Dify AI: Create LLM Apps In SECONDS with NO Code FOR FREE! Flowise 2.0?

WorldofAI
29 Oct 202313:40

Summary

TLDRこのビデオでは、AIネイティブアプリの作成と運用に特化したツールであるDefi(旧称DII)について紹介しています。3ヶ月前にGPTモデルに限定されていたが、現在はオープンソースやLlamaなどのクローズドソースモデルも使用可能です。Defiは、プロンプトエンジニアリングやAIアプリの作成など、幅広い機能とプラグインを提供しています。特に注目すべきは、Hugging Faceの組み込みモデルのサポートや、データセットサービス、APIキーとモデル名を追加してオープンソースモデルを呼び出す機能です。これにより、柔軟性とカスタマイズ性が向上し、オープンソースプロジェクトに特化した人々にとっては、簡単に効率的な開発方法となります。また、Defiは、内部チームで使用するアプリケーションや外部リリース向けに、わずか5分で展開できるツールとして、生産性を向上させる機能を提供しています。

Takeaways

  • 🚀 新しいDefi(dii)は、大規模言語モデルを用いたアプリケーションの作成と管理に特化したオールインワンソリューションです。
  • 📈 3ヶ月前とは比べ、diiはオープンソースやLlamaなどのクローズドソースモデルも利用可能になりました。
  • 🔌 新機能として、Hugging Faceの埋め込みモデルのサポートや、プロンプトエンジニアリングの統合が追加されました。
  • 🔍 diiを使用すると、AIアプリケーションの作成プロンプトエンジニアリングなど、幅広い用途に利用できます。
  • 🛠️ diiは、プログラミング言語の変換やテキスト生成など、多種多様なタスクを自動化することができます。
  • ⏱️ diiを使用することで、AIアプリケーションの開発と運用の時間を大幅に短縮できます。
  • 🌐 diiはクラウドサービスとしてアクセス可能で、またDockerを使用してインストールすることもできます。
  • 📚 注文されたDefi Cloudユーザーには、200クエリの無料OpenAI Curが提供されます。
  • 📈 diiは、プログラミング、エンターテイメント、ライティングアシスタント、翻訳、HRなど、多種のカテゴリーのアプリケーションを作成できます。
  • 📱 diiを使用して作成されたアプリケーションは、すぐに展開することができ、エクスポートや組み込みも可能です。
  • 🔗 diiは、オープンソースプロジェクトに特化しており、オープンソースモデリングの活用が容易になります。
  • 📈 注文されたDefi Cloudユーザーには、プラグ&プレイでアプリケーションを構築できるUIが提供されます。

Q & A

  • 最近のアップデートで、Defi(dii)はどのような新しい機能を追加しましたか?

    -Defiは、オープンソースモデルだけでなく、プロンプトエンジニアリングやHugging Faceの埋め込みモデルのサポートなど、多くの新機能を追加しました。これにより、柔軟性とカスタマイズ性が向上し、AIアプリケーションの作成が容易になります。

  • Defiを使用してAIアプリケーションを構築する際に、どのようなプロンプトエンジニアリングが可能ですか?

    -Defiでは、特定のコンテキストに焦点を当てたり、APIアクセスを通じてプラグインやAPIと統合したり、応答を別の場所に出力したりすることができるプロンプトエンジニアリングが可能です。

  • Defiのプラグインタブで何ができますか?

    -プラグインタブでは、Defiのプラグインを追加・削除・変更することができます。また、Google検索APIやGitHub、Googleなどの外部サービスと統合することも可能です。

  • Defiでサポートされている言語モデルには何がありますか?

    -Defiでは、オープンソースモデルやHugging Face、Anthropicなどの様々な言語モデルがサポートされています。これにより、幅広い範囲の言語モデルを利用してアプリケーションを作成できます。

  • Defiのデータセットサービスとは何ですか?

    -Defiのデータセットサービスを使用すると、自分のデータセットを作成し、それを使用してアプリケーションをトレーニングすることができます。また、Notionやウェブサイトからデータを同期することも可能です。

  • Defiを使用してAIアプリケーションを展開する際のシステム要件は何ですか?

