Questions
36 of 46
1What is RAG and why is it preferred over fine-tuning for domain-specific knowledge in production applications?
2What are the core components of a RAG pipeline in LangChain — Document Loaders, Text Splitters, Embeddings, Vector Stores, Retrievers, and Chains?
3What is the difference between semantic search and keyword search and why does RAG rely on semantic similarity?
4What is an Embedding in the context of RAG — what does it represent and why is cosine similarity used to compare them?
5What is a Vector Store and how does it differ from a traditional relational or document database?
6What is the difference between a Retriever and a Vector Store in LangChain — why is the abstraction separation important?
7What is a Document object in LangChain — what are pageContent and metadata fields and why does metadata matter in RAG?
8What are Document Loaders in LangChain and how do you choose the right loader for PDFs, web pages, Notion, Google Drive, or SQL databases?
9What is the difference between RecursiveCharacterTextSplitter and CharacterTextSplitter — when would you use one over the other?
10What is chunk size and chunk overlap in text splitting — how do you decide the right values for your use case?
11How do you handle structured documents like tables, code blocks, or markdown files during the splitting phase to avoid breaking semantic meaning?
12How do you load and split documents lazily (streaming) to handle very large files without running out of memory?
13What is a SemanticChunker and how does it differ from fixed-size character-based splitting?
14How do you preserve and propagate source metadata (filename, page number, URL, timestamp) through the loading and splitting pipeline?
15How do you choose the right embedding model — what tradeoffs exist between OpenAI embeddings, Cohere, HuggingFace, and local models like nomic-embed?
16What is the difference between dense embeddings and sparse embeddings (BM25) — when would you combine both in a hybrid search?
17How do you handle embedding model upgrades in production — what happens to your existing vectors when you switch models?
18How do you efficiently batch embed a large corpus of documents without hitting rate limits or memory constraints?
19What are the tradeoffs between vector stores like Pinecone, Weaviate, Chroma, pgvector, and FAISS — how do you choose for production?
20How do you implement namespace or tenant isolation in a vector store for a multi-tenant RAG application?
21How do you handle incremental updates to a vector store — adding, updating, and deleting documents without full re-indexing?
22What is HNSW indexing and why does it make approximate nearest neighbor search fast at scale?
23What is a similarity score threshold in retrieval and how do you use it to filter out low-confidence results?
24What is MMR (Maximal Marginal Relevance) retrieval and how does it balance relevance with diversity of results?
25What is a MultiQueryRetriever and how does it improve recall by generating multiple phrasings of the same question?
26What is Contextual Compression in LangChain retrieval and how does it reduce noise in retrieved chunks?
27What is a ParentDocumentRetriever — how does it index small chunks but return larger parent chunks to the LLM?
28What is HyDE (Hypothetical Document Embedding) and how does it improve retrieval for vague or abstract queries?
29What is Self-Query Retrieval and how does it allow the LLM to generate structured metadata filters alongside the semantic query?
30How do you implement hybrid search combining dense vector search with BM25 keyword search using EnsembleRetriever?
31What is a Re-ranker (cross-encoder) and where does it fit in the RAG pipeline after initial retrieval?
32What is the difference between Stuff, MapReduce, Refine, and MapRerank document chain strategies — when do you use each?
33How do you build a Conversational RAG chain that maintains chat history and reformulates follow-up questions into standalone queries?
34What is query decomposition and how do you break a complex multi-part question into sub-queries for better retrieval?
35How do you implement Step-Back Prompting in a RAG pipeline to improve retrieval for highly specific questions?
36What is CRAG (Corrective RAG) and how does it add a grading step to decide whether retrieved docs are relevant before answering?
37What is Self-RAG and how does the LLM decide when to retrieve, whether retrieved docs are relevant, and whether the answer is grounded?
38How do you implement a fallback strategy when retrieval returns no relevant documents — how do you avoid hallucination in this case?
39How do you implement RAG evaluation — what metrics like faithfulness, answer relevancy, and context recall do you measure using RAGAS?
40How do you detect and mitigate hallucination in RAG outputs — what role does citation and source grounding play?
41How do you build a citation system that maps each sentence in the LLM's answer back to the exact source chunk it came from?
42How do you handle multilingual RAG — embedding and retrieving documents in multiple languages for a global user base?
43How do you optimize retrieval latency in production — what caching, pre-fetching, or index optimization strategies do you apply?
44How do you implement access control at the retrieval layer — ensuring users only retrieve documents they are authorized to see?
45How do you handle long context RAG — when retrieved chunks exceed the LLM's context window, what strategies do you apply?
46How do you design a RAG pipeline with LangGraph — turning retrieval, grading, and generation into discrete stateful graph nodes?
langchainlangchain
Basics
Agents
Models
Messages
Tools
Middleware
Memory
MCP
Multi Agents
RAG
Context Engineering
Human in the loop
36 / 46

