Questions
13 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
13 / 46

What is a SemanticChunker and how does it differ from fixed-size character-based splitting?

SemanticChunker is an experimental LangChain splitter that uses embedding similarity to divide text at semantically logical boundaries, unlike fixed-size splitters that cut arbitrarily based on character or token counts.

SemanticChunker is an advanced splitting strategy available in langchain_experimental. Instead of splitting text at arbitrary positions (character count, newlines, spaces), it analyzes the meaning of the content. It computes embeddings for sentences or paragraphs and then splits at points where the semantic similarity between adjacent segments drops below a threshold. This creates chunks that are more semantically coherent, often aligning with topic boundaries or logical sections, which is highly beneficial for retrieval-augmented generation.

Using SemanticChunker

The advantage of SemanticChunker is that it can produce chunks that are more meaningful for the LLM, potentially leading to better retrieval and generation results. However, it comes with a computational cost (requires embedding calculations) and is slower than fixed-size splitters. It is particularly useful for long, narrative texts (e.g., articles, books) where semantic boundaries matter, but may be overkill for simple, factual data. It's an experimental feature, so APIs may change.

Difficulty: 5/10
Topics: text chunking, semantic similarity, langchain

Scenario Questions

0-2 years experience
  1. 1

    If you need to split a 10,000‑character document for a retrieval‑augmented generation pipeline, how would you use LangChain’s SemanticChunker instead of a simple CharacterTextSplitter? Walk me through the steps.

  2. 2

    What would happen if you set the SemanticChunker’s chunk size too low on a document with many short sentences? How would the output differ from a fixed‑size splitter?

  3. 3

    Suppose a paragraph contains a code block; how does the SemanticChunker treat it compared to a character‑based splitter?

2-5 years experience
  1. 1

    You integrated a SemanticChunker into a QA bot, but the latency increased dramatically. What factors could cause this slowdown, and how would you troubleshoot?

  2. 2

    During a migration from CharacterTextSplitter to SemanticChunker, some downstream vector store queries returned fewer matches. Why might that happen, and how would you adjust the chunker parameters?

  3. 3

    If the embeddings model you use has a token limit, how do you decide the optimal chunk size for SemanticChunker versus a fixed‑size splitter?

5-8 years experience
  1. 1

    Design a scalable pipeline that processes millions of documents nightly, using SemanticChunker. What architectural choices would you make to balance quality of semantic chunks with throughput?

  2. 2

    How would you handle edge cases where a document contains very long tables or code snippets that exceed the model’s context window when using SemanticChunker?

  3. 3

    Compare the cost implications of using SemanticChunker versus character splitting when you bill per embedding request. How would you estimate and optimize costs?

8+ years experience
  1. 1

    Your organization wants to replace all existing character‑based chunking across multiple services with a unified SemanticChunker approach. What migration strategy would you propose to minimize disruption and ensure backward compatibility?

  2. 2

    At a cross‑team level, how would you standardize chunking policies (size, overlap, language support) while allowing teams to plug in different embedding models? Discuss governance and observability.

  3. 3

    Looking ahead five years, what risks do you see in relying heavily on semantic chunking for LLM pipelines, and how would you future‑proof the architecture against model or token‑limit changes?

Follow-up Questions

  • ❓How would you measure whether the semantic chunks are improving retrieval quality?
  • ❓What metrics would you track to detect a regression after switching chunkers?
  • ❓Can you describe a fallback strategy if the embedding service becomes unavailable?