A lot has been going on with AI over the

past few years. Prompt engineering,

context windows tokens embeddings

rag, vector DB, MCPS, agents, lang

chain langraph claude Gemini and

more. If you felt left out, this is the

only video you'll need to watch to catch

up. In this video, we assume you know

absolutely nothing and try to explain

all of these concept through a single

project so that by the end of it, you go

from zero to gaining an overall

understanding of everything that's going

on with AI. We'll start with AI

fundamentals, then move on to rag,

vector DB, lang chain, langraph, MCP,

prompt engineering, and finally put it

all together with a complete system.

Let's start with the basics. When you

ask an AI model a question, it's

typically answered by a subset of AI

called large language models. Large

language models have gotten popular

right around when Chachib was released

in late 2022 when we started to see

language models get larger in size

because of their obvious benefits in

performance. So let's dig a bit deeper

to understand how large language models

are able to process requests that we

send. Popular LLMs like OpenASGPT,

Enthropics Claude, and Google's Gemini

are all transformer models that are

trained on large sets of data. The size

of training tokens can go up to tens of

trillions of tokens that are used to

train these models. And the training

data includes data from thousands of

different domains like healthcare, law,

coding, science, and more. But when we

work in TechCorb, the 500 GB of data

that we have aren't part of the training

data that was used to train the model,

which means that in order for us to use

the LLMs to ask questions about the

TechCorp's internal documents, we need

the ability to pass in data to the LLM.

One of the ways that we can pass the

data into the model is by adding them to

the conversation history functions like

a short-term memory where during the

duration of the conversation, all of

this context is kept in memory. And this

memory is called the context window.

Context windows are measured in tokens

which is roughly 3/4 of a word for

English text. The context window is

typically limited in size and the upper

limit varies depending on the model.

Some models like XAI GO 4 have 256,000

tokens whereas Enthropics Cloud Opus 4

has 200,000 tokens and Google's Gemini

2.5 Pro has 1 million tokens. So as you

can see the total upper bound for how

much context can be stored for each

model can vary. While the context window

plays an important role in storing them

in memory, there are practical

limitations in how LLM treats what's

inside the context window. For example,

if I asked you to memorize the pi digits

3.141592653589791

and asked you to recite it, some of you

might have a hard time committing that

many numbers all at once, which is

similar to how LLM's context window

works. So therein lies the current

limitations in LLM. How much context can

it hold in a given time? This can vary

depending on model to model. For

example, a lot of nano, mini, and flash

models can have very small context

windows in the size of 2,000 to 4,000

tokens, which amounts to about 1,500 to

3,000 words. Conversely, bigger models

like GPT4.1 and Gemini 2.5 Pro offer

context windows up to 1 million tokens,

which is equivalent to roughly 7,500

words or 50,000 lines of code. So, as

you can see, choosing the right model

for the task can be very important. For

example, if you downloaded a novel in a

txt format and you wanted to change the

script, choosing a model that offers a

large context window would be best.

Conversely, if you are working on a

small document and require very low

latency, meaning faster responses, using

flash and nano variants would be best.

Here's another angle to look at when it

comes to memory in LLMs. Let's say I ask

you this question. Sally and Bob own an

apple farm. Sally has 14 apples. Apples

are often red. 12 is a nice number. Bob

has no red apple, but he has two green

apples. Green apples often taste bad.

How many apples do they all have? This

might require you to think about the

problem a little bit to get to the final

answer, which is 16. That's because the

context here includes information that

is completely irrelevant to the

question, which is to count how many

apples they have in total. The fact that

apples are red or green or how it tastes

have nothing to do with the total number

of apples that they have because they

either have the apple or they don't. Now

that we have a grasp on what context

window provides, Techorp's 500 GB of

documents, this creates an immediate

problem. Even the largest context

window, like Gemini 2.5 Pro's 1 million

tokens, can hold only about 50 files of

typical business documents all at once.

We need our AI model to understand all

500 gigabytes, but it can only see a

tiny fraction at a given moment. This is

where embedding comes in, and they're

absolutely crucial to understand.

Embeddings transform the way we think

about information. Instead of storing

text as words, we convert meaning into

numbers. The sentence employee vacation

policy and staff time off guidelines use

completely different words, but they

mean essentially the same thing.

Embeddings capture that semantic

similarity. And here's how it works. An

embedding model takes a text and

converts it into a vector. Typically,

1536 numbers that represent the meaning.

Similar concepts end up with similar

number patterns like vacation and

holiday will have vectors that are

mathematically close to each other. For

TechCorb, this means that we can find

relevant documents based on what someone

means, not just the exact word that

they've used. When an employee asks,

"Can I wear jeans to work?" Our system

will find the dress code policy, even if

it never mentions the word jeans

specifically.

Now that we understand how LLMs and

embeddings work, we will need a system

that ties everything together. In our

case, Tech Cororb needs a chatbot where

customers can ask questions about the

company policy, product information, and

support issues. The chatbot needs to

remember conversation history, access

the company knowledge base, and handle

complex multi-step interactions. Your

first instinct might be to use OpenAI's

SDK to build a quick chat interface. But

you quickly realize that there are

massive missing pieces. Storing chat

messages, maintaining conversation

context, connecting to Tech Corp's

internal knowledge base, and handling

the possibility that the company might

switch from OpenAI to Anthropic or

Google in the future. And now what

seemed like a simple project becomes a

massive undertaking. While you can write

your own implementation to connect them,

there's already a wellestablished

abstraction layer called langchain.

