The Fifth Elephant OSAI meet-up - Hyderabad edition

The Fifth Elephant OSAI meet-up - Hyderabad edition

Call for Proposals - make a submission; give visibility to your work

Kannan Ramamoorthy

@agentboutiqueai

Semantic Search - Beyond Embeddings & Vector DB

Submitted Aug 27, 2025

Description:

It’s a simple claim that for semantic search, “Capture the embedding of the document and save it during indexing”, “Capture the embedding of the query and do the searching”.

But production grade semantic search requires much more than that like “Choice of eval”, “Choice of model”, “Maturity of the search level you need”, “Hard Negative analysis”, “Improvement and optimization techniques”.

Takeaways

  • Mental model of “What it takes for semantic search” (for Leaders as well as Implementers)
  • Key pointers
  • Tentative Roadmap
  • Walkthrough of a generic eval script that my team is working on(Which I’m planning to opensource as it takes shape)

Audiences:

  • Architects and Tech leads who are implementing and starting with semantic search.
  • Leaders who are driving the “Semantic Search” initiatives in their enterprise/startups.

About Me:

Founder of Agent Boutique AI (new startup that I’m setting up), Ex-Co-founder of TechConative AI.

Technologist, running my own consultant startup with a couple of people. Currently working on solving some of the most interesting AI problems for a client which is trusted by BBC, Times Now, NASA and some other giant media creators.

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jump starting better data engineering and AI futures

Supported by

Community sponsor