LangChain

Pipelines for LLM applications: prompts, tools, memory.

LangChain is taught here in 13 lessons, running from Prompt templates and chains through to Deploying LangChain apps and moving to LangGraph. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. Prompt templates and chainsBuild prompts that stay clean at scale, then compose them into chains with the pipe operator instead of nested function calls.
2. Tools and agentsExpose Python functions to a model, let it choose between them, and keep the loop bounded and safe.
3. Retrieval-augmented generationChunk and index documents, retrieve the right passages, and answer with citations while allowing an honest not-found reply.
4. Models, messages and providersinit_chat_model, provider packages, message types, streaming, and swapping providers without rewriting the rest of the application.
5. Structured output and output parserswith_structured_output, Pydantic and JSON schemas, plain text parsers, and handling parse failures with retries instead of hope.
6. Runnables and LangChain Expression Language in depthRunnableLambda, RunnablePassthrough, parallel and branching runnables, fallbacks, retries, runtime configuration and streaming through a chain.
7. Document loaders and text splittersLoaders for PDF, HTML, CSV, Markdown and directories, keeping metadata intact, and choosing a chunk size and overlap you can defend.
8. Embeddings and vector storesEmbedding model choice, FAISS, Chroma and pgvector, indexing and updating, and filtering on metadata before similarity search.
9. Retrievers in depthSimilarity search, MMR, multi-query and contextual compression, hybrid search, reranking, and writing your own retriever.
10. Conversation memory and historyMessage history, trimming and summarising long threads, per-user retrieval, and deciding what belongs outside the model's context.
11. Observability with callbacks and LangSmithCallbacks, tracing every step, token and cost accounting, and reading a trace to find the step that actually failed.
12. Evaluating chains and RAGDatasets and evaluators, correctness and groundedness scoring, regression suites, and testing a prompt change before you release it.
13. Deploying LangChain apps and moving to LangGraphDependency pinning, streaming from an API, production error handling, and migrating a multi-step agent workflow to LangGraph state machines.

More in AI & Intelligent Development

AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow PyTorch Natural Language Processing Ollama OpenCV Codex Claude Code OpenCode Vibe Coding Selenium Playwright

FAQ