LangChain Crash Course: Build AI Apps Fast with Python & LLM

Create a Python virtual environment to provide isolated workspace for projects, manage library versions without global installs, and activate it to keep Python and pip aligned with its site packages.

Create an isolated Python environment for this course by setting up a virtual environment with venv, navigating to a project folder, and activating it to confirm readiness.

Generate your Deep Seek API key, sign up on platform.com, and save the key securely. Use the free credits and monitor usage as you prepare LangChain AI apps.

Activate the virtual environment, install LangChain libraries, and build your first LangChain app. Create a capital querying flow using a country input and a .env API key.

Preview the upcoming LangChain crash course project: a chatbot that writes poems from any word users type, showcasing interactive word-to-poem capabilities and creative AI responses.

Master prompt templates in LangChain by running a lab that generates a short funny poem from a topic and sets up a Python virtual environment and project files.

Learn to build and test prompts with PromptTemplate in LangChain, using a deepsea LLM and environment variables to generate topic-based poems, with a guardio web chat interface that preserves history.

Chain together prompts, databases, APIs, and documents with logic to transform an LLM into a full stack app, maintaining state and orchestrating multi-step workflows for reliable, data-driven tasks.

Learn how generic chains combine a prompt template with a large language model to convert user input into prompts and return the model output.

Walks through building a LangChain lab app, loading api keys from a dot env file, and launching a Guardio web interface to generate company names with a dipstick model.

Discover how LangChain's simple sequential chain connects multiple llm powered chains in a strict sequence, where each output feeds the next, illustrated by a grocery shopping workflow.

Set up a Python virtual environment, install dependencies from requirements.txt, and run a sequential chain in LangChain to generate a genre-based title and its short story via a Gradio app.

Walk through LangChain's simple sequential chain lab, building a title-generation chain feeding into a story-summary chain, with prompts, a chat model, and verbose debugging for clear output.

Explore sequential chain, a multi-input, multi-output workflow that tracks intermediate results. See how title, summary, and image are generated in a three-step process from a genre.

Explore how tools empower language models to act, calling Python functions, API calls, or tools like Google search, database queries, or calculators, as part of an agent.

Build an AI powered restaurant menu creator with LangChain and Streamlit, using a two-step chain to name a dish from a category and craft its description.

Demonstrates building an AI app demo with Streamlit to generate dish names and descriptions, manage menus with drop-downs, and navigate a concise crash course on rapid prototyping.

Build an AI-powered restaurant menu creator with LangChain's sequential chain, set up the environment, install dependencies, run a local app, and generate menu items.

Walks through building an AI-powered restaurant menu creator using Streamlit UI and LangChain prompts; demonstrates two chained prompts producing a dish name from a category and a corresponding description.