Scribd
Upload
74 views3 pages

Bootcamp GenAI AgenticAI Backend Engineers MacBook

The document outlines a three-day bootcamp for backend engineers focusing on Generative AI and Agentic AI using Python and Java. It covers core concepts, practical applications, and project development involving tools like LangChain and FastAPI, along with system setup instructions for macOS. Participants will learn to build AI agents and integrate them with various data sources and APIs.

Uploaded by

rohit01ggn
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
74 views3 pages

Bootcamp GenAI AgenticAI Backend Engineers MacBook

The document outlines a three-day bootcamp for backend engineers focusing on Generative AI and Agentic AI using Python and Java. It covers core concepts, practical applications, and project development involving tools like LangChain and FastAPI, along with system setup instructions for macOS. Participants will learn to build AI agents and integrate them with various data sources and APIs.

Uploaded by

rohit01ggn
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Generative AI & Agentic AI Bootcamp for Backend Engineers (Python + Java,

MacBook M3 Max)

Day 1: Core Concepts of Generative AI

Theory:

- What is Generative AI? How it's used in real systems (chatbots, copilots, RAG)

- Introduction to Transformers and Large Language Models (LLMs)

- Prompt Engineering (zero-shot, few-shot, temperature, top-k/top-p)

- Introduction to Embeddings and Vector Databases

Practice:

- Try prompts using ChatGPT or Ollama (locally)

- Load a small model via Ollama: `ollama run llama3`

- Use OpenAI or HuggingFace Transformers in Python (basic text generation)

Day 2: Agentic AI & Tool-Using Agents

Theory:

- What is an Agent? Differences from regular LLMs

- Agents as planners with tools, memory, and reasoning

- Agent Frameworks: LangChain, AutoGen, Haystack

Practice:

- Install LangChain: `pip install langchain langchain-community fastapi`

- Create a basic agent with tools (e.g., search, calculator)

- Deploy as a REST API using FastAPI


- Explore Flowise or Langflow for no-code chaining

Day 3: Project - Build Your First Gen AI Agent

Theory:

- Combine RAG (Retrieval-Augmented Generation) with agents

- How to integrate with PDFs, SQL databases, or external APIs

Project Ideas:

1. PDF Q&A Agent using LangChain + ChromaDB + Ollama

2. Task Planner: Multi-step planning using tools

3. SQL Generator: Ask natural language questions, return SQL queries

Practice:

- Use LangChain's document loaders and vector store wrappers

- Build an interactive API endpoint with FastAPI

- Optional: Call Python-based agents from Java using REST

System Setup for macOS Sequoia 15.4 (M3 Max):

1. Install Homebrew (if not already):

`/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"`

2. Install Python 3, Git, and Ollama:

`brew install python git`

`brew install --cask ollama`

`ollama run llama3`


3. Create a virtual environment for the project:

`python3 -m venv genai-env && source genai-env/bin/activate`

4. Install dependencies:

`pip install langchain langchain-community fastapi uvicorn chromadb`

5. Optional Tools:

- Flowise: `npm install -g flowise` then `flowise start`

- Ollama GUI for better model browsing (via website)

You might also like