Langchain is an abstraction layer that

helps you build AI agents with minimal

code. It addresses all those pain points

using pre-built components and

standardized interfaces. But first,

let's understand the crucial difference

between an LLM and an agent. When you

use large language models like GBT,

Claude and Gemini directly, you're using

them as static brain that can answer

question based on their training data.

An agent on the other hand has autonomy,

memory, and tools to perform whatever

task it thinks that is necessary to

complete your request. For TechCorp's

customer support scenario, imagine a

customer asks, "What's your company's

policy on refunding my product that

arrived damaged?" An agent will

self-determine how it should answer that

request based autonomously instead of

traditional software that requires

conditional statement that determines

how a program should execute. Langchain

comes with extensive pre-built

components that handle the heavy lifting

for Techorp Chatbot. Langchain chat

models provide direct access to LLM

providers. Instead of writing custom API

integration code, you can set up OpenAI

with open bracket model equals GPT3

turbo. So if the requirements change to

use enthropic instead, you simply change

one line LLM equals chat enthropic open

bracket model equals claw 3 sonnet. This

same pattern applies to every other

capability techp needs. Memory

management uses memory saver to

automatically store and retrieve chat

history, which means there's no need to

build your own database schema or

session management. Vector database

integration works through standardized

interfaces. Whether you choose Pine Cone

or Chroma DB, Langchain provides

consistent APIs and we'll go through

what a vector database is in the next

couple chapters. For text embedding, it

uses OpenAI embeddings or similar

components to convert Tech Corp's

document into vector representation. The

embedding process becomes a single

function call instead of managing API

connections and data transformations

manually. Finally, tool integration

allows the agent to access external

system. So if you need to query Tech

Corp's customer database, you can simply

create a tool that the agent can call

when it determines customer specific

information is needed. Without lang

chain, you would need to build all of

this infrastructure yourself. API

management for multiple LLM providers,

vector databases, SDKs, embedding

pipelines, semantic search logic, state

management, memory system, and tool

routing. The complexity grows

exponentially. Lang chain's component

library includes modules like chat

anthropic API connections. Chromad

vector database operations, OpenAI

embeddings for texttoveector conversion,

memory saver for chat history

management, custom tool definitions for

external system integrations. The agent

orchestrates these components based on

the conversation context. So as we're

talking about tech corp depending on

what the question is asked the agent

will now use the given tools like vector

databases as well as the context it

built from conversation memory and the

system prompt written in API layer

autonomously handle your request and you

can extend the agents abilities beyond

this example by using other pre-built

tools that lang chain offers like custom

database access web search local file

system access and more. Now that we

covered the conceptual elements of lang

chain, let's look at how it looks like

on a practical level. We can look over

at this lab specifically geared towards

how to use lang chain. All right, let's

start with the labs. In this lab, we're

going to explore how to make your very

first AI API calls. The mission here is

to take you from absolute zero to being

able to connect, call, and understand

responses from OpenAI's APIs in just a

few progressive steps. We begin by

verifying our environment. In this step,

we're asked to activate the virtual

environment. Check that Python is

installed. Ensure the OpenAI library is

available and confirm that our API keys

are set. This is important because

without this foundation, nothing else

will work. Once the verification runs

successfully, the lab will confirm that

the environment is ready. Next, we take

a moment to understand what OpenAI is.

Here we're introduced to the company

behind chatbt and their family of AI

models including GBT4, GBT4.1 Mini and

GBT 3.5. The narration highlights that

we'll be working with the Python OpenAI

library which acts as a bridge between

our code and OpenAI server. With that

context set, we move into task one. In

this task, we're asked to open up a

Python script and complete the missing

imports. Specifically, we need to import

the OpenAI library and the OS library.

After completing these lines, we run the

script to make sure that the libraries

are properly installed and ready to use.

If everything is correct, the program

confirms that the import worked. From

here, we transition into authentication

and client setup. Here, the lab explains

the importance of an API client, an API

key, and the base URL. The API key works

like a password that identifies us and

grants access, while the base URL

defines the server location where

requests are sent. This prepares us for

task two. In task two, we open another

Python script and are asked to

initialize the client by plugging in the

correct environment variables. This

involves making sure we pass the OpenAI

API key and OpenAI API base. Once those

values are filled in, we run the script

to verify the client has been properly

initialized. If done correctly, the

script confirms the connection to

OpenAIS servers. Once the setup is

complete, we move on to the heart of the

lab, making an API call. Before jumping

into it, we learn what chat completions

are. This is OpenAI's conversational API

where we send messages and receive

messages just like a chat. Lab explains

the three roles in a conversation.

System, user, and assistant, and how the

request format looks like in Python.

That takes us into task three. Here we

open the script, uncomment the lines

that define the model, role, and

content, and then configure it. So the

AI introduces itself. Once we run the

script, if all is correct, the AI should

respond back with an introduction. This

is the first live call to the model.

Next, we're guided into understanding

the structure of the response object.

The lab breaks down the response path,

showing how we drill down into the

response, choices, message content to

extract the actual text returned by the

AI. Although the response object

contains other fields like usage,

statistics, and timestamps, most of the

time what we really need is the content

field. That brings us to task four,

where we're asked to update the script

to extract the AI's response using the

exact path. Running the script here

confirms that we can successfully

capture and display the text that the AI

returns. Once we've mastered making

calls and extracting responses, the lab

shifts gears to tokens and costs. We

learned that tokens are the pieces of

text used by the model that every

request consumes tokens. Prom tokens are

what we send in. Completion tokens are

what the AI sends back and total tokens

are the sums of both. Importantly,

output tokens are more expensive than

input tokens. So being concise can save

money. Finally, in task five, we're

asked to extract the token usage values,

prompt completion, and total tokens from

the response. The script is already set

up to calculate costs. So once we

complete the extraction and run it, we

can see exactly how much the API call

costs. The lab wraps up by

congratulating us. At this point, we

verified our environment, connected to

OpenAI, made real API calls, extracted

responses, and calculated costs. The key

takeaway is remembering how to navigate

the response object with

response.content.

