Background Information

Project overview

Setup

Introduction

Prompt template

LCEL

Introduction to prompt engineering

Prompts

Memory

Conversation memory

Supabase

Restoring memory

Vectorstores

Supabase vector

Ingest

Retrieval

Generation

Retrieval Augmented Generation

Output Parsing

Tools

Agents

Langsmith

Farewell

( the primaryDescriptionMarkdown is long - several lines, include images, as long as you want )

In this course we <headline of what we do>. <why this technology is good> but <here's how learning it is problem>. 

In <the length of these lessons> we cover <three salient points about what we cover. Your BEST points>. Its <however long it is> and comes with <these bonus features, and reasons to buy. code, etc.>

It's taught by <author name> who <credibility, reason you should listen to them>. <social proof, if you have it yet>

<then you can list other supporting stuff you want to add, anything you want here>

-------
Example:
-------

We created a free course to create your first GraphQL server (from scratch) using Node and TypeScript. TypeScript and GraphQL are a powerful combo, but there's a lot of confusing edges if you're getting it setup the first time.

In this course we cover the basics of getting TypeScript setup with Node, how GraphQL works, and how to set up a GraphQL server using Apollo server. It's two hours long, it comes with complete code examples, and we walk through the code step-by-step.

It's taught by my friend, Shopify-engineer Hassan Djirdeh and he's integrated what he's learned using GraphQL in production as an engineer at Shopify. We've already had over 1,300 students enroll and it's been getting great reviews so far.

// ... and so on

In this course we <headline of what we do>. <why this technology is good> but <here's how learning it is problem>. 

( the summary is short - one or two lines )

Langchain.js Bootcamp

In this module we are going to talk about Retrieval Augmented Generation (RAG). As an introduction, let's discuss what consider a story. Then, we'll define the term and get an overview. We'll implement the parts in later lessons.

It is 5:40 PM on a Friday and you've spent the last 2 hours picking through Jeff's spaghetti code. All you've had for food was a slice of pizza on the go. You have no idea what is going on. The console errors are not helping. Your coworker Kerry is not answering her DM's because she peaced out early today. You feel desperate.

context1

Hey! Have you ever found yourself copy and pasting code from a file into a chat service?

Copy and pasting code is actually more complex than you think! There's several things you have to take into consideration. You have to decide which lines you want to give the model. For example, you may want to include helper functions or choose to describe a different part of the codebase. You also need to think about how you frame the text and how you pose your question. Like, 

You are giving the model "Context" by providing extra information.

Copy and pasting code is similar to what we'll implement in the module. But, of course, we'll do it programmatically.

Going forward, we can split the steps into 3 to help us reason about the process better.

Now let's relabel the previous diagram with some key terms. This is a list of what we've done:

# Introduction

## Forward

In this module we are going to talk about Retrieval Augmented Generation (RAG). As an introduction, let's discuss what consider a story. Then, we'll define the term and get an overview. We'll implement the parts in later lessons.

## Story: A day of software development

It is 5:40 PM on a Friday and you've spent the last 2 hours picking through Jeff's spaghetti code. All you've had for food was a slice of pizza on the go. You have no idea what is going on. The console errors are not helping. Your coworker Kerry is not answering her DM's because she peaced out early today. You feel desperate.

_I didn't want to._ You tell yourself.

_It feels like cheating..._

But you decide to use an AI chatbot.

### Interlude - copy pasta

![context1](https://d2uusema5elisf.cloudfront.net/courses/langchainjs-bootcamp/module_04/lesson_04.01/public/assets/context.png "context1")

**Hey! Have you ever found yourself copy and pasting code from a file into a chat service?**

Copy and pasting code is actually more complex than you think! There's several things you have to take into consideration. You have to decide which lines you want to give the model. For example, you may want to include helper functions or choose to describe a different part of the codebase. You also need to think about how you frame the text and how you pose your question. Like, ["let's think step by step"](https://arxiv.org/pdf/2205.11916.pdf).

:::note
You are giving the model "Context" by providing extra information.
:::

### Copy pasta II

Copy and pasting code is similar to what we'll implement in the module. But, of course, we'll do it programmatically.

Going forward, we can split the steps into 3 to help us reason about the process better.