Key Concepts
| S.No | Topic | Sub-Topics |
|---|---|---|
| 1 | LlamaIndex | Architecture, Core Concepts, Components, Workflows, Data Flow, Installation, Project Structure |
| 2 | LlamaIndex Setup | Python Environment, Package Installation, Configuration, API Keys, Settings, Logging, Dependencies |
| 3 | Documents | Document Object, Metadata, IDs, Text Extraction, Transformation, Custom Metadata, Document Management |
| 4 | Readers | SimpleDirectoryReader, PDF Reader, CSV Reader, JSON Reader, HTML Reader, Database Reader, Custom Reader |
| 5 | Nodes | TextNode, Node IDs, Metadata, Relationships, Parent-Child Nodes, Custom Nodes, Node Parsing |
| 6 | Node Parsing | SentenceSplitter, TokenTextSplitter, Semantic Splitting, Hierarchical Parsing, Metadata Extraction, Chunk Overlap, Custom Parsers |
| 7 | Metadata | Document Metadata, Node Metadata, Metadata Extraction, Metadata Filtering, Automatic Metadata, Metadata Templates, Metadata Propagation |
| 8 | Embeddings | Embedding Models, OpenAI Embeddings, Hugging Face Embeddings, Local Embeddings, Batch Embeddings, Similarity, Configuration |
| 9 | Vector Stores | VectorStore, Chroma, Pinecone, Qdrant, Milvus, FAISS, PGVector |
| 10 | Storage | StorageContext, Document Store, Index Store, Vector Store, Persistence, Loading Indexes, Remote Storage |
| 11 | Indexes | VectorStoreIndex, SummaryIndex, TreeIndex, KeywordTableIndex, KnowledgeGraphIndex, Property Indexes, Index Selection |
| 12 | VectorStoreIndex | Index Construction, Node Insertion, Embeddings, Persistence, Loading, Filtering, Retrieval Configuration |
| 13 | Retrievers | Vector Retriever, Keyword Retriever, BM25, Hybrid Retrieval, Metadata Filters, Similarity Top-K, Custom Retrievers |
| 14 | Query Engine | QueryEngine, Query Pipeline, Retrieval, Response Synthesis, Similarity Threshold, Streaming, Async Queries |
| 15 | Response Synthesis | Compact, Refine, Tree Summarize, Simple Summarize, Citation Responses, Structured Responses, Custom Synthesis |
| 16 | RAG Fundamentals | Ingestion, Chunking, Embedding, Indexing, Retrieval, Generation, End-to-End RAG |
| 17 | Advanced RAG | Hybrid Search, Query Rewriting, Reranking, Metadata Filtering, Contextual Retrieval, Recursive Retrieval, Fusion Retrieval |
| 18 | Reranking | Cross-Encoder, Cohere Reranker, Sentence Transformers, Top-K Retrieval, Score Thresholds, Reciprocal Rank Fusion, Custom Rerankers |
| 19 | Query Transformation | Query Expansion, Query Rewriting, Sub-Question Generation, HyDE, Multi-Query Retrieval, Routing, Query Decomposition |
| 20 | Chat Engines | Chat Engine, Conversational Context, Memory, Context Management, Streaming Chat, Async Chat, Custom Chat Behavior |
| 21 | Memory | Chat Memory, Short-Term Memory, Long-Term Memory, Token Limits, Memory Blocks, Retrieval-Based Memory, Persistent Memory |
| 22 | Agents | Agent Architecture, Tools, Tool Calling, ReAct Agents, Function Calling, Agent Memory, Multi-Step Reasoning |
| 23 | Workflows | Workflow Concepts, Events, Steps, State, Async Workflows, Branching, Parallel Execution, Error Handling |
| 24 | Tools | FunctionTool, QueryEngineTool, Custom Tools, API Tools, Database Tools, Tool Metadata, Tool Selection |
| 25 | LLM Integration | OpenAI, Anthropic, Gemini, Ollama, Hugging Face, Local LLMs, Custom LLM Integration |
| 26 | Structured Outputs | Pydantic Models, Structured Prediction, JSON Output, Schema Validation, Extraction, Response Parsing, Typed Outputs |
| 27 | Data Extraction | LLM Extraction, Structured Extraction, Metadata Extraction, Table Extraction, Entity Extraction, Relation Extraction, Validation |
| 28 | Evaluation | Retrieval Evaluation, Response Evaluation, Faithfulness, Relevance, Correctness, Context Evaluation, RAG Benchmarking |
| 29 | Production RAG | Caching, Observability, Tracing, Logging, Security, Latency Optimization, Cost Optimization |
| 30 | Production Deployment | FastAPI, Docker, Kubernetes, Vector DB Deployment, Scaling, Monitoring, CI/CD |
| 31 | Advanced Architecture | Multi-Index RAG, Agentic RAG, Multimodal RAG, Knowledge Graphs, Hybrid Architecture, Distributed Ingestion, Enterprise Architecture |
| 32 | Capstone Project | Enterprise RAG, PDF Ingestion, Intelligent Chunking, Vector Database, Hybrid Retrieval, Reranking, Conversational Memory |
Interview question
| What is LlamaIndex and what problem does it solve? |
| Why is LlamaIndex commonly used for RAG applications? |
| What are the core components of LlamaIndex? |
| What is the architecture of LlamaIndex? |
| How does LlamaIndex differ from LangChain? |
| What are Documents in LlamaIndex? |