Some of the finer points and details

like exploring usage fields or playing

with different models are left for you

to explore yourself. But by now, you

should have a solid foundation for

working with AI APIs and be ready for

what comes next in the upcoming labs.

All right, let's start with the labs. In

this lab, we're going to explore Lang

Chain and understand how it makes

working with multiple AI provider

simpler and faster. The key idea here is

that instead of being locked into one

provider's SDK and rewriting code

whenever you switch, Langchain offers

one interface that works everywhere.

With it, you can move from OpenAI to

Google's Gemini or XAI's Gro by changing

just a single word. We begin the

environment verification. In this step,

we're asked to run a script that checks

whether Langchain and its dependencies

are installed, validates our API keys

and our base URL, and confirms that we

have access to different model

providers. Once this check passes, we're

ready to start experimenting. The first

test compares the traditional OpenAI SDK

approach with Lang. We have to write 10

or more lines of boilerplate code just

to make an API call. If we want to

switch to another provider, we'd have to

rewrite all of it. With Langchain, the

same logic is cut down to just three

lines. And switching providers is as

simple as changing the model name. In

this task, we're asked to complete both

versions in a script and then run them

side by side.

This is where we really see the 70%

reduction in code. The second task

demonstrates multimodel support. Here

we're asked to configure three

providers. Open GPT4, Google's Gemini,

and XAS Gro, all with the same class and

structure. Once configured, we can run

the exact same prompt through all of

them and compare their responses. This

is especially powerful when you need to

do AB test or balance cost because you

can evaluate multiple models instantly

without changing your code structure. In

the third task, we're introduced to

prompt templates. Instead of writing

separate hard-coded prompts for every

variations, we create one reusable

template with placeholders. Then we can

fill in the variables dynamically just

like fstrings in Python. This eliminates

the nightmare of maintaining hundreds of

slightly different prompt files. After

completing the template, we test it with

multiple inputs to see how the same

structure generates varied responses.

The fourth task takes a step further by

introducing output parsers. Often AI

responses are just free text, but what

our code really needs are structured

objects. Here we're asked to add parsers

that can transform responses into lists

or JSON objects. In this way, instead of

dealing with unstructured sentences, we

can access clean Python lists or

dictionaries that our application can

use directly.

Finally, we reach task five, which is

all about chain composition. Langchain

allows us to connect components together

with pipe operator. Just like Unix

pipes, instead of writing multiple

variables for each step, creating a

prompt, sending it to the model, getting

a response, and parsing the result, we

simply chain everything together. With

one line, we can link prompts, models,

and parsers, and then invoke the chain

to get the structure output. It's a much

cleaner and more scalable way to build

AI pipelines. By the end of this lab,

we've learned how a lane chain reduces

boiler plate, enables multimodel

flexibility, creates reusable templates,

parses structured outputs, and ties

everything together with elegant

chaining. Some of the finer details like

experimenting with more complex parser

setups or chaining additional steps are

left for you to explore on your own.

Now, we come to the technique, but it's

not a technique in the sense of building

lane chain application like we just did.

No, we're talking about a technique that

involves how you send your prompt to the

agent that we just built. In other

words, prompt engineering. When you send

a prompt as an input to TechCorps AI

document assistant that we just built,

the quality of your prompt directly

impacts the quality of responses you

receive. While AI agents can certainly

handle wide range of prompts,

understanding prompt techniques help you

communicate more effectively with

TechCorp system. For example, if you

prompt the agent with this question,

"What is the policy?" It can pull a lot

of details that are irrelevant. Sending

a more specific prompt like, "What's the

company's remote work policy for

international employees?" will lead to a

more accurate result from the agent. And

the same thing applies to role

definition when you're describing the

role of the agent. For example, you

might descriptively write out a detailed

prompt like, "You are a tech customer

support expert." When you are asked

about the company's policy, you are to

always respond with bullet points for

easier readability. As you can see,

being able to control the agents

behavior can directly benefit from a

well-written prompt. This type of

technique is referred to as prompt

engineering. And there are different

prompt techniques like zeroot, oneshot,

fshot, and chain of thought prompting

have its own use case for the task. For

example, zerootshot prompting means that

we are asking AI to perform a task

without providing any examples. So if

you send a prompt, write a data privacy

policy for our European customers,

you're essentially relying entirely on

the AI's existing knowledge base to

write the data policy document. Since

within the prompt, we're not giving any

examples of what they are. Oneshot and

few shot prompting is similar to

zerootshot but in this case we're

providing examples of how the agent

should respond directly within the

prompt. For example, you might say

here's how we format our policy

documents. Now write a data privacy

policy following the same structure

because you provided a template. The AI

follows your specific formatting and

style preferences more consistently. And

conversely, fusart learning is the act

of learning from the LLM side where even

though the LLM might not have seen the

exact training data for how to process

your unique request, it's able to

demonstrate the ability to fulfill your

request from similar examples provided.

And finally, chain of thought prompting

is a style of prompting where you

provide the model with a trail of steps

to think through how to solve specific

problems. For example, instead of

prompting the AI agent with fix our data

retention policy, you might instead use

chain of thought prompting to say here's

how you fix data retention policy.

