pgvector
Data · Build
Store embeddings in PostgreSQL and compare similarity-search results.
All capabilities · Retrieval & knowledge systems
Generate embeddings and run vector search
Choose embedding models, store vectors (pgvector/Chroma/Pinecone), run similarity and hybrid search.
Explore 4 tools for this projectMarket relevance
Which roles ask for this — and how often
Share of job postings in India, per role, that name this capability.
What employers mean
You should be able to…
- Generate embeddings for text chunks and store them in a vector database
- Run similarity search to retrieve the most relevant chunks for a query
- Combine keyword (BM25) and vector search for hybrid retrieval
- Choose an embedding model and dimension appropriate for cost/accuracy tradeoffs
- Set up indexing (HNSW/IVF) for fast approximate nearest-neighbor search at scale
- Re-embed and update the index when source documents change
Needs first: Ingest and chunk documents
Learn — free, link-checked
The few resources that matter
Read · beginner · 30 min · platform.openai.com
Embeddings
Explains embedding models, dimensionality, and similarity metrics with runnable examples. — OpenAI
Read · beginner · 35 min · docs.trychroma.com
Chroma Documentation
Simplest open-source vector DB to get running locally — best on-ramp before touching a managed service. — Chroma
Build from · intermediate · 40 min · github.com
pgvector
The vector extension employers actually ask about when they already run Postgres — indexing (HNSW/IVFFlat) details included. — pgvector (Andrew Kane)
Course · intermediate · 90 min · deeplearning.ai
Building Applications with Vector Databases
Ties embeddings + vector DB choice + hybrid search together into applied examples, not just API syntax. — DeepLearning.AI
Tools for practice
Choose a tool for the job
Start with one tool for each part of your project. You don’t need to learn them all.
4 tools to explore
Chroma
Data · Build
Index embeddings and metadata, then retrieve relevant records for a query.
Qdrant
Data · Build
Build vector search with metadata filtering and inspect retrieval quality.
OpenAI API
Build · Test
Connect model calls, tool use and structured responses to your own application.
Practices & references
- Hybrid search
- Retrieval relevance
Practice
Hybrid search over Indian consumer-tech product reviews
Embed a few thousand Flipkart product reviews into pgvector or Chroma, build a BM25 keyword index over the same corpus, and fuse the two with a re-ranking step. Test it on queries that need both halves at once - 'battery drains fast Redmi phone' needs the model name matched literally and the complaint matched semantically. Benchmark hybrid against vector-only and keyword-only on a query set you write, and measure top-k retrieval latency at the indexed corpus size.
Start from
Flipkart Products Review Dataset on Kaggle - product reviews with ratings and product metadata
Milestones
- Load and clean the reviews, then embed 500+ into the vector store · ~2.5h
- Add a BM25 index and a fusion step over both result sets · ~2.5h
- Write 10 realistic queries and score all three retrieval modes · ~1.5h
- Add re-ranking, measure top-k latency, justify the embedding model · ~1.5h
Done when
- At least 500 reviews embedded and indexed in a vector store (pgvector or Chroma)
- A BM25 keyword index runs alongside vector search, with a combined re-ranked result set
- A test set of 10 realistic queries shows hybrid search outperforming vector-only or keyword-only on relevance
- Query latency for top-k retrieval is measured and reported (target: sub-second on the test dataset)
Prove it
Evidence a recruiter can check
- A relevance table scoring hybrid against vector-only and keyword-only on the same 10 queries
- The query 'battery drains fast Redmi phone' with all three result sets pasted, showing exactly what each mode misses
- Top-k retrieval latency at the indexed corpus size, with the corpus size stated
- The embedding-model choice argued against at least one alternative you actually ran on the same queries
Signal it
Built hybrid retrieval over a few thousand product reviews - vector embeddings fused with a BM25 index and re-ranked - and showed it beating vector-only and keyword-only search on a hand-scored query set at sub-second latency.
Interview
Questions you'll get asked
- How do you choose between pgvector, Chroma, and a managed service like Pinecone for a given project?
- What's the difference between exact and approximate nearest-neighbor search, and when does it matter?
- How would you implement hybrid search combining BM25 keyword matching with vector similarity?
- How do you decide on embedding dimensionality and its cost/latency/accuracy tradeoffs?
- How would you keep a vector index in sync as underlying documents get updated or deleted?
- How do you evaluate whether your embedding model is actually retrieving relevant results?