nextRound
TechnologiesCoding ProblemsBookmarksLearning Paths
nextRound
TechnologiesCoding ProblemsBookmarksLearning Paths
nextRound

AI-powered interview preparation platform. Practice with curated questions, mock interviews, and personalized learning paths to crack your dream tech interview.

Quick Links

  • Technologies
  • Saved Questions
  • Pricing

Company

  • About Us
  • Contact Us

Legal

  • Privacy Policy
  • Terms of Use

© 2026 nextRound. All rights reserved.

TOPIC OVERVIEW

langchain/RAG

Give an LLM access to your own documents and data so it can answer using information outside its built-in knowledge.

20 QuestionsAdvancedHigh Priority ~15 min read

Retrieval-Augmented Generation, or RAG, combines information retrieval with language generation. Instead of asking a model to answer entirely from what it already knows, the application first finds relevant information from a knowledge source and then gives that information to the model as context.

A typical RAG system loads and splits documents, creates embeddings, stores them in a vector database, retrieves relevant chunks for a question, and passes those chunks to the model. The quality of the final answer depends heavily on retrieval quality, chunking, metadata, context construction, and the model itself.

What you'll walk away knowing

What RAG solves
How documents become searchable knowledge
How retrieval and generation work together
Why chunking, embeddings, and retrieval quality matter
1What is a Document object in LangChain — what are pageContent and metadata fields and why does metadata matter in RAG?Intermediate2What are Document Loaders in LangChain and how do you choose the right loader for PDFs, web pages, Notion, Google Drive, or SQL databases?Intermediate3What is RAG and why is it preferred over fine-tuning for domain-specific knowledge in production applications?Intermediate4How do you implement RAG evaluation — what metrics like faithfulness, answer relevancy, and context recall do you measure using RAGAS?Intermediate5What is HNSW indexing and why does it make approximate nearest neighbor search fast at scale?Advanced6What are the core components of a RAG pipeline in LangChain — Document Loaders, Text Splitters, Embeddings, Vector Stores, Retrievers, and Chains?Intermediate7What is the difference between dense embeddings and sparse embeddings (BM25) — when would you combine both in a hybrid search?Intermediate8What is an Embedding in the context of RAG — what does it represent and why is cosine similarity used to compare them?Intermediate9What is a Vector Store and how does it differ from a traditional relational or document database?Intermediate10How do you choose the right embedding model — what tradeoffs exist between OpenAI embeddings, Cohere, HuggingFace, and local models like nomic-embed?Advanced11What is a MultiQueryRetriever and how does it improve recall by generating multiple phrasings of the same question?Intermediate12How do you optimize retrieval latency in production — what caching, pre-fetching, or index optimization strategies do you apply?Advanced13What is HyDE (Hypothetical Document Embedding) and how does it improve retrieval for vague or abstract queries?Advanced14How do you preserve and propagate source metadata (filename, page number, URL, timestamp) through the loading and splitting pipeline?Intermediate15What is chunk size and chunk overlap in text splitting — how do you decide the right values for your use case?Intermediate16What is a Re-ranker (cross-encoder) and where does it fit in the RAG pipeline after initial retrieval?Intermediate17How do you implement namespace or tenant isolation in a vector store for a multi-tenant RAG application?Advanced18What is a ParentDocumentRetriever — how does it index small chunks but return larger parent chunks to the LLM?Intermediate19How do you handle incremental updates to a vector store — adding, updating, and deleting documents without full re-indexing?Intermediate20How do you build a citation system that maps each sentence in the LLM's answer back to the exact source chunk it came from?Advanced21How do you implement Step-Back Prompting in a RAG pipeline to improve retrieval for highly specific questions?Advanced22How do you handle embedding model upgrades in production — what happens to your existing vectors when you switch models?Advanced23How do you handle multilingual RAG — embedding and retrieving documents in multiple languages for a global user base?Advanced24How do you handle long context RAG — when retrieved chunks exceed the LLM's context window, what strategies do you apply?Advanced25How do you detect and mitigate hallucination in RAG outputs — what role does citation and source grounding play?Advanced26How do you implement hybrid search combining dense vector search with BM25 keyword search using EnsembleRetriever?Intermediate27What is Self-Query Retrieval and how does it allow the LLM to generate structured metadata filters alongside the semantic query?Intermediate28How do you design a RAG pipeline with LangGraph — turning retrieval, grading, and generation into discrete stateful graph nodes?Advanced29What is the difference between semantic search and keyword search and why does RAG rely on semantic similarity?Intermediate30What are the tradeoffs between vector stores like Pinecone, Weaviate, Chroma, pgvector, and FAISS — how do you choose for production?Advanced31What is the difference between RecursiveCharacterTextSplitter and CharacterTextSplitter — when would you use one over the other?Intermediate32How do you handle structured documents like tables, code blocks, or markdown files during the splitting phase to avoid breaking semantic meaning?Intermediate33What is the difference between a Retriever and a Vector Store in LangChain — why is the abstraction separation important?Intermediate34What is CRAG (Corrective RAG) and how does it add a grading step to decide whether retrieved docs are relevant before answering?Advanced35How do you implement a fallback strategy when retrieval returns no relevant documents — how do you avoid hallucination in this case?Advanced36What is Self-RAG and how does the LLM decide when to retrieve, whether retrieved docs are relevant, and whether the answer is grounded?Advanced37What is the difference between Stuff, MapReduce, Refine, and MapRerank document chain strategies — when do you use each?Intermediate38What is query decomposition and how do you break a complex multi-part question into sub-queries for better retrieval?Intermediate39How do you build a Conversational RAG chain that maintains chat history and reformulates follow-up questions into standalone queries?Intermediate40What is a similarity score threshold in retrieval and how do you use it to filter out low-confidence results?Intermediate41What is a SemanticChunker and how does it differ from fixed-size character-based splitting?Intermediate42How do you implement access control at the retrieval layer — ensuring users only retrieve documents they are authorized to see?Intermediate43What is Contextual Compression in LangChain retrieval and how does it reduce noise in retrieved chunks?Intermediate44What is MMR (Maximal Marginal Relevance) retrieval and how does it balance relevance with diversity of results?Intermediate45How do you load and split documents lazily (streaming) to handle very large files without running out of memory?Intermediate46How do you efficiently batch embed a large corpus of documents without hitting rate limits or memory constraints?Intermediate
All Topics
1
Basics
Models
Messages
2
Agents
Tools
Middleware
Memory
3
MCP
Multi Agents
Human in the loop
4
RAG
Context Engineering
Sharethis topic

Share via WhatsApp, X, Facebook, LinkedIn or copy link. Open Graph preview enabled.