Review current GDPR requirements for

data retention periods. Then analyze our

existing policy for specific gaps. Then

research industry best practices for

similar companies. And finally, draft

specific recommendations within

implementation steps. Now fix our

customer policy. As you can see,

providing how LLM should go through in

breaking down a specific request for how

data retention policy should be fixed

gives an exact blueprint for how the LLM

should then go and fix the customer

policy, which in this case, we're not

explicitly telling the agent how to fix

the policy for that, but it gives the

reasoning steps for the model to fix

accordingly. So, in this lab, we're

going to master prompt engineering using

lane chain. The main problem being

addressed here is that AI can sometimes

give vague or inconsistent responses or

not follow instructions properly. The

solution is to use structured prompting

techniques, zero shot, one shot,

viewshot, and chain of thought. Each of

which controls the AI's behavior in a

different way. We begin by verifying the

environment. The provided script checks

that lang chain and its OpenAI

integrations are installed, confirms

that the API key and base URL are set

and ensures that prompt template

utilities are available. Once this

verification passes, we're ready to move

into tasks. The first task introduces

zero prompting. In this exercise, we're

asked to compare what happens when we

provide a vague instruction versus when

we write a very specific prompt. For

example, simply asking the AI to write a

policy results in a long generic essay.

But when we specify write a 200word GDPR

compliant privacy policy for European

customer with 30-day retention period,

the response is focused, useful, and

aligned to the constraints. This

demonstrates why being specific is

crucial in zero shot prompts. The second

task moves us to oneot prompting. Here

we provide one example for the AI to

follow almost like showing a single

template. For example, if we gave the AI

one refund policy example with five

structured sections, we can then ask it

to produce a remote work policy and it

will replicate the same style in

structure. This shows how one example

can set the tone and ensure consistency

across many outputs. Next, in task

three, we expand on this with few shop

prompting. Instead of one example, we

provide multiple examples so the AI can

learn not only the format but also the

tone, patterns, and style. For example,

giving three examples of emphatic

support replies teaches the model how to

handle customer support issues

consistently. Once the examples are in

place, the AI can generate new responses

that follow the same tone and structure,

making it especially powerful for use

cases like customer service. In task 4,

we're introduced to chain of thought

prompting. This technique encourages the

AI to show its reasoning step by step.

Instead of vague oneline answer, the AI

breaks a problem into steps and works

through it systematically. This results

in clear or more reliable and more

accurate outputs, particularly for

complex reasoning tasks. Finally, task 5

brings all of these techniques together

in a head-to-head comparison. We run the

same problem through zero shot, one

shot, few shot and chain of thought

prompts to see the difference. Each

approach has its strength. Zero shot is

quick. One shot ensures formatting. Few

shot enforces tone and consistency and

chain of thought excels at detailed

reasoning. The outcome shows that

choosing the right technique can

dramatically improve results depending

on the task. By end of this lab, we not

only learned what each prompt method is,

but we've also seen them in action. The

key takeaway is that the right technique

can make your prompts 10 times more

effective. Some of these exercises are

left for you to explore and refine. But

now you have the foundation to decide

whether you need speed, structure,

style, or reasoning in your AI

responses. That wraps up this narration.

And with it, you're now ready to move on

to the next lab onto vector databases

and semantic search.

Let's do a quick recap of what we just

built. We learned about what LLM is and

how LLMs use what's inside the context

window. After learning about LLMs, we

wanted to solve Tech Corp's business

requirements of searching for 500 GB

worth of data. In order to do that, we

determined that embedding is a good way

to search a massive set of documents.

After that, we went over Langchain and

what functions they serve, which is that

they allow us to easily build Gentic

application like Tech Corps chatbot. So

now that we have the lang chain

application, we need to be able to

search through these large sets of

documents. Let's say inside the 500 GB

of documents, your company has a

document called employee handbook that

covers policies like time off, dress

code, and equipment use. Employees might

ask terms like vacation policy, but miss

time off guidelines. While these are

common questions that people would

typically ask, building a database

around this requirement can be tricky.

In a conventional approach where data is

stored in a structured database like

SQL, you typically need to do some

amount of similarity search like select

all from documents content like vacation

or vacation policy with a wild card

before and after to look for details

about questions on holiday. To expand

your result set, you might increase the

scope by adding VA or VAC space P.

However, the drawback to this approach

is that it puts the onus on the person

searching for the data to get the search

term formatted correctly. But what if

there was a different way to store the

data? What if instead of storing them by

the value, we store the meaning of those

words? This way, when you search the

database by sending the question itself

of can I request time off on a holiday

based on the meaning of those words

contained in the question, the database

returns only relevant data back. This is

a spirit of what vector databases tries

to address storing data by the

embedding. So essentially instead of

searching by value, we can now search by

meaning. Popular implementation of

vector databases include pine cone and

chroma. These platforms are designed to

handle embeddings at scale and provide

efficient retrieval based on semantic

similarity. And these are also great use

cases for prototyping something quick.

While conceptually this seems

straightforward, there's a bit of an

overhead in setting this up. And you

might be asking, well, can we just throw

the employee handbook into the database

like we just did for SQL database? Not

quite. And here's why. With SQL

database, the burden is put on the user

searching to structure the database. But

with vector databases, the burden is put

on you who is setting up the database

since you are trying to make it easier

for someone searching for the data. And

you can imagine why a method like this

is becoming extremely popular when

paired with large language models in AI

since you don't have to train separately

on how LLM should search your database.