    -Defiを使用するには、2コア以上のCPUと4GB以上のRAMが必要です。ただし、より良いスペックを持つマシンで使用すると、より機能的で適切に動作します。

  • Defiのインストールにはどのような方法がありますか?

    -Defiはクラウドサービスを通じてアクセスすることもできますし、Dockerを使用してインストールすることもできます。Docker Composeを使用して簡単にセットアップすることが可能です。

  • Defi Cloudユーザーにはどのような無料リソースが提供されますか?

    -Defi Cloudユーザーには、200回の無料OpenAI Cur Queriesが提供されます。これにより、OpenAIベースのアプリケーションを構築することができます。

  • Defiのダッシュボードでは何ができますか?

    -Defiのダッシュボードでは、作成できるアプリケーションを発見し、コードインタープリターやチャットボットなどのサンプルアプリケーションを試すことができます。また、カテゴリー別にアプリケーションをブラウズし、テンプレートから新しいアプリケーションを作成することもできます。

  • Defiのアップデートで追加された新しい機能をどのように活用できますか?

    -新しい機能を活用して、プログラミング、エンターテイメント、ライティングアシスタント、翻訳、HRなどのカテゴリーに属するアプリケーションを作成することができます。また、SQLジェネレーターやコードコンバーターなどの特定のタスクに特化したアプリケーションも作成可能です。

  • Defiのアプリケーションをカスタマイズするために、どのような設定ができますか?

    -Defiのアプリケーションをカスタマイズするために、モデルプロバイダーを設定して、使用したいモデルを選択することができます。また、プロンプトエンジニアリングタブを使用して、アプリケーションのプロンプトを設定し、APIアクセスを通じてプラグインやAPIと統合することもできます。

  • Defiのドキュメントタブで何ができますか?

    -Defiのドキュメントタブでは、Defiの高度な機能や使用方法について学ぶためのチュートリアルにアクセスできます。これにより、Defiをより効果的に活用し、カスタマイズされたアプリケーションを作成することができます。

Outlines

00:00

🚀 AIアプリケーションの創造と運用:D5ツールの紹介

3ヶ月前に発表されたD5ツールは、強力な言語モデルアプリケーションを作成するのに役立ちます。これまでは、Chat GPTモデルに限定されていましたが、オープンソースモデルも使用可能になりました。LlamaやAnthropicなど、様々な言語モデルが利用可能です。D5はAIアプリケーションのプロンプトエンジニアリングなど、幅広い用途に使えます。また、Hugging Faceの埋め込みモデルのサポートやデータセットサービス、プロンプトエンジニアリングの統合など、多くの機能とプラグインが追加されました。これにより、柔軟性とカスタマイズ性が向上し、オープンソースプロジェクトに特化した人々にとっては、AIアプリケーションの作成が簡単かつ効率的になるでしょう。

05:02

🌐 D5の新規機能とプラグイン:SQLジェネレーターの例

D5の新規機能を紹介し、プラグインの活用方法を解説します。SQLジェネレーターの例として、自然言語をSQL文に変換するプロンプトを設定し、デバッグとプレビューが可能であることが示されています。また、D5はクラウドサービスとして利用可能で、アカウントを作成するだけですぐに始められます。D5 Cloudユーザーには、無料で200回のOpen AI Cur Queriesが提供されます。D5はプログラミング、エンターテイメント、ライティングアシスタント、翻訳、HRなど、様々なカテゴリのアプリケーションを作成することができます。

10:02

𑁍 D5のインストール方法とカスタマイズ:モデルプロバイダーの設定

D5のインストール方法について説明し、Dockerを使用する方法も紹介しています。また、D5のカスタマイズについても触れています。モデルプロバイダーの設定では、オープンAIやAnthropicなどのトライアルモデルを利用できます。また、APIキーを入力して、Hugging FaceなどのオープンLMプロバイダーを実装することも可能です。データソースタブでは、Notionやウェブサイトからデータをアップロード・同期することができ、SerpやGitHubとGoogleの統合も可能です。最後に、D5の高度な機能についても触れ、チュートリアルを提供しています。

