DEV Community

Cover image for FAISS vs Qdrant vs pgvector: choosing a vector store for a student or startup RAG project
PRANJUL RATHOUR
PRANJUL RATHOUR

Posted on Originally published at pranjulrathour.scult.in

FAISS vs Qdrant vs pgvector: choosing a vector store for a student or startup RAG project

#rag #vectordatabase #faiss #qdrant

Students ask me which vector database to use far more often than they ask how to chunk, which is backwards — but the question deserves a straight answer. I have shipped with FAISS, Qdrant and pgvector. None is universally best; each is best at a stage.

FAISS: the fastest way to start

FAISS is a library, not a server. You build an index in memory, search it in microseconds, and save it to a file. It is perfect for prototypes, hackathons and offline evaluation. Its limits appear the moment you need metadata filtering ("only chunks from this document"), concurrent writes, or an index bigger than your RAM.

Qdrant: a real vector service

Qdrant runs as a service with a clean HTTP API, payload filtering, and persistence out of the box. For document-scoped RAG — a user asks questions about their own uploads only — its filtering is exactly what you need. It is one more container to run, which matters on small hosts; plan the memory budget.

pgvector: vectors next to your data

If your app already has PostgreSQL, pgvector adds a vector column and similarity operators to the database you are already backing up and querying. Joins between chunks and users, documents and permissions become ordinary SQL. It is the choice I reach for when the product has real users and real access control, because one database is easier to operate than two.

A decision table

  • Hackathon or notebook experiment → FAISS.
  • Multi-tenant RAG with per-document filtering and no existing database → Qdrant.
  • Product with users, permissions and PostgreSQL already in place → pgvector.
  • Corpus under 100k chunks and a single server → any of the three; optimise for operational simplicity.

The mistake to avoid

Choosing a vector store before you have an evaluation set. Retrieval quality is decided by chunking, embeddings and hybrid search — not by the database. Pick the store that fits your hosting and data model, then spend your effort on the pipeline in front of it.

About Pranjul Rathour

Pranjul Rathour speaking from the podium at VSICS, Kanpur
At the VSICS podium, Kanpur

Pranjul Rathour holding a trophy and a certificate of merit after a win
Trophy and certificate after a win

Pranjul Rathour presenting evaluation criteria — feasibility, innovation, practicality, problem solving — on a projector screen
Walking a room through evaluation criteria

Pranjul Rathour presenting BrandHive on a projector screen
Presenting BrandHive

Pranjul Rathour in a shirt and tie holding a microphone in front of a career-opportunities slide
A career session for students

Pranjul Rathour is a GenAI engineer from Kanpur, India, and CTO at SCULT INDIA, currently shipping production RAG,
fine-tuning and agentic AI systems, mentoring 200+ students through TechVerse Enclave, and judging and speaking at
student hackathons across India. Updated 2026-09-06.

Reach out if you want to talk GenAI, book a campus session, or invite him to judge:

Pranjul Rathour · GenAI engineer, 3x hackathon winner, campus mentor. Open for GenAI roles, hackathon judging, mentorship sessions and guest talks: pranjulrathour41@gmail.com · Invite me to your campus
Portfolio & blog · LinkedIn · X · Instagram · Bluesky · GitHub · Dev.to

Top comments (0)