Instead, the LLM can freely search based

on meaning and have the confidence that

your database will return relevant data

it needs. So let's explore some of the

key concepts behind what goes into

setting up a basic vector database.

Let's start with embedding. Embedding is

really the key concept that makes the

medium go from value to meaning. In SQL,

we store the values contained in the

employee handbook as a straightup value.

But in a vector database, you need to do

some extra work up front to convert the

value into semantic meanings. And these

meanings are stored in what's called

embeddings. For example, the words

holiday and vacation should semantically

share a similar space since the meaning

of those words are close to each other.

So before the sentence employee shall

not request time off on holidays in the

document is added to the database. The

system runs through an embedding model

and the embedding model converts that

sentence into a long vector of numbers

and when you search the database you are

actually comparing this exact vector.

That way when someone later asks can I

take vacation during a holiday even

though the phrasing is a little bit

different the database can still service

the request. And this is the fundamental

shift. Instead of searching by exact

wording, we're now searching by meaning.

Another important concept is

dimensionality. And you might be asking,

why do I have to worry about

dimensionality? Can't I just throw the

words into embedding and store it into

the database? There's one more aspect in

embedding that you need to think about,

and that's dimensionality. Typically, a

word doesn't just have one meaning to

learn from. For example, the word

vacation can have different semantics

depending on the context that is used

in. and capturing all those intricacies

like tone, formality, and other features

can give richness to those words.

Typically, dimensions we use today are

1536 dimensions, which is a good mix of

not having too much burden in size, but

also giving enough context to allow for

depth in each search. Once the embedding

is stored with proper dimension, there

are two other major angles that we need

to consider when we're working with

vector databases. And this is the

retrieval side. Meaning now that we

store the meaning of those words, we

have to take on the burden of the

retrieval side of embeddings. Since we

are not doing searches like we did in

SQL with a wear query, we need to make a

decision on what would technically be

counted as a much and by how much. This

is done by looking at scoring and chunk

overlap. And if you're at this point

wondering, this seems like a lot of

tweaking just to use vector database.

And that's the serious trade-off you

ought to consider when using a vector

database, which is that while a properly

set up vector database makes searching

so much more flexible, getting the

vector database properly configured

often adds complexity up front. So with

that in mind, scoring is a threshold you

set to how similar the results need to

be to be considered a proper match. For

example, the word Florida might have

some similarity to the word vacation

since it's often where people go for

vacation. But asking the question, can I

take my company laptop to Florida is

very different than does my company

allow vacation to Florida? Since one is

asking about a policy in IT jurisdiction

and the other is about vacation policy.

So setting up a score threshold based on

the question can help you limit those

low similarities to count as a match.

Okay, there's one final angle which is

chunk overlap. So in SQL, we're used to

storing things rowby row, but in vector

databases, things look a little bit

different. When we're storing values in

vector databases, they're often chunked

going into the database. So when we

chunk down an entire employee handbook

into chunks, it's possible that the

meaning gets chunked with it. That's why

we allow chunk overlap so that the

context spills over to leave enough

margin for the search to work properly.

In this app, we're going to build a

semantic search engine step by step. The

story begins with TechDoc Inc. where

users search through documentation

10,000 times a day. But more than half

of those searches fail. Why? Because

traditional keyword search can't connect

reset password with password recovery

process. Our mission is to fix that by

building a search system that

understands meaning, not just words. We

begin with the environment setup. In

this step, we're asked to install the

libraries that make vector search

possible. Sentence transformers for

embeddings. lang chain for

orchestration, chromadb for vector

database and few utility libraries like

numpy. Once installed, we verify the

setup using a provided script. If

everything checks out, we're ready to

move forward. Next, we take a moment to

understand embeddings. These are the

backbone of semantic search. Instead of

treating texts as words, embedding

converts text into numerical vectors.

Similar meanings end up close to each

other in this mathematical space. That

means forgot my password in account

recovery looks very different in words

but almost identical in vector 4. This

is a magic that allows our search engine

to succeed where keyword search fails.

That takes us into task number one where

we put embedding into action. We open

the script, initialize the mini LM

model, encode both queries and documents

and then calculate similarity using

cosign similarity. Running the script

demonstrates how a search for forgot

password successfully matches password

recovery, showing semantic understanding

in real time. Once we understand

embeddings, we move to document

chunking. Large documents can't be

embedded all at once. So, we need to

split them into smaller chunks, but if

we cut too bluntly, we lose context.

That's why overlapping chunks are

important. They preserve meanings across

boundaries. For example, setting a chunk

size of 500 characters with 100

characters overlap can improve retrieval

accuracy by almost 40%. Lang chain helps

us do this intelligently. In task number

two, we put this into practice by

editing a script to import lane chain's

recursive characters text splitter and

set the chunking parameters. Running the

script confirms that our documents are

now split into overlapping pieces ready

for storage. The next concept we explore

is vector stores. Embeddings alones are

just numbers. We need a system to store

and search through them efficiently.

That's where Chromma comes in. It's a

production ready vector database that

can handle millions of embeddings,

perform similarity search in

milliseconds, and support metadata

filtering. In task number three, we're

asked to create a vector store using

Chroma DB. We import the necessary

classes, configure the embedding model,

and then run the script. Once confirmed,

we have a working vector store that can

accept documents and retrieve them

semantically. Finally, we bring

everything together with semantic

search. Here we implement the full

pipeline, convert the user query into an

embedding, search the Chromma store,

retrieve the most relevant document

chunks, and return them to the user. For

example, a query like work from home

policy will now correctly surface remote

work guidelines. In task 4, we configure

the query, set the number of top results

to return, and establish a threshold for

similarity scores. Running the script

validates our search engine end to end.