Mindmap

Keywords

💡Defi

Defiは、大規模言語モデルを用いたアプリケーションの構築と管理を支援するツールです。ビデオでは、Defiが提供する幅広い機能とプラグイン、そしてオープンソースモデルの利用について説明されています。Defiは、AIアプリケーションの開発と運用を視覚的に行えるLM Opsプラットフォームとして紹介されています。

💡オープンソースモデル

オープンソースモデルとは、誰もが自由に使用できる言語モデルのことです。ビデオでは、DefiがGPTモデルだけでなく、オープンソースモデルも使用できるようになったと触れられており、これにより柔軟性とカスタマイズ性が向上しています。

💡プロンプトエンジニアリング

プロンプトエンジニアリングは、AIモデルに入力するテキストを設計するプロセスです。ビデオでは、Defiのプロンプトエンジニアリング機能を使って、自然言語の問い合わせをSQL文に変換することができると説明されています。

💡Hugging Face

Hugging Faceは、自然言語処理モデルを提供する企業です。ビデオでは、DefiがHugging Faceの埋め込みモデルをサポートし、ユーザーがオープンソースモデルを簡単に利用できるようになっていることが紹介されています。

💡アプリケーション

ビデオでは、Defiを使用して作成できる様々な種類のAIアプリケーションについて説明されています。これには、プログラミング、娯楽、ライティングアシスタント、翻訳、HRなどのカテゴリーに分類されるアプリケーションが含まれます。

💡Docker

Dockerは、アプリケーションをコンテナ化して実行するためのプラットフォームです。ビデオでは、DefiをDockerを使用してインストールし、実行することができると触れられており、これによりクラウドサービスとは別の方法でDefiを利用できることが示されています。

💡APIキー

APIキーは、アプリケーションが外部サービスにアクセスするための認証情報を提供するものです。ビデオでは、Defiで使用するオープンソースモデルにアクセスするために、Hugging FaceのAPIキーを入力する必要があると説明されています。

💡データセットサービス

データセットサービスとは、AIアプリケーションにデータを提供するサービスのことです。ビデオでは、Defiのデータセットサービスを使って、ユーザー自身のデータセットを作成し、アプリケーションをトレーニングすることができると紹介されています。

💡プラグイン

プラグインは、アプリケーションに追加の機能を提供するソフトウェアです。ビデオでは、Defiのプラグイン機能を使って、アプリケーションに新しい機能を追加することができると触れられており、これによりアプリケーションの柔軟性が向上します。

💡プロダクトIVITY

プロダクトIVITYとは、仕事や活動の効率や成果を指します。ビデオでは、DefiがAIアプリケーションの作成を簡素化し、プログラミングのバックエンドコーディングの労力を軽減することで、ユーザーのプロダクトIVITYを向上させると説明されています。

💡チャットボット

チャットボットとは、テキストベースの対話型のAIアプリケーションです。ビデオでは、Defiを使って作成されたワールドオブAIチャットボットについて紹介されており、これはユーザーが質問に答えることができる対話型アプリケーションです。

Highlights

Defi, also known as 'do it for you', is an all-in-one solution for building and managing AI native apps based on large language models.

Defi has expanded its capabilities to include open source models in addition to proprietary ones like LLaMA and Anthropic.

The platform offers new features and plugins, such as support for Hugging Face embedded models and dataset services.

Users can now add Hugging Face or Replicate API keys and model names to call any open source model.

Defi provides flexibility and customization for creating large language model applications.

The tool can create AI-powered applications within minutes for internal or external use.

Features of Defi include an SQL generator, code converter, text generator, and support for coding completion.

Defi can create out-of-the-box websites with form mode and chat conversation modes using a single API.

The platform saves backend coding effort and allows users to focus on visual data analysis.

