How do I approach ML System Design interview questions?

ML System Design questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master ml system design interviews.

What difficulty level is this interview question?

This is a hard difficulty ML System Design question, commonly asked during Technical Screen rounds at Credit Genie.

What role is this question designed for?

This question is commonly asked for Software Engineer candidates at Credit Genie during technical interviews.

Integrate Chroma and design semantic search API | Credit Genie Interview Question

Quick Overview

This question evaluates a candidate's competency in ML system design and backend engineering, covering integration of a vector store, embedding model selection and schema design, API endpoint design for upsert/delete/query, metadata handling, and consistency between a CRUD datastore and a semantic search index.

System Design: Add Semantic Search to an Existing CRUD Service Using Chroma

Context

You own a document CRUD service (create/read/update/delete) that stores documents with an id, text body, and optional metadata. Extend this service by integrating a Chroma vector store to support semantic search over documents. Assume you can add a background worker if needed, but aim for a minimal, production-ready design.

Tasks

Define the vector collection schema and explain how text embeddings are produced (model choice, dimensionality, normalization, and how metadata is stored).
Implement API endpoints to:
- Upsert documents into the vector store.
- Delete documents (by id and/or by metadata filter).
- Query by vector similarity (semantic search) with optional metadata filters.
Implement a search_query function that returns a response object with a required results list (may be empty; never None ). Include per-result scores and metadata.
Describe how you would handle:
- Indexing strategy and parameters.
- Pagination for vector search results.
- Filtering by metadata.
- Eventual consistency between the CRUD store and the vector index.
Discuss production concerns: latency targets, batching strategies, and error handling (including retries, timeouts, and idempotency).

Quick Overview

Context

Tasks

Define the vector collection schema and explain how text embeddings are produced (model choice, dimensionality, normalization, and how metadata is stored).

Implement API endpoints to:

Upsert documents into the vector store.
Delete documents (by id and/or by metadata filter).
Query by vector similarity (semantic search) with optional metadata filters.

Implement a search_query function that returns a response object with a required results list (may be empty; never None ). Include per-result scores and metadata.

Describe how you would handle:

Indexing strategy and parameters.
Pagination for vector search results.
Filtering by metadata.
Eventual consistency between the CRUD store and the vector index.

Discuss production concerns: latency targets, batching strategies, and error handling (including retries, timeouts, and idempotency).

Integrate Chroma and design semantic search API

Quick Overview

System Design: Add Semantic Search to an Existing CRUD Service Using Chroma

Context

Tasks

Solution

Comments (0)

Integrate Chroma and design semantic search API

Quick Overview

System Design: Add Semantic Search to an Existing CRUD Service Using Chroma

Context

Tasks

Solution

Comments (0)