The lab closes with a recap. We started

with a broken keyword search system

where 60% of the search failed. Along

the way, we learned about embeddings,

smart document chunking, vector stores,

and semantic search. By the end, we

built a productionready search engine

with 95% success rate. Some of the

deeper experiments like adjusting chunk

sizes, testing different embedding

models and or adding metadata filters

are left for you to explore on your own.

So is it possible that instead of

searching through the entire 500 GB of

documents, AI assistant can fit them

into their context window and generate

output. This is called rag or retrieval

augmented generation. Let's say your

company used the AI assistant to ask

this question. What's our remote work

policy for international employees? In

order to understand how rag works, we

need to break them into three simple

steps. Retrieval, augmented, and

generation. Starting with retrieval,

just like how we convert the document

into vector embeddings to store them

inside the database, we do the exact

same step for the question that reads,

"What's our remote work policy for

international employees?" Once the word

embedding for this question is

generated, the embedding for that

question is compared against embeddings

of the documents. This type of search is

called semantic search where instead of

searching by the static keywords to find

relevant contents, the meaning and the

context of the query is used to match

against the existing data set. Moving on

to augmentation in rag refers to the

process where the retrieved data is

injected into the prompt at runtime. And

you might think why is this all that

special? Typically, AI assistants rely

on what they learned during

pre-training, which is static knowledge

that can become outdated. Instead, our

goal here is to have the AI assistant

rely on up-to-date information stored in

the vector database. In the case of RAG,

the semantic search result pends to the

prompt that essentially serves as an

augmented knowledge. So, for your

company, the AI assistant is given

details from company's documents that

are real, up-to-date, and private data

set. And all this can occur without

needing to fine-tune or modify the large

language model with custom data. The

final step of rag is generation. This is

a step where AI assistant generates the

response given the semantic relevant

data retrieved from the vector database.

So the initial prompt that says what's

our remote work policy for international

employees? The AI assistant will now

demonstrate its understanding of your

company's knowledge base by using the

documents that relate to remote work and

policy. And since the initial prompt

specifies a criteria of international

employees, the generation step will use

its own reasoning to wrestle with the

data provided to best answer the

question. Now, RAG is a very powerful

system that can instantly improve the

depth of knowledge beyond its training

data. But just like any other system,

learning how to calibrate is an acquired

skill that needs to be learned to get

the best results. Setting up a rag

system will look different from one

system to another because it heavily

depends on the data set that you're

trying to store. For example, legal

documents will require different

chunking strategies than a customer

support transcript document. This is

because legal documents often have long

structured paragraph that need to be

preserved and intact. While

conversational transcript can be just

fine with sentence level chunking with

high overlap to preserve context. In

this lab, we're taking our semantic

search system to the next level by

adding AI power generation. Up until

now, we've been able to find relevant

documents with high accuracy. For

example, matching remote work policy

when someone searches work from home.

But the CEO wants more. Instead of

retrieving a document, the system should

actually answer the user's questions

directly. something like yes, you can

work three days from home, not just

showing a PDF. We begin the environment

setup. In this step, we're asked to

activate the Python environment and

install the key libraries. These include

Chroma DB for vector storage, sentence

transformers for embeddings within lane

chain with integrations for OpenAI and

hugging face. Once installed, we verify

everything using the provided script to

ensure the rack framework is ready.

Next, we move into task number one,

setting up the vector store. Here we

initialize a chromabb client. Create our

get collection named tech corp brag and

configure the embedding model all

mini6v2.

This is where we get our system of

memory. A place where all of our company

documents will be stored as vectors so

that we can search them semantically. In

task number two, the focus shifts to

document processing and chunking. Unlike

our earlier lab where we split text into

fixed-size character chunks, here we

upgrade to paragraph-based chunking with

smart overlaps. The goal is to preserve

meaning so that each chunk contains

complete thoughts. This is crucial for

RAG because when AI generates answers,

the quality depends on having coherent

chunks of context.

From there, we go to task number three,

LLM integration. This is where we

connect OpenA model GPD4.1 Mini. The API

key and base are already preconfigured

for us. We just need to set the

generation parameters like temperature,

max tokens, and top P values. Once

integrated, we can test simple text

generation before layering on retrieval

and augmented steps. Task number four

introduces prompt engineering for rag.

We're asked to build a structured prompt

template that always ensures context is

included. The system prompt makes it

clear that answers must come only from

the retrieved documents. If the

information isn't in context, the AI

must respond with, "I don't have that

information in the provided documents."

This keeps our answers factual and

prevents hallucinations. Finally, we

reach task number five, the complete rag

pipeline. Here we wire everything

together. The flow is embed the user

query, search Chromad, retrieve the top

three chunks, build a contextaware

prompt, and generate an answer using

LLM. The final touch is a source

attribution. Every answer points back to

the document it was derived from. This

transforms the system into a full

production ready Q&A engine. At the end,

we celebrate rag mastery. What started

as simple document search has evolved

into a powerful system that retrieves,

augments, and generates answers. This is

the same architecture that powers tools

like catchupt, claude, and gemini. Some

parts like experimenting with different

trunk strategy, refining prompts are

left for you to explore yourself. But by

now you've built a complete RAG system

that answers questions with context,

accuracy, and confidence.

