19 Generative AI Real Time Projects End to End

Name: 19 Generative AI Real Time Projects End to End
Rating: 4.1 (33 reviews)

Master Generative AI with 20+ Real-World Projects: Build, Deploy & Scale End-to-End Solutions

Created byBoktiar Ahmed Bappy

Last updated 10/2024

English

English [Auto],

What you'll learn

Develop practical skills in building and deploying generative AI applications using LLM models.
Gain hands-on experience in training and fine-tuning LLM models using various datasets.
Create diverse applications leveraging the power of these LLM models.
End-to-end Projects Using LLM, VectorDB, Langchain, LlamaIndex, Flask, Streamlit, Chainlit and so on.
Gain hands-on experience in LLMOps
Master Google Vertex AI & AWS Bedrock for Generative AI Project Implementation

Course content

1 section • 19 lectures • 7h 20m total length

Text summarization with hugging face23:28
Explore text summarization with Hugging Face by fine-tuning Pegasus CNN Daily Mail on the Samsung dataset in Colab, using GPU, tokenizer, data collator, and rouge scores.
Text to Image generation with LLM with hugging face15:07
Learn text to image generation with diffusion models on Hugging Face, using the diffusion pipeline to turn prompts into images and compare pre-trained versus fine-tuned multimodal models.
Text to speech generation with LLM with hugging face2:39
Demonstrate text to speech generation with the Hugging Face transformer pipeline using the pseudo bark small model, loaded on Cuda, to convert text to audio.
Telegram bot using OpenAI35:24
Build a Telegram chatbot using OpenAI's GPT-3.5 chat completion model, linking the Telegram front end to the OpenAI back end for real-time responses.
Finetuning of GPT-3 model for text classification10:39
Fine-tune a GPT-3 Ada classifier on custom data to distinguish baseball from hockey. Prepare data as prompt and completion in JSONL, then train and evaluate via OpenAI API.
Audio Transcript Translation with Whishper18:18
Translate audio transcripts in real time by using whisper for transcription and GPT-3 or GPT-4 for translation, integrated into a Flask web app that uploads audio and outputs translated text.
Image generation with DALL-E5:40
Build an image generator using the OpenAI DALL-E model via API, creating a Flask app with HTML templates to render generated images from text prompts.
Interview Questions Creator Application57:47
Create an end-to-end interview question creator with generative AI, using Lang Chain, a vector database, and a front-end UI to upload documents and generate questions and answers.
Custom Website Chatbot17:15
Build a rag-based custom website chatbot with LangChain and a vector database. Load website data via sitemap, embed documents, build a semantic index, and answer site-specific questions using an LLM.
Custom Website Chatbot using Open source LLMs30:48
Build a custom website bot using llama two, vector database and Lang Chain framework to answer questions from site content via sitemap.xml, embeddings, and semantic search.
Build a Q&A App with RAG using Gemini Pro and Langchain9:10
Build a retrieval augmented generation q&a app using Gemini Pro and LangChain, extracting PDFs, chunking data, and indexing semantically with embeddings and a vector store for accurate answers.
Financial Stock Analysis using LlamaIndex14:47
Build end-to-end generative ai stock analysis apps using llama index and Streamlit, performing single stock and competitive analyses with vector stores, embeddings, and data handling.
End to End Medical Chatbot Project with LLM, Pinecone, LangChain1:11:00
Build an end-to-end medical chatbot using a custom knowledge base, embeddings, Pinecone vector store, and LangChain with an OpenAI LLM, plus a Flask front end and cloud deployment.
End to End Source Code Analysis with LangChain, OpenAI and ChromaDB32:05
Learn to build an end-to-end source code analysis system with LangChain, OpenAI and ChromaDB that ingests a GitHub repo and enables QA via a Flask front end.
Implementing Zomato chatbot with Chainlit33:56
Implement a Zomato chatbot with Chainlit, building an end-to-end app using the OpenAI GPT 3.5 turbo, crafting system prompts and a user-friendly UI.
How to Deploy Generative AI Application as CICD on AWS30:39
Learn to deploy generative ai projects on aws with ci/cd by dockerizing the app, pushing to ecr, deploying on ec2 via GitHub actions, and securing keys and secrets.
RAG on Vertex AI with Vector Search and Gemini Pro16:21
Explore rag-based applications on Vertex AI by building a knowledge base from data and PDFs, generating embeddings, storing them in a vector store, and performing vector search to answer queries.
LLM powered application on Vertex AI4:04
Configure an llm powered chatbot on Vertex AI by setting up the environment, installing Flask, and deploying a Flask app with a prediction endpoint and a bootstrap front end.
Hands-on AWS Bedrock11:35
Learn to access and deploy AWS Bedrock foundation models from a local Python environment using boto3, Streamlit, and a language-model chain with the Mistral model.

Requirements

Proficiency in Python Programming: Strong understanding of Python syntax and experience with data manipulation libraries (NumPy, Pandas).
Basic Deep Learning Knowledge: Familiarity with neural networks, backpropagation, and concepts like CNNs and RNNs.
Experience with ML Frameworks: Hands-on experience using TensorFlow, PyTorch, or Keras for model development and training.
Mathematics Foundation: Knowledge of linear algebra, calculus, and probability for comprehending model architecture.

Description

Welcome to the ultimate hands-on course on Generative AI, where theory meets practice through a series of 20+ real-world projects! This course is meticulously crafted to help you master cutting-edge Generative AI models like GPT, GANs, Transformers, Variational Autoencoders, and more by building complete, end-to-end solutions from scratch.

This comprehensive course is designed to accommodate learners at different levels, making it ideal for both beginners and experienced AI professionals. Whether you are new to the field or have some foundational knowledge, you’ll start with a solid introduction to the core concepts of Generative AI. From there, we’ll dive into advanced topics, ensuring that by the end, you’ll have a deep understanding of the intricacies of various models, their applications, and implementation techniques.

Throughout the course, you’ll work on projects spanning a wide range of domains, including natural language processing, image synthesis, video generation, code completion, music composition, and creative design. Each project is carefully structured to take you through every stage of the development process—from data collection and preprocessing to model building, optimization, and deployment strategies.

By following our step-by-step tutorials, you will gain hands-on experience in building real-world AI applications, creating a rich portfolio of projects that showcase your skills. You’ll also learn about best practices for model performance optimization, cloud deployment, and scaling solutions for various business needs. This course includes source codes, project files, quizzes, and interactive exercises to help reinforce your learning.

By the end, you’ll have the confidence and expertise to build, deploy, and scale state-of-the-art Generative AI solutions in diverse industries.

Who this course is for:

AI Enthusiasts & Beginners: Individuals looking to explore and build a solid foundation in Generative AI through practical projects.
Data Scientists & Machine Learning Engineers: Professionals wanting to expand their skillset by implementing advanced AI models.
Software Developers: Developers interested in transitioning to AI roles and building real-world AI applications.
Researchers & Academics: Those looking to apply Generative AI techniques in research or academic projects.