Orchestration Frameworks (LangChain, LlamaIndex)

94 lessons in AI Engineering / Working with LLMs

• Output Parsers and Structured OutputSlides / Video
• LangChain vs LlamaIndex: PurposeSlides / Video
• What Orchestration Frameworks AreSlides / Video
• Abstraction Leakage and Debugging PainSlides / Video
• Framework vs Direct API CallsSlides / Video
• Provider and Model Swapping via AbstractionsSlides / Video
• Streaming Responses in LLM FrameworksSlides / Video
• Callbacks, Tracing, and LangSmithSlides / Video
• LangGraph and Stateful Agent OrchestrationSlides / Video
• Agents and Tool IntegrationSlides / Video
• Building a RAG App with LlamaIndexSlides / Video
• LlamaIndex Core: Nodes, Indexes, Query EnginesSlides / Video
• Retriever Abstraction and RAG PipelinesSlides / Video
• Wiring conversation memoryCode Quiz
• Invoke vs batch on a runnableCode Quiz
• Applying an output parserCode Quiz
• Composing chains with LCELCode Quiz
• PromptTemplate input variablesCode Quiz
• Constructing a ChatModel wrapperCode Quiz
• Initializing an agent executorCode Quiz
• Attaching callbacks to a chainCode Quiz
• Passing values with RunnablePassthroughCode Quiz
• Persisting and reloading an indexCode Quiz
• Using a node parserCode Quiz
• Configuring LlamaIndex SettingsCode Quiz
• Querying a query engineCode Quiz
• Building a VectorStoreIndexCode Quiz
• Assembling a RetrievalQA chainCode Quiz
• Configuring a retrieverCode Quiz
• Populating a vector storeCode Quiz
• Splitting documents with a splitterCode Quiz
• Loading documents with a loaderCode Quiz
• Defining a LangChain ToolCode Quiz
• Selecting similarity_top_kCode Quiz
• Injecting context into a promptCode Quiz
• Embeddings and Vector Store IntegrationsSlides / Video
• Text Splitters and Chunking StrategiesSlides / Video
• Document Loaders and Data IngestionSlides / Video
• Memory Modules for Conversational StateSlides / Video
• Prompt Templates and Variable InjectionSlides / Video
• LCEL and the Runnable InterfaceSlides / Video
• Chains: Composing Multi-Step LLM WorkflowsSlides / Video
• LangChain Core: Models, Prompts, ParsersSlides / Video
• LangChain Expression Language (LCEL)Quiz
• LLM and ChatModel WrappersQuiz
• Chains and Chaining ComponentsQuiz
• Streaming SupportQuiz
• Document LoadersQuiz
• Retrievers AbstractionQuiz
• Vector Store IntegrationsQuiz
• Combining LangChain and LlamaIndexQuiz
• Memory Modules for ConversationQuiz
• Output ParsersQuiz
• Structured Output via FrameworksQuiz
• Framework Overhead TradeoffsQuiz
• Embeddings AbstractionQuiz
• Text Splitters and ChunkingQuiz
• Provider and Model SwappingQuiz
• Prompt Templates in LangChainQuiz
• LangSmith Tracing and DebuggingQuiz
• LangChain Core ComponentsQuiz
• LangChain vs LlamaIndex FocusQuiz
• Framework vs Raw API CallsQuiz
• What an Orchestration Framework IsQuiz
• Callbacks and Observability HooksQuiz
• Data Ingestion PipelineQuiz
• Nodes and Documents in LlamaIndexQuiz
• LlamaIndex Query EnginesQuiz
• LlamaIndex Index TypesQuiz
• Building a RAG PipelineQuiz
• Retriever AbstractionFlashcard
• Streaming SupportFlashcard
• Ingestion Pipelines and PostprocessorsFlashcard
• Overhead and Leaky AbstractionsFlashcard
• Async and Batch ExecutionFlashcard
• Callbacks and ObservabilityFlashcard
• LlamaIndex Index TypesFlashcard
• Output ParsersFlashcard
• LangChain vs LlamaIndexFlashcard
• Combining LangChain and LlamaIndexFlashcard
• Embeddings AbstractionFlashcard
• Agents and ToolsFlashcard
• Memory AbstractionsFlashcard
• Nodes and DocumentsFlashcard
• Building a RAG PipelineFlashcard
• Text SplittersFlashcard
• Prompt TemplatesFlashcard
• LCEL and RunnablesFlashcard
• Chains for Multi-Step WorkflowsFlashcard
• What Orchestration Frameworks AreFlashcard
• LlamaIndex Query EnginesFlashcard
• Document LoadersFlashcard
• Framework vs Raw SDKFlashcard
• Model Abstraction and SwappingFlashcard