Scribd
Upload
251 views14 pages

RAG and AI Agents Simplified

Uploaded by

boyrockstar100
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
251 views14 pages

RAG and AI Agents Simplified

Uploaded by

boyrockstar100
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

WELCOME

RAG and AI Agents


Simplified
#exploring_ai_with_mongodb

Ronit Jai Prakash


Application Developer, Caelius Consulting
Feel Free to Code
Along, Ask Doubts,
and Enjoy
Agenda
● What is RAG
● AI Agents Simplified
● Intro to Google Cloud AI Ecosystem
● Use Case Demo
● Use Case Implementation
What is RAG
Retrieval Augmented Generation
Retriever

Query

User LLM Response

Context
● Retrieval-Augmented Generation
(RAG) is a machine learning
technique that combines
retrieval-based and

In Other
generation-based models. It
retrieves relevant information from
external sources (such as a
database or document repository)

Words
and uses that information to
generate context-aware and
informed responses or outputs.
AI Agents and
Agentic Systems
AI Agents and Agentic Systems
● They are driven by AI agents, that can be single or multi agent systems.
● They often use large language models (LLMs) to help with decision making.
Google Cloud
GenAI Ecosystem
The Infrastructure Powerhouse for GenAI
Vertex AI: Comprehensive platform for building, deploying, and managing ML models.

TPUs: Specialized hardware acceleration for training and inference.

Scalable Infrastructure: Handle demanding workloads with ease.

Integration with other Google Cloud services: Seamless workflow with BigQuery, Cloud Storage,
etc.

Cloud Run Function Vertex AI API


#show_time

Use Case
Demo
#show_time

const rawReviewId =
rawReview._id.toString();

const rawReviewGameId =
rawReview.gameId

const rawReviewContent =
rawReview.content;

to analyze sentiment

const response = await


context.http.post({

Use Case url: analyzeSentimentFunctionURL,

Implementation });
Use Case Architecture

Query Vector Embeddings

Formulated Response Retrieve Context

Express
Gemini MongoDB
Thank you for
your time.

You might also like