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 order to get to Retrieval we need to store and query text. Think of web search. You have to query the entire internet for ranked results.

For our course, we will use embeddings to store documents. Embeddings are useful for the retrieval process.

An embedding model takes in text and returns a vector of a fixed length. It typically originates as part of a language model and is learned through training. The output is a semantic representation of the text.

If you are not familiar, a vector is like an array of numbers. A vectorstore is like an array of vectors.

cosine

In this graph, we're plotting ants against a set of other animals. The scale is size and legs - Ants have small size, medium legs. Let's call the difference between ants and other animals "ant scale". Imagine a robot ant that doesn't trust animals that deviate too much on ant scale.

One method to get the similarity between animals is cosine similarity. Which calculates the difference in angles between vectors (represented by theta). If you take the cos(theta), you will get a float which is easier to work with.

# Vectorstores

In order to get to Retrieval we need to store and query text. Think of web search. You have to query the entire internet for ranked results.

For our course, we will use embeddings to store documents. Embeddings are useful for the retrieval process.

## What are embeddings?

An embedding model takes in text and returns a vector of a fixed length. It typically originates as part of a language model and is learned through training. The output is a semantic representation of the text.

If you are not familiar, a vector is like an array of numbers. A vectorstore is like an array of vectors.

![embeddings](https://d2uusema5elisf.cloudfront.net/courses/langchainjs-bootcamp/module_04/lesson_04.02/public/assets/cosine.png "cosine")

In this graph, we're plotting ants against a set of other animals. The scale is size and legs - Ants have small size, medium legs. Let's call the difference between ants and other animals "ant scale". Imagine a robot ant that doesn't trust animals that deviate too much on ant scale.

### Similarity

One method to get the similarity between animals is cosine similarity. Which calculates the difference in angles between vectors (represented by theta). If you take the cos(theta), you will get a float which is easier to work with.