Vector Databases

38 questions

Storing and searching embeddings at scale. HNSW, IVF, PQ, DiskANN, hybrid filtering, sharding, vendor selection (Pinecone, Weaviate, Qdrant, Milvus, pgvector).

Sort

Questions

Identify the workload pattern where a traditional ANN-indexed vector database is the wrong tool, and a log-structured or batch-rebuild approach fits better.
Multiple ChoiceHard·Qual 4.0Qdrant
Pick the right vector database for a startup with 2M documents, no DevOps headcount, and a one week launch deadline.
Multiple ChoiceEasy·Qual 4.0Pinecone
Which of these 2026 vector databases are credible at billion-vector scale? Select all that apply.
Multi-selectMedium·Qual 4.0PineconeQdrant
How does an HNSW index handle deletes and updates under a heavy write workload?
FlashcardMedium·Qual 4.0Qdrant
Sharding a vector index that does not fit on one node, how is it typically done, and what's the query-time cost?
Short AnswerMedium·Qual 4.0PineconeQdrant
A vendor's benchmark chart plots QPS against recall@10. What should you look for, and what claim should make you skeptical?
Multiple ChoiceHard·Qual 4.0Pinecone
Define recall@10 for a vector index, and spell out exactly what 'ground truth' means in that definition.
Short AnswerMedium·Qual 4.0Pinecone
Match each vector-compression scheme to its core mechanism.
Match PairsMedium·Qual 4.0Qdrant
Spot the conceptual error: 'We're using PQ instead of HNSW for our vector index because PQ is faster.'
Spot the ErrorMedium·Qual 4.0Zilliz
Walk through how Product Quantization compresses a 1024-dim float32 vector down to 32 bytes, step by step.
Short AnswerMedium·Qual 4.0Zilliz
PQ-based distance computation outruns full float32 distance even after decoding the vectors. Why?
Multiple ChoiceMedium·Qual 4.0Zilliz
At what scale does 'just put it in Postgres with pgvector' stop being the right answer?
Multiple ChoiceMedium·Qual 4.0
pgvector ships two index types. Which should be your default reach in 2026, and why was it added later than the other?
FlashcardEasy·Qual 4.0
Compare namespace-per-tenant against single-shared-index-with-tenant-filter for a B2B RAG product serving 5000 customers.
Short AnswerHard·Qual 4.0Pinecone
A team indexed embeddings under cosine but queried with Euclidean, and recall collapsed. Diagnose the cause.
Short AnswerMedium·Qual 4.0Pinecone
What does Matryoshka representation learning buy a vector-database operator beyond regular embeddings?
Multiple ChoiceMedium·Qual 4.0Pinecone
Predict the shape of recall and latency on an IVF index of 10M vectors as nprobe sweeps from 1 to 50.
Predict OutputMedium·Qual 4.0Pinecone
Spot the error in this candidate's description of IVF's two main parameters.
Spot the ErrorMedium·Qual 4.0Pinecone
Fill in the IVF nlist rule of thumb.
Fill in BlankEasy·Qual 4.0Pinecone
Modern vector databases combine sparse (BM25) and dense vectors at the storage layer via two distinct patterns. Identify them.
Multiple ChoiceMedium·Qual 4.0Pinecone
Estimate the RAM cost of an HNSW index over 100M vectors at 1024 dimensions with M=32, including graph overhead.
Short AnswerHard·Qual 4.0Pinecone
As M grows in an HNSW index, four things move at once. Identify what climbs versus what slows.
Multiple ChoiceMedium·Qual 4.0Pinecone
Explain exactly what the ef_search knob on an HNSW index controls at query time.
FlashcardEasy·Qual 4.0Pinecone
Where does Hamming distance become the natural metric inside a vector database, and how is it implemented efficiently?
FlashcardEasy·Qual 4.0Qdrant
Explain what NVIDIA CAGRA buys you over CPU HNSW and the operational catch that decides whether you should reach for it.
FlashcardMedium·Qual 4.0Zilliz

Showing 1–25 of 38

← PrevNext →