Defi increases productivity by saving time on the hassle of creating AI applications.

The video will explore new features of Defi that were not covered in a previous video made 3 months ago.

The presenter offers one-on-one sessions to help develop solutions for AI tools and brainstorm ideas.

Defi is user-friendly and can be used by teams to visually develop and operate AI applications.

The platform provides 200 free OpenAI Cur queries for registered Defi Cloud users to build apps.

Defi has a visual UI for easy plug-and-play application creation and supports API-based services.

Users can create a variety of apps, such as code interpreters, chatbots, and SQL generators, with Defi.

Defi allows users to choose from different templates or start from scratch to build their own AI applications.

The platform is continuously working on incorporating new plugins and features.

Defi enables users to create their own datasets and train apps based on their data.

The platform supports integration with various services like GitHub, Google, and the Google Search API.

Defi can be accessed through the cloud or installed using Docker, with minimum system requirements provided.

The video concludes with a demonstration of creating a chatbot app and configuring model providers in Defi.

Transcripts

play00:00

[Music]

play00:00

around 3 months ago I had made a video

play00:02

on a tool that helps you create powerful

play00:04

large language model applications like

play00:06

flow wise it's called defi also known as

play00:10

do it for you it's an all-in-one

play00:12

solution for seamlessly building and

play00:14

managing AI native apps based on ranges

play00:17

of large language models 3 months ago

play00:20

you were restricted to only using chat

play00:22

GPT models for creating LM based apps

play00:25

however you are now open to the

play00:27

possibility to use open source as well

play00:30

Plus close Source models such as llama

play00:32

you have anthropic and so many others

play00:35

now this could be used for AI app

play00:37

creation prompt engineering and many

play00:39

other possibilities you have way more

play00:42

features and plugins such as a new

play00:44

support for hugging face embedded models

play00:46

you have data set Services as well as

play00:49

integration of prompt engineering just

play00:51

take a look at this example where you're

play00:53

able to now add hugging face or

play00:55

replicate API Keys plus the model name

play00:58

so that you're able to call any any open

play01:00

source model on the model providers they

play01:03

added this functionality where you're

play01:05

able to utilize many different ranges of

play01:07

large language models to create these

play01:09

large language model applications this

play01:11

brings in so much more flexibility and

play01:14

customization to what you're trying to

play01:16

create and this will be really useful

play01:18

for a lot of people who are focusing on

play01:20

open- Source projects as this is a great

play01:23

Gateway for you to create them as it's

play01:25

an easy and efficient way to do so so

play01:28

throughout today's video we're going to

play01:29

be ding a little bit deeper deeper on di

play01:32

by exploring these new features that we

play01:34

haven't covered before and we're also

play01:36

going to take a look at how you can get

play01:37

started with it and showcasing just a

play01:39

brief overview of this application so

play01:41

with that thought stay tuned and let's

play01:43

get straight to

play01:47

it hey guys I started this new thing

play01:50

where I'm going to be offering my one-on

play01:51

ones with you guys so if you're

play01:52

interested in this I can definitely help

play01:54

you develop a solution for AI tools help

play01:57

you brainstorm ideas as well as just is

play02:00

basically elevating what you're trying

play02:01

to accomplish with my knowledge so if

play02:04

you're interested in this definitely

play02:05

take a look at this link in the

play02:06

description below hey what is up guys

play02:09

welcome back to another YouTube video at

play02:10

the world of AI in today's video we're

play02:12

going to take a look at dii which is an

play02:14

AI tool focused on creating and

play02:17

operating AI native apps with a range of

play02:19

different large language models not

play02:21

restricted to only using the GPT models

play02:23

you are able to use open service models

play02:26

for creating these free applications now

play02:29

this is quite similar to what flow flow

play02:31

wise was actually capable of doing but

play02:33

this is more of an easier way to use

play02:36

this LM Ops platform as you're able to

play02:39

use this for teams to develop AI

play02:40

applications and operate them visually

play02:43

