AI 4 Everyone: Build Generative AI & Computer Vision Apps

In this tutorial, you will learn how to obtain the Groq API key to access the Llama 3.1 model via API.

In this tutorial, you will learn how to obtain your Google Gemini API key.

This lecture will cover key terms used throughout the course, such as training data, tokens, temperature, guidance scale, embeddings, and memory.

In this lecture, we will learn how to write prompts to communicate effectively with an AI model. We will cover six key topics: Persona, Details, Steps, Reference, Delimiters, and Output Formats. These elements will help us craft effective prompts to achieve the desired responses from the AI model.

If you don't know how to code, you can still seek assistance, get guidance, and automate your tasks with the help of AI. In this lecture, we'll explore some online AI tools that we'll use in the upcoming lectures of this section. We'll also review the various tasks we'll accomplish using these tools in the following lessons.

In this lecture, we'll learn how to use AI to write a sick leave. We'll also explore various prompt engineering techniques to craft effective prompts and achieve the desired response.

In this lecture, we'll learn how to use AI to summarize a YouTube video. We'll also apply various prompt engineering techniques to structure the response in the desired format, including a table of contents, section titles, and a detailed description.

In this lecture, we'll learn how to use various AI tools to generate images instantly, without writing a single line of code—simply by providing an input prompt.

In this lecture, we'll learn how to use AI tools to get explanations for graphs.

In this section, we will explore the various components involved in creating an application and learn how to develop the frontend of our application using Streamlit.

In this video, we cover how to use basic Streamlit web elements to quickly display text, data, images, videos, dates, and other visuals in your apps.

In this tutorial, you will learn how to build a simple LLM application with LangChain. This application will translate text from English into another language.

At the end of this section, you will have a high level overview of:

1. Using language models.

2. Using PromptTemplates and OutputParsers.

3. Using LangChain Expression Language (LCEL) to chain components together.

4. Deploy your LLM Application with LangServe as a REST API.

In this tutorial, you will learn how to deploy LLM Application with LangServe as a REST API.

At the end of this section, you will have a high level overview of:

1. Using language models.

2. Using PromptTemplates and OutputParsers.

3. Using LangChain Expression Language (LCEL) to chain components together.

4. Deploy your LLM Application with LangServe as a REST API.

In this tutorial, you'll learn how to build a simple Q&A application over a text data source using Retrieval Augmented Generation (RAG). RAG allows us to ask questions about our documents that were not included in the training data without fine-tuning the Large Language Models (LLMs).

In RAG, if you are given a Question, you first do a retrieval step to fetch any relevant documents from a special database, a vector database where these documents were indexed.

In many Q&A applications, we want to allow the user to have back and forth conversation like eg.

Question 01: Who won the cricket world cup 2019?

Question 02: Who was the captain of the team?

To answer the second question we need a memory element, we need memory of past Q&A and some logic of incorporating those into its current thinking.

In this tutorial we cover two approaches:

01. Chains, in which we always execute a retrieval step.

02. Agents, in which we give LLM the discretion over whether and how to execute a retrieval step (or multiple steps).