Build a Gemini App for my data | Vertex AI Search and Conversation demo

We look to build a Search and Conversation App that uses your PDF data on Google Cloud and Vertex AI Search using the LLMs provided. The video covers off how to setup, use and configure the google AI application. We also demonstrate how to add the search and conversation into your website or local site. Google search and conversation API, and using Vertex AI with your data helps you to Build generative AI search and conversations for customers and employees with no code and simple install.
Vertex AI Search and Conversation's easy-to-use orchestration layer abstracts the complexity of building enterprise-ready apps. Maintain control over your data and applications.
Links:
Install and setup Google Cloud: • How to implement Enter...
Google Cloud: cloud.google.com
Google Search and Conversation App: console.cloud.google.com/gen-...
Step-by-step: www.1stfordata.com/post/build...
Web Code: www.1stfordata.com/tools-and-...
For a Full course on AI with Google Vertex and how to build your AI applications support me here: www.udemy.com/course/ai-on-go...
Contents:
00:00 Introduction
00:17 Build your AI App
02:00 Create DataStore and add your documents for searching
04:25 Preview your App
05:20 Configuration of App for more features
07:02 Integrating the AI app with your website
07:38 Enable a local AI app on your server
08:55 Enable AI app on a public site
09:23 Demo
#googleai #vertexai #googleVertex #googlegemini

[@brunoaziza]

Well done!

[@LevelUp_Plus]

Thanks, glad you enjoyed it.

[@ee-lonlim8240]

tks very much for sharing this! would u advise using Wix as the easiest approach to deploy? thank you!

[@LevelUp_Plus]

Hi Thanks for watching. Wix is a easy option, but you are free to use whatever web tool you are familiar with. The main part is to be able to create a custom HTML page that you can put your code in.

[@VISHVANI9]

DataStore create based on CloudStorage bucket you pointed, is that Data Store vector database? If so what is the Vector db used behind? Is this using RAG?

[@VISHVANI9]

I found it Data Store uses RAG technique. Please refer.... kzbin.info/www/bejne/fnzCkHiAfbKGg7c

[@LevelUp_Plus]

Hi Yes it is using RAG.

[@JulianHarris]

​@@LevelUp_Plus isn't the data store the source? Under the hood somewhere in the App I would've thought there'd be a Vertex AI Vector Search Index created that is the vector db but I've not looked for it.

[@chetanhiregoudra8232]

Authentication app please

[@victornl32]

That's exactly what I was looking for! I've just created an app, but the citations it provides are mostly wrong...

[@LevelUp_Plus]

Hi thanks for watching, there is some fine tuning and the quality of the data you pass in. I have found success with company documents that are clean, nicely formatted and logical. There may be cases that it doesn't work first try, and that is where you need to format or get the data quality of the inputs to a good standard. The old "data quality" is part of the equation - I wish it worked 100% first time round, but there is some tweaking required.

[@victornl32]

@@LevelUp_Plus thanks for your reply!

[@Nirosh-cy2zu]

What is the cost involved with this?

[@LevelUp_Plus]

Hi, thanks for watching. For the pricing, you will be charged storage costs of the data and your information you uploaded or indexed. For this example it was low cents per day. The second part of the costing is per query your chatbot does, you can check latest pricing from google here: cloud.google.com/generative-ai-app-builder/pricing. At the moment there is free credits applied, so be sure to use those.