Now that we covered the conceptual

elements of RAG, let's look at how it

looks on a practical level. To better

understand this, we can look over at

this lab specifically geared towards how

to use Rag. Now we covered the basic

concepts of simple chat application that

allows us to chat with documents using

vector databases and rag. Most business

cases in the real world may be slightly

more complicated. For example, in tech

corp's case, the business requirement

might extend to more complex

requirements like being able to connect

the agent to human resource management

system to pull employee documents to

cross reference and make personalized

responses. However, lang chain has

limitations. When business requirements

become more complex like multi-step

workflows, conditional branching or

iterative processes, you need something

more sophisticated for better

orchestration. That's where langraph

becomes essential. Langraph extends lane

chain to handle more complex multi-step

workflows that go beyond simple question

and answer interactions. For example, if

a customer asks, I need to understand

our data privacy policy for EU

customers. Since we assume that inside

the 500 GB of database, it contains

details about EU specific regulations,

we need to create a system that can

analyze Tech Corp's data privacy

policies for EU customers, ensuring

compliance with GDPR, local regulations,

and company standards. While in a

traditional software development, you

need to write code that can sequentially

and conditionally call different

sections of the code to process this

request. With lang graph, this becomes a

graph where each node handles a specific

responsibility. For example, node one,

search and gather privacy policy

documents. Node two, extract and clean

document content. Node three, evaluate

GDPR compliance using LLM analysis. Node

four, cross reference the local EU

regulations. And node five, identify

compliance gaps and generate

recommendation. A node is an individual

unit of computation. So think of a

function that you can call. Once you

have all the nodes created in langraph,

you will then need to connect them and

this connection is called an edge. Edges

in langraph define execution flow. For

example, after node one gathers

documents, the edge routes to node two

for content extraction. And after node 3

evaluates compliance, a conditional edge

either routes to node four for

additional analysis or jumps to node

five for report generation. And one

final concept to keep in mind beyond

nodes and edges is shared state between

each node. This is possible by using

state graph that essentially stores

information throughout the entire

workflow. For example, class compliance

state type dictionary topic string

documents list of string current

documents optional string compliance

score optional integer gaps list of

string recommendation list of string can

be used for nodes we identified before.

As the workflow progresses, each node

updates relevant state variables. Node

one populates documents with found

policy files. Node two processes

individual documents and updates current

document. Node 3 calculates compliance

score. Node 4 identifies gaps. Node 5

generates recommendation. The state

graph orchestrates execution based on

configured flow. If node 3 determines

compliance score is below 75% the

conditional edge routes back to node one

to gather additional documents. If the

score exceeds 75% execution proceeds to

node 5 for final report generation. As

you can see this creates powerful

capabilities loops for iterative

analysis conditional branching on

intermediate results persistent state

that maintains context across the entire

workflow. So for Tech Corps compliance

assistant, Langraph is an essential tool

for workflow automation. All right,

let's start with the labs. In this lab,

we're diving into Langraph, a framework

designed for building stateful

multi-step AI workflows. Unlike simple

chains, Langraph gives us specific

control over how data moves, letting us

create branching logic, loops, and

decision points. By the end of this

journey, we'll have built a complete

research assistant that can use multiple

tools intelligently. We begin with

environment setup. In this setup, we

activate the Python virtual environment

and install the required libraries.

Langraph itself, Langchain, and OpenAI

integration. Once everything is

installed, we run a verification script

to make sure our setup is ready. With

the environment ready, we start small.

Task number one introduces us to

essential import. We bring in state

graph end and type dict to define the

data that flows through the workflow.

Then we add a simple state field for

messages. This is the foundation. State

graph holds the workflow and marks

completion and the state holds shared

data. In task number two, we create our

first nodes. Nodes are just Python

functions that take state as inputs and

return partial updates. In this case, we

define a greeting node and an

enhancement node. Once connected, one

node outputs a basic greeting and the

next node improves it with a bit of a

flare. This demonstrates how state

accumulates step by step. Pass number

three is about edges. The connections

between nodes. Here we use add nodes and

add edges to wire greeting nodes to the

enhancement node. With that, we built

our first mini workflow. Data flows from

one function to another. The state

updates along the way. In task number

four, we take it further with a

multi-step flow. We add new nodes like a

draft step and a review step. Connect

them and see how the data moves through

multiple stages. Each step preserves

states, adds detail and passes it on.

This mimics real world pipelines where

content is outlined, drafted and

polished. Pass number five introduces

conditional routing. Instead of a fixed

flow, the system now decides

dynamically. For example, if the query

is short, it routes one way. If

detailed, it routes another. The router

inspects the state and returns the next

node name, making workflows flexible and

adaptive. Then comes task number six,

tool integration. Here we add a

calculator tool. The router checks if

the query is math related. If so, it

routes to the calculator node which

computes the answer. This is our first

glimpse at how Langraph lets us

integrate specialized tools directly

into workflows. Finally, task number

seven puts everything together into

research agent. We combine the

calculator with a web search tool like

duck.go. Depending on the query, the

system decides whether to perform a

calculation, run a web search, or handle

a text normally. This is a dynamic tool

orchestration, the foundation of modern

AI agents. By the end of this lab, we've

gone from simple imports to a fully

functional research assistant. We've

seen how to build nodes, connect them,

design multi-step flows, and add routing

logic and integrate tools. Some of the

deeper experiments like chaining more

advanced tools or refining the router

logic are left for you to explore on

your own.

