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

Now we have a way for users to ingest documents and for our application to retrieve relevant documents. Our last step is to define how the documents interact with the prompt. We also want to keep conversational memory.

By the end of this lesson, you will have a fully functional Retrieval Augmented Generation (RAG) Chain.

document chat

To create our Chain, we need to use everything we've learned so far. We need 

We have to initialize our vectorstore, supabase client, and 

. Then we can create a retriever from our vectorstore.

 and converting Documents into strings with 

. You also need to import everything to create a chat model with memory, vectorstore, and retriever.

import { RunnableSequence } from "langchain/schema/runnable";
import { formatDocumentsAsString } from "langchain/util/document";

We should change the retriever to have a constant 

    const retriever = new HydeRetriever({
      vectorStore,
      llm: model,
      k: 4,
      verbose: true,
    });

Edit your system prompt to make sense for the task.

  const systemTemplate = `You are a helpful friend and medical professional.`

---
code: https://gitlab.com/fullstackio/books/newline-course-apps/jeffery-wang-langchain.js-bootcamp-app/-/tree/main/Code/module_04/lesson_04.06/protected/src?ref_type=heads
---

# Generation

Now we have a way for users to ingest documents and for our application to retrieve relevant documents. Our last step is to define how the documents interact with the prompt. We also want to keep conversational memory.

By the end of this lesson, you will have a fully functional Retrieval Augmented Generation (RAG) Chain.

![document chat](https://d2uusema5elisf.cloudfront.net/courses/langchainjs-bootcamp/module_04/lesson_04.06/public/assets/documentchat.png "document chat")

To get started, we can create a new `POST` route at `/api/retrieval/chat`.

## Chain

To create our Chain, we need to use everything we've learned so far. We need `prompt` and `memory` from previous modules. And `vectorstore` and `retriever` from this earlier.

We have to initialize our vectorstore, supabase client, and `StreamingTextResponse`. Then we can create a retriever from our vectorstore.

We're creating a Chain with `RunnableSequence` and converting Documents into strings with `formatDocumentsAsString`. You also need to import everything to create a chat model with memory, vectorstore, and retriever.

```ts { actualFilename=./protected/src/qachat.ts endLine=15 startLine=14 statedFilename=import url=https&#x3A;//gitlab.com/fullstackio/books/langchainjs-bootcamp/module_04/lesson_04.06/protected/src/qachat.ts#L14 }
import { RunnableSequence } from "langchain/schema/runnable";
import { formatDocumentsAsString } from "langchain/util/document";
```

We should change the retriever to have a constant `k` from previous sections.

```ts { actualFilename=./protected/src/qachat.ts endLine=62 startLine=57 statedFilename=hyde url=https&#x3A;//gitlab.com/fullstackio/books/langchainjs-bootcamp/module_04/lesson_04.06/protected/src/qachat.ts#L57 }
    const retriever = new HydeRetriever({
      vectorStore,
      llm: model,
      k: 4,
      verbose: true,
    });
```

Edit your system prompt to make sense for the task.

```ts { actualFilename=./protected/src/qachat.ts endLine=76 startLine=76 statedFilename=system url=https&#x3A;//gitlab.com/fullstackio/books/langchainjs-bootcamp/module_04/lesson_04.06/protected/src/qachat.ts#L76 }
  const systemTemplate = `You are a helpful friend and medical professional.`
```

Do the same for the human template.

```ts { actualFilename=./protected/src/qachat.ts endLine=74 startLine=70 statedFilename=human url=https&#x3A;//gitlab.com/fullstackio/books/langchainjs-bootcamp/module_04/lesson_04.06/protected/src/qachat.ts#L70 }
  const humanTemplate = `Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. 
  Context:
  {context}
  Question:
  {question}`
```