Develop a practical understanding of Retrieval-Augmented Generation (RAG)

Design user-friendly, interactive interfaces for RAG applications using Gradio

Learn about LlamaIndex, its uses in building RAG applications, and how it contrasts with LangChain

Build RAG applications using LangChain and LlamaIndex in Python

Differentiate between vector databases and traditional databases based on their functionality and use cases

Execute fundamental database operations in ChromaDB, including updating, deleting, and managing collections

Understand and apply similarity search techniques, both manually and with ChromaDB, and develop recommendation systems using these techniques

Develop a thorough and comprehensive understanding of key internal mechanisms within RAG

Build RAG applications using vector databases and advanced retrieval patterns

Employ the core mechanics of Vector Databases such as FAISS and Chroma DB and implement indexing algorithms like HNSW

Implement advanced retrievers using LlamaIndex and LangChain to improve the quality of LLM responses

Develop comprehensive RAG applications by integrating LangChain, FAISS, and front-end user interfaces built using Gradio

Build the job-ready skills you need to build multimodal generative AI applications in just 3 weeks

Understand the fundamental concepts and challenges in multimodal AI, including the integration of text, speech, images, and video

Build multimodal AI applications using state-of-the-art models and frameworks such as IBM’s Granite, Meta’s Llama, OpenAI’s Whisper, DALL·E and Sora

Develop multimodal AI solutions, including chatbots and image/video generation models, using IBM watsonx.ai, Hugging Face, Flask and Gradio

Develop AI agents that can reason and perform tasks independently

Implement tool calling and chaining to create structured AI workflows

Utilize built-in LangChain agents to analyze data, generate visualizations, and execute database queries

Apply best practices in prompt engineering and tool calling to enhance AI agent performance

Build agentic AI systems using LangChain and LangGraph to support memory, iteration, and conditional logic

Design and implement self-improving agents using Reflection, Reflexion, and ReAct architectures

Apply agent orchestration techniques to build collaborative multi-agent systems

Implement agentic RAG systems that route queries and support retrieval-enhanced reasoning

Design optimized AI systems by selecting and combining appropriate agentic frameworks and architectural patterns

Implement AI workflow patterns using agentic design principles and LangGraph

Build structured multi-agent workflows using CrewAI, including agents, tasks, and custom tools

Develop AI applications with BeeAI and design conversation-driven interactions using AG2 (AutoGen)

Explain the architecture, components, and use cases of the Model Context Protocol (MCP), and how it differs from traditional APIs and tool calling

Build and run MCP servers using FastMCP, configuring tools, resources, and prompts to support AI applications such as retrieval-augmented generation

Develop MCP clients that connect to single and multiple servers using STDIO and Streamable HTTP for structured, context-aware LLM interactions

Implement secure, interactive MCP workflows by applying sampling, roots, and permission-based user-approval mechanisms for multi-agent applications

Demonstrate you have the job-ready skills to design and implement a complete AI system from data to deployment.

Transform unstructured text and multimodal data into structured JSON formats using LLMs to drive data-driven decision-making.

Architect multimodal vector databases and multi-agent systems to coordinate specialized agents for high-accuracy recommendations.

Integrate complex AI ecosystems using MCP, configuring servers and clients to build, validate, and scale tool-augmented agents.