now with dii you are able to create

play02:46

these AI powered applications within

play02:48

minutes whether it's for internal teams

play02:50

to use or external releases and you can

play02:53

deploy them quickly within just 5

play02:55

minutes the tool provides various

play02:57

different features such as Storyteller

play02:59

Bots for an answering specific questions

play03:01

you have an SQL generator for converting

play03:03

natural language to SQL you have a code

play03:06

converter for converting programming

play03:08

languages and a text gener generator for

play03:11

summarizing these key information sets

play03:14

now you're also able to code complete

play03:16

with this model which is absolutely

play03:18

insane as you have such a wide range of

play03:21

different tasks that you could be

play03:22

completed with the AI applications that

play03:25

are made off of dii it can create out of

play03:28

the-box websites supporting form mode

play03:30

and chat conversation modes with a

play03:33

single API encompassing plug-in

play03:36

capabilities as well as context and

play03:38

enhancements and such forward you save

play03:41

so much backend coding effort you have

play03:44

so much time to focus on the visual data

play03:46

analysis that's presented through defy

play03:49

it saves you time with log review

play03:53

annotations for applications and so much

play03:55

more in simple terms it's increasing

play03:58

your productivity while using defi as it

play04:01

saves you time with all the hassle that

play04:04

is there for creating AI applications

play04:06

this is why I wanted to put emphasis on

play04:08

this because of these new amazing

play04:10

features and plugins that were released

play04:12

with this new update so let's get to the

play04:14

next step of the video where I showcase

play04:15

how to download it and then we will go

play04:17

quickly into showcasing how you can

play04:19

actually use this if you would like to

play04:22

access our private Discord which gives

play04:23

you subscriptions to AI tools for free

play04:26

you have networking opportunities

play04:27

networking calls consultings so much

play04:30

more definitely take a look at this link

play04:32

in the description below follow world of

play04:34

AI if you guys haven't already

play04:35

definitely take a look at the YouTube

play04:37

page subscribe like this video turn

play04:38

notification Bell and check out our

play04:40

previous videos for the case of this

play04:42

video I want to be showcasing how to

play04:44

create an app it's fairly easy what I

play04:46

did is create an SQL generator so in

play04:49

this case I went along clicked on the

play04:51

create new tab and selected text

play04:52

generator I provided the name clicked

play04:55

continue and I created it something that

play04:57

is fairly easy and I'll then keep take

play04:59

take you to this overview page in which

play05:01

you can go and set up the model provider

play05:04

I selected the base model that is

play05:05

provided which is completely free which

play05:07

is the open AI based model and in this

play05:10

case you're able to utilize open uh

play05:12

Source models but I'm just going to go

play05:14

ahead and use open AI selected the gp3

play05:17

3.5 turbo reasoning method as well as

play05:19

using the text embedding uh Ada model

play05:23

now once this is all set you can

play05:25

configurate plugins but in this case

play05:26

we're not going to be using that we have

play05:28

done that and then go onto the prompt

play05:30

engineering Tab and then you're able to

play05:32

set the actual prompt where I said that

play05:36

you are an SQL generator that will help

play05:38

users translate their input natural

play05:40

language query rep requirements and

play05:43

Target database now it does this by

play05:45

putting this into the target SQL

play05:47

statement and you're now able to deploy

play05:50

this fairly easily after you save it now

play05:52

you're able to debug it as well which is

play05:54

also really useful but in this case

play05:56

you're able to preview this off the

play05:58

preview tab which allows you to select

play06:00

database types and just not I did not do

play06:04

any of this it did it on its own and it

play06:06

was able to create all this from a

play06:08

single prompt which is absolutely

play06:09

amazing you're able to use SQL MySQL SQL

play06:13

server and such forth you're able to run

play06:16

the batch with your own file and you can

play06:19

just input your uh whatever text that

play06:22

you want to translate for the SQL

play06:23

generator you can then execute it and

play06:25

it'll have this output over here which

play06:27

you can copy save it as as well as

play06:29

export it and that's easy as that in

