and pgvector. Staff now find relevant, budget-aware products in seconds instead of reviewing large catalogues by hand.

Official references: [What is Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) · [AWS Well-Architected Framework](https://docs.aws.amazon.com/wellarchitected/latest/framework/welcome.html)

ISO 27001 · SOC 2 · Working with companies across India and abroad from Ahmedabad, in IST

## Executive summary

HK Infosoft runs corporate gifting operations with a catalogue sourced from multiple vendors. Customer requests such as “premium onboarding gifts under ₹2,500” rarely matched catalogue wording, so keyword search failed and staff reviewed hundreds of products by hand. DevOps TechLab built a serverless semantic search platform on Amazon Bedrock that understands intent and combines relevance with budget, vendor preference and availability.

**Client:** HK Infosoft · Corporate gifting

**Business problem:** Keyword search failed on natural-language requests, so staff reviewed hundreds of products by hand.

**What we delivered:** Semantic product search with budget-aware recommendations, on Amazon Bedrock.

**Engagement:** Discovery workshop, design, build and security, then ongoing optimisation by DevOps TechLab.

**Outcome:** Relevant products in seconds, with less manual effort and better search accuracy.

## The business challenge

Customer requests did not match the way the catalogue was written, so keyword search failed. Staff reviewed hundreds of products across categories before recommending anything, budget checks were manual, and quality depended on individual experience.

### Why it mattered

- **Keyword search failed**

  Requests in customers’ own words did not match catalogue wording.
- **Lengthy manual review**

  Staff went through hundreds of products before recommending anything.
- **Manual budget checks**

  Every recommendation had to be checked against the budget by hand.
- **Quality depended on the person**

  Results varied with individual experience of the catalogue.

## What HK Infosoft set out to achieve

1. Search the catalogue by intent, in natural language.
2. Combine relevance with budget limits, vendor preference and availability.
3. Cut the time staff spend reviewing products.
4. Use managed AI rather than self-managed models.
5. Run on a scalable, serverless base.

## The solution: semantic product discovery on Amazon Bedrock

Employees type the request the way the customer said it. The platform finds products by meaning, then ranks them using budget limits, vendor preference and availability, and shows the results in a web application.

### Key design choices

- **Managed AI over self-managed**

  Amazon Bedrock with Titan Text Embeddings V2 and Amazon Nova Lite, chosen over running self-managed AI.
- **Search by meaning**

  pgvector with HNSW indexing in Aurora PostgreSQL Serverless v2 finds products by intent, not keywords.
- **Scales with demand**

  API Gateway, AWS Lambda and Aurora Serverless v2, with Amazon RDS Proxy handling concurrent connections.
- **Fast web delivery**

  A React application served from Amazon S3 and Amazon CloudFront.

## Security and governance

Catalogue and customer data stay inside a private AWS environment, defined entirely as code.

- **Secrets managed**

  Credentials are kept in AWS Secrets Manager.
- **Least-privilege access**

  AWS IAM roles control what each component can reach.
- **Private database**

  Private subnets and Amazon RDS Proxy keep the database off the internet; VPC endpoints are recommended in place of a NAT gateway.
- **Infrastructure as code**

  Everything is deployed with AWS CloudFormation.

## Architecture on AWS

Architecture as built

| AWS service | Role in the solution |
| --- | --- |
| Amazon Bedrock · Titan Text Embeddings V2 | Understands requests and products by meaning |
| Amazon Bedrock · Amazon Nova Lite | Generative AI model used alongside the semantic search |
| Amazon Aurora PostgreSQL Serverless v2 · pgvector (HNSW) | Catalogue data and semantic search |
| Amazon API Gateway · AWS Lambda | Search and recommendation logic |
| Amazon RDS Proxy | Handles concurrent connections from Lambda |
| Amazon S3 · Amazon CloudFront | Delivers the React web application |
| AWS Secrets Manager · AWS IAM · AWS CloudFormation | Secrets, access control and infrastructure as code |

## How we delivered

1. 01 **Discovery workshop**

   Analysed the catalogue and metadata, picked semantic search as the highest-value capability, and chose Amazon Bedrock over self-managed AI.
2. 02 **Design**

   API Gateway, Lambda, Aurora Serverless v2 and Bedrock, with architecture, security and running costs reviewed before the build.
3. 03 **Build & secure**

   Natural-language search with budget, vendor and availability logic, a React app on S3 and CloudFront, on private infrastructure.
4. 04 **Optimise**

   Aurora scaling with demand, RDS Proxy for concurrent connections, and VPC endpoints recommended in place of a NAT gateway.