Now that we covered lang chain and

langraph and understood how techp

business requirements can be met by

leveraging pre-built tools that it

offers, there's one final piece that's

been popular since Anthropics released

back in November 2022 called MCP or

model context protocol. Techorps AI

document assistant is working well for

internal knowledge base, but employees

might now need to access external

systems like customer database, support

systems, inventory management software,

and other thirdparty APIs. And writing

custom integrations to all these API

connections will take a huge amount of

time. MCP functions like an API, but

with crucial differences that make it

perfect for AI agents. Traditional APIs

expose endpoints that require you to

understand implementation details

leading to rigid integrations tied to

specific systems. MCP doesn't just

expose tools. It provides

self-describing interfaces that AI

agents can understand and use

autonomously. The key advantage here is

that unlike traditional APIs, MCP puts

the burden on the AI agent rather than

the developer. So when you start an MCP

server, an instance starts and establish

a connection with your AI agent. For

example, the Techorps document assistant

might easily have these MCP servers to

enable powerful integration. Let's say

customer database MCP. When someone

asks, "What's the status of the order 1

2 3 4?" The AI uses an MCP to query

TechCorb's order management system,

retrieves the current status, and

provides a complete response. The same

logic applies for support tickets,

inventory databases and notification

system mentioned earlier where we can

simply plug into existing integrations

of MCP servers to allow the agent to now

extend its capabilities. For example, we

can create a very simple MCP server code

that looks something like this. Here we

have fast MCP customer DB that starts

the MCP server with the name customer DB

at MCB tool that exposes a function to

MCP clients. the AI can call like an API

function parameters and return types

that tells the MCP client what inputs

are required and what type of output to

expect. Finally, customers variable that

is a fake database in this case stored

in memory, but in your company's case,

you can connect this to a SQL database

or MongoDB or any other custom database

you might hold customer information on.

Now, looking at this code might confuse

you on what MCP really is, since it's

typically being talked about as a simple

plugand play, and you're right to think

that way. The difference here is that

this MCP server code that's written only

needs to be written once, and it doesn't

necessarily have to be you. In other

words, a community of MCP developers

might have written custom MCP servers

for other popular tools like GitHub,

GitLabs, or SQL databases, and you can

simply use them directly on your agent

without having to write the code

yourself. That's where the power of MCP

really comes from. In this lab, we're

going deeper into MCP, model context

protocol, and learning how to extend

Langraph with external tools. Think of

MCP as a universal port like USB that

allows AI system to connect to any tool,

database or API in a standardized way.

With it, our langraph agents can go

beyond built-in logic and integrate

external services seamlessly. We begin

with the environment step. In this step,

we activate our virtual environment and

install the key packages. Lang graph for

the workflow framework, Langchain for

the core abstractions, and Langchain

OpenAI for the model integration. The

setup also prepares for fast MCP, the

framework we'll use to build MCP

servers. Once installed, we verify by

learning the provided script, ensuring

everything is ready for MCP development.

Next, we get a conceptual overview of

the MCP architecture. Here the lab

explains that the MCP protocol acts as a

bridge between an AI assistant built

with Langraph and external tools. The

flow works like this. The MCP server

exposes tools and schemas. Langraph

integrates with them and queries are

routed intelligently. The naming

convention MCP server tool ensures

clarity when multiple tools are

involved. A helpful analogy is comparing

MCP to USB devices. A protocol is a

port. The server is a device. The tools

are its functions. And Langraph is a

computer that uses them. That brings us

to task number one, MCP basics. Here

we're asked to create our very first MCP

server. The task involves initializing a

server called calculator, defining a

function as a tool with at MCP.tool

decorator and running it with the SCDIO

transport. This shows how simple it is

to expose a structured function as an

external tool. that langraph can later

consume. In task number two, we

integrate MCP with langraph. The

challenge here is to connect the

calculator server to an agent. This

involves configuring the client fetching

tools from the server create react agent

that can decide when to call the

calculator selected when needed. Next,

task number three scales things up with

multiple MCP servers. Instead of just a

calculator, we add another server, in

this case, a weather service. Now,

Langraph orchestrates between both. The

system retrieves available tools,

creates an agent with access to both

servers, and intelligently routes

queries. If a user asks a math question,

the calculator responds. If they ask

about the weather, the weather tool

responds. This is where we see the true

power of MCP. Multiple servers are

working together under a unified AI

agent. The lab wraps up by celebrating

MCP mastery. By now, we've created MCP

servers, integrated them with ElangRaph,

and orchestrated multiple tools. The key

takeaways are that MCP is universal. It

can connect any tool to any AI. Routing

is what gives it power. The design is

extendable, so we can add servers

anytime. Some deeper explorations like

exposing databases, APIs or file systems

through MCP are left for you to explore

on your own. That concludes this

narration. Next, we'll continue the

journey by experimenting with resource

exposure, human in the loop approval

flows, and eventually deploying

production ready MCP packages.

Now that we have put all these pieces

together like context windows, vector

databases, lang chain, langraph, MCP,

and prompt engineering, Techorp is now

able to do complex document search that

went from manual searching that could

have taken up to 30 minutes to now less

than 30 seconds using our AI agent. And

we also have a higher accuracy using

contextaware semantic search like using

rag. And finally, the chat application

UI allows users to have more

satisfaction in working with a tool that

can help keep track of conversation

history and better intuition overall.

And the availability for this is 24/7 as

long as the application is running. And

this is just the beginning. Imagine

layering on predictive analytics,

proactive compliance agents, and

workflow automation that doesn't just

answer questions, but actively solves

problems before employees can even ask.

The shift from static documents to

living intelligent system marks a

turning point not just for Tech Corp,

but for how every other business can

unlock a full value of its knowledge

using agents.