play06:32

creating your own LM based

play06:35

application now there's two ways to

play06:37

install this you can definitely access

play06:38

it through the cloud as well as

play06:41

installing it using Docker now this is

play06:44

something that you can do with Docker

play06:45

compose so there's a couple commands in

play06:48

which you can do so you can set this up

play06:50

with Docker and then compose it with the

play06:53

command over here now what I recommend

play06:56

is that you actually check out the

play06:58

requirements ments because you need to

play07:01

have a CPU greater than or equal to two

play07:03

core you need to have more than 4 GB of

play07:05

RAM to have this functional now these

play07:08

are just the minimum system requirements

play07:10

so keep that in mind it'll be more

play07:12

functional and more like appropriate to

play07:14

use with better specs than these ones

play07:16

over here so definitely keep that in

play07:18

mind but the best case is that you use

play07:20

it with the cloud service as this is

play07:23

something that you can access right away

play07:25

off their website what you got to do is

play07:27

just create an account and you can get

play07:28

started right away way which we'll do

play07:30

right next quickly let's go over some of

play07:33

the cool features we talked about how

play07:36

you can use different large language

play07:37

models you're able to utilize L chain

play07:39

hogging face and replicate to utilize

play07:42

open source models you can see that

play07:44

there is an access to a wide range of

play07:47

different options in terms of utilizing

play07:49

large nage models to create applications

play07:51

they also stated that we provide the

play07:53

following free resources for registered

play07:55

defi Cloud users which gives you 200

play07:57

free open AI Cur queries queries sorry

play08:01

and this will allow you to build open AI

play08:03

based apps you have visual or

play08:05

registration which is a UI that helps

play08:08

you plug and play and create

play08:10

applications you have text embeddings

play08:12

you have API Based Services which is

play08:15

allowing you to access web apps directly

play08:18

and integrate the API without any

play08:20

complex backend Services once you have

play08:22

created an account you'll be then sent

play08:24

to the dashboard this is where you're

play08:27

able to discover different apps that

play08:28

could be created with def you have a

play08:30

code interpreter that could be created

play08:33

you have job advertisements personalized

play08:35

dialogues you can have chat Bots created

play08:38

and so much more you can see that

play08:40

there's a lot of different ranges of

play08:42

apps that could be created you have

play08:44

different categories such as programming

play08:46

entertainment writing assistant

play08:49

translate as well as HR now these are

play08:51

just some of the things that you can do

play08:53

uh in this case if I click on the code

play08:55

interpreter you can start chatting with

play08:57

it right away which will basically solve

play09:00

different things uh related to coding

play09:02

now in this case I think I asked it

play09:04

previously to write python code for a

play09:06

basic Snakes and Ladder game which it

play09:08

actually did and it created me a

play09:09

functional code for it now this is just

play09:11

one bit of it I believe I deleted the

play09:14

rest of it but you're you're able to

play09:16

delete or generate sorry such things

play09:18

like this now you're able to also start

play09:21

from scratch by building your own

play09:22

chatbot app uh you're also able to focus

play09:25

on different AI applications which could

play09:27

be done over here now you're also able

play09:29

to choose from different uh templates

play09:31

that are already built which will be way

play09:33

easier for a lot of people now if you go

play09:36

to the plugins tab this is something

play09:38

that they're continuously working on

play09:40

which will be incorporated fairly soon

play09:42

but if you click on the data set tab

play09:44

this is something in which you can

play09:45

create your own data sets and train

play09:47

different apps based off your own data

play09:50

you can upload files straight from your

play09:53

desktop you're also able to sync it from

play09:55

notion as well as from websites which is

play09:57

a feature that they're going to be

play09:58

incorporating fairly shortly but in the

play10:01

case of this video I'm going to just

play10:02

simply showcase a chat that I made this

play10:05

is a world of AI chat bot that created

play10:07

and it's something that you can deploy

play10:09

right away and Export it and embed it to

