Up next in 10
How to Setup AI Autocomplete in VS Code (Free & Local) Using Ollama (Unlimited & Free) Setup in 2026
Apr 24, 2026
https://gist.github.com/gauti123456/aec9cf454c4aa6287c0bf20e0bf623ce
Watch My Visual Studio Code IDE Setup Video For Fonts,Themes & Extensions
https://youtu.be/Bon8Pm1gbX8
Hi Join the official discord server to resolve doubts here:
https://discord.gg/cRnjhk6nzW
Visit my Online Free Media Tool Website
https://freemediatools.com/
Buy Premium Scripts and Apps Here:
https://procodestore.com/
Show More Show Less View Video Transcript
0:00
Uh hello guys, in this video I will
0:02
actually show you how to set up uh AI
0:04
autocomplete feature inside VS code
0:08
using Olama AI provider directly locally
0:12
inside your VS code. So we will not be
0:15
using any kind of API. We will directly
0:17
be downloading an AI model inside your
0:20
local machine and connecting it through
0:23
an extension in VS code. So which will
0:26
actually come all the AI suggestions. So
0:28
for this tutorial we will need a
0:30
extension called as continue. So go to
0:32
the extensions tab. Simply type for this
0:35
extension which is
0:37
continue
0:39
which I will be using in this tutorial.
0:42
So this is the extension continue. It's
0:43
an open-source AI coding agent and it
0:46
will be helpful for setting up the AI
0:48
autocomplete suggestions as you type the
0:50
code. Simply ex click the install button
0:53
execute it to install this. So once it
0:57
get installed it will be right here
0:59
inside the sidebar section. Simply
1:00
activate the this extension
1:03
and after activating it
1:06
uh now what we need to do if you're
1:08
doing it for the very first time let me
1:10
just show you.
1:12
You need to go to the config the
1:14
settings option. You will be seeing
1:16
this. So click on that and right here
1:19
you will see this sidebar section and
1:21
you will see this models. So right here
1:24
we need to configure the models. So this
1:27
is section for autocomplete.
1:32
You can also set up the chatting for
1:35
general chatting. You can also configure
1:36
this as well. Simply click this button
1:39
setup autocomplete model. So click on
1:42
open.
1:45
So right here you need to mention you
1:47
can see inside the documentation they
1:49
are exactly mentioned that. So what we
1:51
need to do you simply
1:54
now to configure this you go to the
1:57
config section and go to the local
1:59
configuration and right here you'll be
2:01
downloading a model from Olama
2:06
the
2:08
Olama if you don't know it's actually a
2:10
open-source tool which allows you to
2:12
download any kind of AI model directly
2:14
inside your machine there is also a
2:17
second best alternative if your machine
2:19
is not powerful in my case my machine is
2:22
not powerful. It doesn't have the
2:24
required hardware to actually run the
2:26
these these are very powerful models. If
2:29
you want to run these models then these
2:32
models will not be running in in a very
2:35
ordinary machine. So you need to have
2:37
very highend PCs. So the second approach
2:42
is that you simply log inside
2:44
and it actually gives you enough free
2:48
usage. You can actually use cloud models
2:51
which are completely free. So as you can
2:54
see cloud models are completely free to
2:56
use. So one such cloud model once you
3:00
download directly inside your machine.
3:03
Simply open
3:05
and right here in the chatting bar
3:08
section you will actually see this from
3:12
here you select this this one miniax-
3:15
m27
3:17
col cloud personally I'm using this
3:20
model for about 1 month now this model
3:22
is really fast it's very efficient as
3:25
well it works really well so you can
3:27
directly chat right here as well
3:31
if you send out a message it will direct
3:32
directly respond to you.
3:35
So now to connect inside your VS code,
3:38
you simply mention the name of this
3:41
model.
3:45
So if you simply minimax
3:50
so simply copy the name of the model and
3:52
directly paste it
3:56
inside. So this whole file I have given
3:59
the link in the description. This is a
4:00
config.ml file. So you can go to the
4:03
description link to actually find the
4:05
full source code of this file and simply
4:07
paste it
4:10
in the model section right here.
4:15
So as you can see that we are pasting
4:17
the name right here.
4:21
So we are we will be using this miniax
4:23
cloud model from Olama. So now what will
4:26
happen if you now simply see the
4:29
continue extension go back you will now
4:33
see now it will be using this miniax
4:36
m27 cloud version. If you create a new
4:39
chat and simply ask a question that top
4:45
NodeJS frameworks
4:48
in 2026. So if you ask a question it
4:52
will instantly reply to you. it will
4:55
actually use that. You can see that now
4:57
it is actually replying to you the top
5:00
NodeJS frameworks in 2026.
5:03
It's exactly telling you and same goes
5:06
with the autocomplete feature as well.
5:08
So if you try to create a file right
5:10
here
5:15
so it will show you all these
5:17
autocomplete suggestions.
5:26
If you create a
5:31
script.js JS file,
5:45
so
5:48
so it's actually using these models
5:50
right here. As you can see, we
5:52
configured the autocomplete. So
5:54
autocomplete takes some time. So after
5:56
restarting your VS code just give it
5:58
some time so that it actually
6:01
so you can actually normally chat with
6:04
this as well. So you can see that
6:07
you can simply tell it to say build a
6:10
index h or image to
6:14
pdf file
6:17
full web app.
6:21
So as you see that now it will create a
6:23
file here image to pdf.html HTML file
6:27
it will think about this. So it will now
6:29
you can see it is start coding right
6:31
here.
6:32
So you can just see the speed as well
6:34
because it's actually using the cloud
6:36
model from Olama which is completely
6:38
free to use. So in this easy way you can
6:40
integrate this directly inside your VS
6:44
code.
6:52
You can create any file. This can be a
6:54
Python file as well.
7:13
There is also a second option. You can
7:15
directly install a local model. If you
7:17
have a powerful machine,
7:20
you can install a local model as well
7:22
that I already installed it. This is not
7:25
really powerful. It just have 1.5
7:27
billion parameter. So you can install
7:31
local models through lama as well. If
7:34
you want to remove this model, you
7:35
simply say remove
7:38
and just name the mention.
7:43
So it will be deleted as you can see
7:45
that. So in this easy way you can delete
7:49
install models as well and using this
7:52
continue extension you can you can see
7:55
it created it is actually creating it.
8:08
So you can see it is now continuing it.
8:11
You can see that.
8:15
So in this way you can set up
8:17
autocomplete
8:19
journal chatting with coding can create
8:21
files as well. You can see the speed
8:24
here how the fastly it is generating the
8:27
code for you and
8:30
whenever it reaches 90% it will give you
8:33
email address. So you can anyway go to
8:36
settings and simply check the usage
8:38
section. So it will reset after every 2
8:41
hours session usage and weekly usage. So
8:43
it's more than enough to actually use
8:45
the Olama cloud models.
8:48
So
8:50
you can see that it's created this file
8:52
here for you.
8:55
You can click the create file button. It
8:57
will create paste all this code for you.
8:59
Automatically create this file for you.
9:02
Create file as you see.