## Business outcomes

Finding the right products for a request no longer means reviewing the whole catalogue by hand.

- **Relevant products in seconds**

  Employees search in natural language and find relevant products in seconds.
- **Budget built in**

  Recommendations combine relevance with budget limits, vendor preference and availability.
- **Better search accuracy**

  Search understands intent, not just matching words.
- **Less manual effort**

  Staff no longer review large catalogues by hand before recommending.
- **A scalable base**

  A serverless platform that grows with the catalogue.

## What’s next

The same platform can extend to new vendors and categories. DevOps TechLab continues to optimise search quality and running cost as HK Infosoft’s catalogue grows.

**About DevOps TechLab**

DevOps TechLab is an AWS Advanced Tier Services Partner with the AWS Generative AI Competency and AWS SMB Competency. We design, build and run cloud and generative AI solutions on AWS for growing businesses, with 265+ cloud environments under management.

### Want AI like this working for your sales team?

Tell us where quotes, searches or proposals slow your team down. We will suggest a small first build on Amazon Bedrock, with the running cost estimated up front.

[Next story · AI & GenAI **Chatwit: Conversational AI agent that investigates sales performance** Chat transcript design · 2 min read](https://devopstechlab.com/resources/cases/chatwit)

## More client stories

[AI & GenAI **Dexlyn: Autonomous BI agent that explains what drives revenue**](https://devopstechlab.com/resources/cases/dexlyn) [**−36%** monthly cloud bill Migration **Gamerji: From AWS to Azure in 3 weeks, with a 36% lower cloud bill**](https://devopstechlab.com/resources/cases/gamerji) [Migration **Devine Globe: From managed hosting to a secure, production-ready AWS environment**](https://devopstechlab.com/resources/cases/devine-globe)

Keep exploring

## The work behind this story

- [Service **AI consulting services** Assistants, chatbots and agents on Bedrock, Azure OpenAI or Vertex AI.](https://devopstechlab.com/solutions/generative-ai-data/)
- [Guide **RAG on AWS, Azure or Google Cloud** AI that answers from your own documents: how it works and what it costs.](https://devopstechlab.com/resources/blog/ask-your-documents)
- [Case study **Visual product search case study** Spotem: upload a photo, get similar products in seconds.](https://devopstechlab.com/resources/cases/spotem)
- [Industry **Cloud for retail & e-commerce** Storefronts that hold up on sale day and costs that shrink after peak.](https://devopstechlab.com/industries/retail-ecommerce/)

FAQ

## Questions about HK Infosoft's semantic product search

**Still have a question?**

Send it with the form below and an engineer will reply.

Ask us

###

It understands the intent of a request rather than matching words. Take "premium onboarding gifts under ₹2,500". It looks for premium welcome gifts for new joiners at ₹2,500 or less, even when the catalogue uses different words.

Results combine relevance with business rules. Relevance comes from Titan Text Embeddings V2, finding the products closest in meaning. The recommendation logic then applies the budget limit, vendor preference and availability.

API Gateway, Lambda, Aurora PostgreSQL Serverless v2 and Amazon Bedrock, with Titan Text Embeddings V2 and pgvector HNSW search. The React app runs on S3 and CloudFront, and RDS Proxy handles concurrent Lambda connections.

It uses AWS Secrets Manager, RDS Proxy, IAM roles, private subnets and VPC endpoints, and is deployed with CloudFormation. Architecture, security and running costs were reviewed before the build started.

Before, staff reviewed hundreds of products and checked budgets by hand, and quality depended on individual experience. Now employees search in natural language and find relevant products in seconds, with less manual effort.

Talk to an engineer

## Start with a 20-minute review. Leave with a plan.

An engineer looks at your current setup, points out what’s costing you money or risk, and tells you what we’d fix first. No sales deck, no obligation to go ahead.

[Sales and general enquiries **sales@devopstechlab.com**](mailto:sales@devopstechlab.com) [Call us **+91 90670 77200**](tel:+919067077200)

Every month you wait, the bill grows, the audit gets harder and the AI project waits another quarter.