| What are Nodes in LlamaIndex? |
| What is the difference between a Document and a Node? |
| What is SimpleDirectoryReader? |
| How do you load PDF files using LlamaIndex? |
| How do you load CSV files using LlamaIndex? |
| How do you load JSON files using LlamaIndex? |
| How do you load HTML documents using LlamaIndex? |
| How can you create a custom data reader in LlamaIndex? |
| What is NodeParser in LlamaIndex? |
| What is SentenceSplitter? |
| How does SentenceSplitter split documents? |
| What is chunk size in LlamaIndex? |
| What is chunk overlap? |
| How do you choose an appropriate chunk size? |
| What is a TextNode? |
| How does metadata work with Nodes? |
| What are node relationships? |
| What is parent-child node relationship? |
| Why is metadata important in RAG applications? |
| How do you add custom metadata to documents? |
| What are embeddings in LlamaIndex? |
| Why are embeddings required for semantic search? |
| How do you configure an embedding model in LlamaIndex? |
| How do you use OpenAI embeddings with LlamaIndex? |
| How can you use Hugging Face embeddings with LlamaIndex? |
| How can you use local embedding models with LlamaIndex? |
| What is VectorStoreIndex? |
| How do you create a VectorStoreIndex? |
| What happens internally when a VectorStoreIndex is created? |
| What is StorageContext? |
| What is the purpose of a document store? |
| What is the purpose of an index store? |
| What is a vector store? |
| Which vector databases can be integrated with LlamaIndex? |
| How do you integrate Chroma with LlamaIndex? |
| How do you integrate Pinecone with LlamaIndex? |
| How do you integrate Qdrant with LlamaIndex? |
| How do you integrate Milvus with LlamaIndex? |
| How do you integrate PostgreSQL/PGVector with LlamaIndex? |
| What is FAISS and how can it be used with LlamaIndex? |
| What is persistence in LlamaIndex? |
| How do you persist an index to disk? |
| How do you load a persisted index? |
| What is a Retriever in LlamaIndex? |
| What is VectorIndexRetriever? |
| How does similarity search work in LlamaIndex? |
| What is top-k retrieval? |
| How do you configure similarity_top_k? |
| What is metadata filtering? |
| How do metadata filters improve retrieval? |
| What is hybrid search? |
| How do you implement hybrid retrieval in LlamaIndex? |
| What is BM25 retrieval? |
| What is a QueryEngine? |
| How do you create a QueryEngine? |
| What happens internally when a query is sent to a QueryEngine? |
| What is ResponseSynthesizer? |
| What are the different response synthesis strategies? |
| What is the Compact response synthesis mode? |
| What is the Refine response synthesis mode? |
| What is Tree Summarize response synthesis? |
| How do you generate citation-based responses? |
| What is RAG in LlamaIndex? |
| How do you build a basic RAG pipeline using LlamaIndex? |
| What are the major stages of a LlamaIndex RAG pipeline? |
| How does LlamaIndex handle document ingestion? |
| How does LlamaIndex perform retrieval? |
| How does LlamaIndex use an LLM after retrieval? |
| What are common RAG failure modes in LlamaIndex? |
| How do you improve retrieval accuracy in LlamaIndex? |
| What is reranking in LlamaIndex? |
| Why is reranking useful in RAG? |
| How do you integrate a reranker with LlamaIndex? |
| What is Reciprocal Rank Fusion? |
| What is query transformation? |
| What is query rewriting? |
| What is query expansion? |
| What is HyDE in LlamaIndex? |
| What is sub-question query decomposition? |
| What is SubQuestionQueryEngine? |
| What is RouterQueryEngine? |
| How does query routing work in LlamaIndex? |
| What is RecursiveRetriever? |
| What is AutoMergingRetriever? |
| What is a ChatEngine? |
| What is the difference between QueryEngine and ChatEngine? |
| How does conversational memory work in LlamaIndex? |
| What is ChatMemory? |
| How do you maintain conversation history in LlamaIndex? |
| What are Agents in LlamaIndex? |
| What is a ReAct agent? |
| How does tool calling work in LlamaIndex agents? |
| What is FunctionTool? |
| What is QueryEngineTool? |
| How can an agent use a RAG query engine as a tool? |
| What are Workflows in LlamaIndex? |
| How are events and steps used in Workflows? |
| How do you build an asynchronous workflow? |
| How do you handle errors in LlamaIndex workflows? |
| How do you evaluate a LlamaIndex RAG application? |
| What is faithfulness evaluation? |
| What is retrieval relevance evaluation? |
| How do you optimize LlamaIndex applications for latency and cost? |
| How do you deploy a LlamaIndex RAG application in production? |
