Ollama Embedding: How to Feed Data to AI for Better Response?

this is amazing now we have o llama

embedding you can create rag application

with better performance using this

embedding in this we are going to ingest

data from URL convert those to

embeddings and then store in Vector

database so when we ask a question a

relevant data will be sent to the lodge

language model using Ola and finally we

get a more relevant answer we are going

to use chroma DB nomic embedding and

mless large language model finally going

to add that in user interface using

gradio that's exactly what we're going

to see today let's get

[Music]

started hi everyone I'm really excited

to show you about ol Lama embedding

especially we're going to use nomic

embed text model for embedding why nomic

nomic embed text has a higher context

length and it surpasses open AI

embedding models you can see noric

embedding model performance in this

chart finally we are going to create a

user interface like this this I'm going

to take you through step by step on how

to do this but before that I regularly

create videos in regards to Artificial

Intelligence on my YouTube channel so do

subscribe and click the Bell icon to

stay tuned make sure to click the like

button so this video can be helpful for

many others like you in this we are

going to use l chain put all the pieces

together so pip install Lang chain Lang

chain community and Lang chain core and

then click enter next create a file

called app.py and let's open it inside

the F from longchain Community import

web based loader chroma embeddings chat

ol

runable pass through string out passer

chat prom template character text

splitter now we going to define the

model which is mistal so now we're going

to see four steps one is to retrieve the

data from the URL split the data and the

second step is to convert that to

embedding and store in Vector DB and

third we are going to perform the rag so

first split data into chunks so I'm

passing the list of URLs now I'm going

to use web base loader to extract all

the data from those URLs next combining

those data now we are going to use

character textt splitter and here we are

going to divide the chunk and the chunk

overlap is 100 for example this is a

chunk size and the overlap between

different chunks is chunk overlap next

splitting those documents now we have

completed the first step of splitting

the chunk next we're going to convert

those document into embeddings and store

them in Vector database so we going to

initiate chroma DB so from documents

that's where you pause all the documents

give a name for the collection and here

is where we are defining the olama

embering so the model name we are giving

is nomic Ember text next we are using

the retriever this is used to retrieve

relevant documents when we ask a

question so the third step is rag so we

going to compare before Rag and after

rag so printing for our reference before

rag template and getting the promt

template using chat promt template next

creating the rag chain so first The

Prompt will be sent to the lar language

model so the prompt is what is the topic

name and then that will be sent to the

LOD language model mistal and finally we

get the output now I'm going to print

and invoking the chain and providing the

topic which is Ol so that is before rag

next after rag the same process as

before so we are defining the rag

template here the main difference is

that we are providing the context prom

template as before and then we defining

the rack chain here we providing the

context and also the question finally we

are invoking the chain and asking a

question that's it only few lines of

code so first we extracted the data from

the URL and split the document into

chunks next we converted those to

embeddings store them in chroma DB next

we are passing the promt template and

invoking the chain now I'm going to run

this code so make sure you've downloaded

AMA then AMA pull nomic embed text to

pull the model also AMA pull mistal to

download m model now type Python app.py

and then click enter so here I have

added the log on the right hand side so

you can see the performance so you can

see embedding took 219 milliseconds

approximately so that is really fast and

also you got the answer here so before

rag I'm sorry for the confusion but

olama doesn't seem to be a widely

recognized term so after rag olama is a

local AI model server that allows user

to run large language model on their own

machine

now we have created a rag application

which can run completely locally on your

machine with zero cost now we are going

to add user interface to this so I've

modified the code a little bit added

gradio at the top then I moved

everything to the function process input

with the list of URLs and the question

so I'm going to split the URLs then do

the same process again and finally

assigning the function name here having

two inputs one is for entering the list

of URLs and another one to ask a

question finally in interface. launch

now I'm going to run this code in your

terminal Python ui. piy and then click

enter now I got the URL here I'm going

to open it so here's the URL I'm going

to provide this URL next going to

provide this URL and going to ask what

is olama and click submit now it's

processing the request and here is the

response based on the context provided

olama is a platform or software that

enables user to run and create large

language models locally with support for

Mac OS Linux and Windows this is

exciting I'm really excited about this

I'm going to create more videos similar

to this so stay tuned I hope you like

this video do like share and subscribe

thanks for watching