Curiosity · Syllabus

Knowledge Graphs in a B.Tech — syllabus & what you learn

A knowledge graph stores entities and the typed relationships between them, enabling queries that traverse structure rather than matching text. Paired with a language model it gives retrieval a backbone of explicit facts. Inside a four-year B.Tech, Knowledge Graphs arrives in layers: programming and mathematics foundations in years one and two, core methods next, and applied depth concentrated in years three and four plus the capstone. Using Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura's B.Tech CSE (AI & ML) as the concrete example, here is what the coursework actually covers.

At a glance

Topic
Knowledge Graphs
VSET programme
B.Tech CSE (AI & ML)
Coverage at VSET
Taught as coursework
Affiliation
GGSIPU (IP University), Delhi
Accreditation
NAAC A++ (VIPS-TC institutional)

How VSET teaches Knowledge Graphs

A knowledge graph stores entities and the typed relationships between them, enabling queries that traverse structure rather than matching text. Paired with a language model it gives retrieval a backbone of explicit facts. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • Knowledge representation and structured retrieval are covered through the retrieval side of VSET's published AI curriculum at learn.engineering.vips.edu — RAG, embeddings and vector databases.
  • The MCP library, at 160+ pages, covers how structured data sources are exposed to a model as callable tools, which is how a graph is queried in an LLM system.
  • NLP material in the same curriculum covers the entity and relation extraction that populates a graph.
  • Taught inside the GGSIPU-affiliated B.Tech CSE (AI & ML) track.

Labs and infrastructure

  • Extraction model runs and embedding generation for graph construction use the AICTE IDEA Lab GPU workstations.

What students actually build

  • RAG capstones over VIPS-TC corpora require students to decide how retrieved knowledge is structured and selected.
  • Student-built MCP servers define exactly which structured sources a model may query.

Frequently asked questions

When does Knowledge Graphs content actually start in a B.Tech?

Meaningful Knowledge Graphs content typically ramps up from the second or third year, after programming and mathematics foundations. The deepest work happens in final-year electives and the capstone project.

Are knowledge graphs covered in the VSET curriculum?

They are covered through the retrieval and knowledge-representation side: RAG, embeddings, vector databases, NLP extraction and the 160+ page MCP library on exposing structured sources to models.

Do students build graph-backed retrieval?

The documented capstone is a RAG system over VIPS-TC corpora; structuring what is retrieved, and exposing it through an MCP server, is part of that build.

What supplies the entities and relations?

The NLP material in the same published curriculum covers the extraction techniques used to populate a graph.

Sources

  1. VSET — Artificial Intelligence department — accessed 2026-08-31
  2. VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
  3. GGSIPU — IP University — accessed 2026-08-31

Related