What is CRAG (Corrective RAG) and how does it add a grading step to decide whether retrieved docs are relevant before answering?

CRAG (Corrective Retrieval-Augmented Generation) adds a grading step between retrieval and generation. A small LLM grader evaluates the relevance of each retrieved document, then triggers correction (e.g., web search) or falls back to the LLM's internal knowledge if all documents are deemed irrelevant.

Corrective Retrieval-Augmented Generation (CRAG) introduces a feedback loop into the RAG pipeline. After retrieving documents, a lightweight LLM grader assesses how relevant each document is to the query. If the grader finds sufficient relevant content, generation proceeds normally. If not, CRAG can trigger a correction action: rewriting the query, performing a web search, or using the LLM's parametric knowledge as a fallback. This prevents hallucination when retrieval fails.[reference:8][reference:9]

Implementing CRAG with LangGraph and Grading
Correction Strategies in CRAG
  1. 1

    Rewrite Query: Use an LLM to reformulate the query and re‑retrieve.

  2. 2

    Web Search Fallback: Call an external search API (e.g., Tavily, Google) to fetch additional context.

  3. 3

    Parametric Knowledge: Rely on the LLM's internal training data when no relevant documents are found.

  4. 4

    Confidence Thresholds: Tune grader thresholds to balance precision and recall.

Difficulty: 7/10
Topics: retrieval augmentation, document grading, LangChain pipelines

Scenario Questions

0-2 years experience
  1. 1

    Suppose you need to build a simple Q&A bot with LangChain that uses a vector store. How would you incorporate a grading step to filter retrieved documents before generating the answer?

  2. 2

    If the grader incorrectly marks a relevant document as irrelevant, what would the user see, and how could you quickly debug it?

2-5 years experience
  1. 1

    You added a CRAG pipeline to an existing RAG feature, but the latency increased noticeably. Walk me through how you would identify the bottleneck and what trade‑offs you might consider.

  2. 2

    During testing you notice that the grader sometimes returns low scores for documents that contain the exact answer phrase. What could cause this, and how would you adjust the prompt or model to fix it?

  3. 3

    Explain how you would design a fallback when the grader filters out all retrieved docs—what should the system do next?

5-8 years experience
  1. 1

    Design a scalable CRAG architecture for a product that serves millions of queries per day. Discuss how you would shard the vector store, cache grading results, and handle model serving.

  2. 2

    What are the failure modes of the grading component in a distributed LangChain deployment, and how would you mitigate them?

  3. 3

    If you need to support multiple languages, how would you extend the grading step without duplicating pipelines?

8+ years experience
  1. 1

    Your organization wants to migrate from a custom RAG implementation to LangChain with CRAG across several teams. What governance, versioning, and monitoring strategy would you put in place to ensure consistency and reliability?

  2. 2

    Discuss the long‑term maintenance implications of embedding a grading LLM in the retrieval pipeline. How would you handle model upgrades, cost management, and data drift?

  3. 3

    How would you evaluate whether adding a grading step is worth the added complexity for a legacy knowledge‑base system that already has high answer accuracy?

Follow-up Questions

  • ❓What metrics would you track to know the grader is improving answer quality?
  • ❓How would you handle a situation where the grader filters out all retrieved documents?
  • ❓Can you compare the cost and latency impact of CRAG versus a plain RAG pipeline?