play10:12

a different workflow you can start

play10:13

chatting with it and I believe this one

play10:16

was trained with my own channels data so

play10:20

it answers questions based off what I

play10:22

ask it I mean what the like channel is

play10:25

about so in the case it gives you

play10:26

reference to what the channel is gives

play10:28

you more idea about what AI is in

play10:30

machine learning that's basically the

play10:32

gist of what I created with this world

play10:33

of AI chatbot it's fa easy to do so you

play10:36

can have a prompt engineering feature

play10:38

which allows you to have it focus on a

play10:41

certain context it has API access which

play10:44

could be integrated with different

play10:46

plugins different apis as well as have

play10:49

it so that it could be basically

play10:52

outputed to another place you can see

play10:54

the logs and annotations that helps you

play10:56

track what the responses are and that's

play10:59

basically a gist of how this basically

play11:02

operates now guys if you are to click on

play11:05

this blue button which is the setup

play11:07

model provider within your application

play11:09

you're able to configurate and select

play11:10

the models that you want in this case

play11:12

they give you two models which are on

play11:15

trial you can utilize gbt 4 and gbt 3.5

play11:18

turbo in this case they're B on trial so

play11:21

they give you tokens that are completely

play11:22

free and you can utilize them in this

play11:24

case you can use 200 calls from open Ai

play11:27

and you can use 600 tokens from

play11:30

anthropic now once you have used those

play11:32

up you can obviously purchase more and

play11:34

input your own API keys and you're able

play11:36

to select from the reasoning model types

play11:39

as well as the embedded models and the

play11:40

speech detects models but if you do not

play11:43

want to use these you can basically

play11:45

Implement and search through showing

play11:47

different models that could be

play11:48

implemented over here you can use a

play11:50

range of different like open LM

play11:54

providers uh for example if you're going

play11:55

to be using hugging face you can simply

play11:57

just click on ADD uh you can do

play12:00

embeddings you have text generation the

play12:02

model type you have end points that

play12:04

could be set and you simply just need to

play12:06

put your API key hugging face uh hugging

play12:09

face API key sorry token over here in

play12:11

the case of the model you simply just go

play12:13

on to hugging face copy the model card

play12:16

and you simply go back and paste it over

play12:18

here it's easy as that you click save

play12:21

and you're able to move forward in this

play12:22

case I didn't upload my API key so it

play12:24

wouldn't be showing but that's easy as

play12:26

that guys if you go to data source you

play12:28

can add your own workspace from notion

play12:31

you can play around with different uh

play12:33

plugins in this case you can work with

play12:34

serp which is the Google search API and

play12:38

you're basically able to integrate

play12:40

different things as well by integrating

play12:42

GitHub and Google you're able to also

play12:44

work with different languages so

play12:46

definitely take a look at this if you

play12:47

want to work with anything other than

play12:49

English but that's basically what the

play12:51

model provider tab is about now if you

play12:54

want to configurate this further you can

play12:56

definitely go on the documentation Tab

play12:58

and you can get started with all of

play13:00

their tutorials which will help you

play13:02

learn a lot more on what you can do with

play13:04

Advanced features of D5 but that

play13:07

basically concludes today's video guys I

play13:09

hope you got some more insight as to

play13:10

what you can do with this new updated D5

play13:13

model I'll leave all these links in the

play13:15

description below definitely check out

play13:17

the Consulting page if you want to book

play13:18

a oneon-one with me follow the patreon

play13:21

page if you want to check out our

play13:23

Discord definitely give world of AI a

play13:25

follow if you guys haven't already and

play13:27

lastly make sure you guys subscribe to

play13:28

notification Bell like this video and

play13:30

check out our previous videos so you can

play13:31

stay up to date with the latest AI news

play13:33

but with that thought guys thank you

play13:34

guys so much for watching have an

play13:36

amazing day and I'll see you guys fairly

play13:38

shortly peace out fellas

Rate This

5.0 / 5 (0 votes)

Related Tags
AIツールアプリケーション開発オープンソースGPTモデルプロダクトIVITYSQL生成プロンプトエンジニアリングAPI統合データセットプラグインチャットボット
Do you need a summary in English?