Design an AI-Powered Semantic Search Engine — System Design Interview Practice

Interview prompt

Design embedding, hybrid retrieval, vector search, filtering, and relevance ranking so users can search using a natural-language query reliably at scale.

• Define the source of truth for documents, embeddings, and index versions and make retries idempotent.
• Use bounded, partitioned state to meet 1B documents and 100K queries per second and p95 <=300ms search.
• Separate the critical request path from embedding, indexing, re-ranking, and evaluation.
• Explain consistency, failure recovery, authorization, observability, and a degraded mode.

Requirements and scale assumptions

• Support the core workflow to search using a natural-language query.
• Expose status, results, and freshness appropriate to embedding, hybrid retrieval, vector search, filtering, and relevance ranking.
• Support authorization, validation, updates, deletion, and recovery semantics.
• Meet p95 <=300ms search under normal load.
• Scale to 1B documents and 100K queries per second without a single hot key or unbounded synchronous work.
• Do not lose committed state; make retries and duplicate events safe.
• Degrade safely when downstream workers, caches, or external dependencies fail.
• 1B documents and 100K queries per second
• Partition by the primary tenant, user, item, or geographic key and isolate hot partitions.
• Keep serving state bounded; retain raw events or durable records for replay and auditing.

• Peak scale: 1B documents — Capacity assumption that drives partitioning and backpressure.
• Latency target: p95 <=300ms search — User-facing budget for the primary request or read path.
• Durable boundary: Committed before async — The source of truth is documents, embeddings, and index versions.
• Async boundary: At-least-once workers — Keep embedding, indexing, re-ranking, and evaluation off the synchronous path.

Key entities

• DocumentVersiondocumentId, sourceVersion, contentHash, aclVersion, language, updatedAt

  Canonical semantic search engine content and access-policy version used for indexing.

• IndexGenerationgenerationId, sourceWatermark, schemaVersion, status, alias, createdAt

  Rebuildable semantic search engine index generation that can be validated before an atomic alias swap.

• QuerySessionqueryId, tenantId, normalizedQuery, filters, generationId, nextCursor

  Auditable semantic search engine query context with filters, cursor, and the generation used to answer it.

• RankingFeedbackqueryId, documentId, position, action, modelVersion, occurredAt

  Privacy-scoped semantic search engine relevance signal for offline evaluation and ranking improvement.

Data flow

1. 1. Accept and authorize source changesThe semantic search engine ingestion boundary validates content, tenant ownership, ACLs, versions, and idempotency before publishing a document change.
2. 2. Retrieve and rank candidatesThe query service applies authorization filters, retrieves from the active semantic search engine generation, ranks within the latency budget, and returns generation freshness.
3. 3. Build a safe index generationPartitioned workers transform semantic search engine documents, checkpoint progress, validate counts and ACL parity, then atomically swap the serving alias.
4. 4. Handle freshness and deletesTombstones and ACL changes propagate through the same pipeline so deleted or newly restricted semantic search engine content is not left searchable.
5. 5. Measure relevance and recoverFeedback, query traces, lag, and failed partitions drive semantic search engine ranking evaluation, replay, and bounded degraded behavior.

Deep dives and trade-offs

• ACL correctness and index generationsFilter semantic search engine results by tenant and effective ACL, or prove the active generation contains the same policy snapshot. Build shadow generations and swap aliases atomically so partial reindexes are never visible. Keep source versions and ACL snapshots for replay when permissions or content change.
• Latency, cursors, and graceful degradationUse bounded candidate retrieval, stable sort keys, and generation-aware cursors for semantic search engine pagination. Serve the last healthy generation when a new build is incomplete, but expose freshness and avoid silently violating authorization. Protect the query path with timeouts, circuit breakers, and per-tenant quotas.
• Relevance feedback without leakageSeparate semantic search engine click or conversion signals from personally identifying data and honor retention or deletion requests. Evaluate ranking by query class and tail latency, not only aggregate click-through. Use replayable query sets and staged model or synonym changes before production rollout.
• Synchronous indexing versus queued indexingCommit the source version synchronously and index asynchronously with a visible freshness contract. Waiting for index mutation makes writes fragile and cannot guarantee immediate consistency at scale.
• Denormalized ACL fields versus filter-time checksDenormalize safe, versioned authorization facts when it meets the policy model, while retaining a source-of-truth check for sensitive results. Stale permissions can become a data-leak path if index updates are treated as authoritative.
• Lexical, vector, or hybrid retrievalStart with the retrieval method that matches the corpus and latency budget, then add hybrid ranking behind an experiment and rollback boundary. Adding embeddings without freshness, explainability, or access-control design increases cost without improving user trust.