Curriculum
13 Sections
132 Lessons
Lifetime
Expand all sections
Collapse all sections
Introduction
3 Items
1.1
What is in this Course?
1.2
How to succeed in this course
1.3
Creating API keys and using them in VS code
Module-1 : Langchain
9 Items
2.1
Prompts and Tokens
2.2
Langchain
2.3
Dynamic Prompting
2.4
Different ways of Prompting LLM’s
2.5
Output parsers
2.6
Runnables
2.7
Chains in langchain
2.8
Memory in langchain
2.9
Assignment – 1
Module-2 : Embeddings
4 Items
3.1
Vectors
3.2
Representing text as vectors
3.3
Text Similarity Search
3.4
Embedding models
Module-3 : RAG(Retrieval Augmented Generation)
21 Items
4.1
What is RAG
4.2
Data Extraction
4.3
Text splitters
4.4
Selecting Embeddings
4.5
Testing for Bias
4.6
Selecting Vector Database
4.7
Qdrant Data Ingestion Code (Part-1)
4.8
Qdrant Data Ingestion Code (Part-2)
4.9
vanilla RAG pipeline
4.10
User Query Augmentation
4.11
Qdrant Search
4.12
RRF (Reciprocal Rank Fusion)
4.13
Reranking
4.14
Reranking (Code Walkthrough)
4.15
Selecting LLM
4.16
Creating Test Dataset
4.17
Metrics for retrieval
4.18
Metrics for LLM generation
4.19
Experiment tracking
4.20
Assignment-2
4.21
Mock Interview-1
Module-4 : LangGraph
8 Items
5.1
Introduction to LangGraph
5.2
Components of Langgraph
5.3
Conditional Edge
5.4
Parallel Processing
5.5
Dynamic Routing and Reducers
5.6
Chatbot with Memory
5.7
Chatbot execution
5.8
Callbacks
Module-5 : Text To SQL using LangGraph (Project-1)
6 Items
6.1
Introduction
6.2
Coding Router node and Knowledge base
6.3
Coding Specialised nodes
6.4
Coding Filter check node
6.5
Testing the Flow
6.6
Assignment-3
Module-6 : Health Insurance Recommendation (Project-2)
11 Items
7.1
Introduction
7.2
React agent
7.3
Compare Tool
7.4
Extract policy names
7.5
Extract policy data
7.6
Compare Tool Code
7.7
QA tool overview
7.8
QA tool code walkthrough
7.9
Testing
7.10
Assignment – 4
7.11
Mock Interview -2
Module-7 : Metrics
4 Items
8.1
GenAI application lifecycle-1
8.2
GenAI application lifecycle-2
8.3
Technical Metrics to Monitor
8.4
Business metrics and iterative improvement
Module-8 : Deployment Toolkit
14 Items
9.1
TCP, HTTP
9.2
HTTP versions
9.3
REST API principles
9.4
Client implementation
9.5
Server implementation
9.6
Testing HTTP API
9.7
Websocket
9.8
Disadvantages of Websocket
9.9
Code walkthrough of Websocket in local
9.10
Grpc protocol
9.11
Grpc Code walkthrough in local
9.12
Docker Overview
9.13
Container Orchestration
9.14
Compute and memory for Container Orchestration Tools
Module-9 : Deployment of Opensource LLM's on Kubernetes (AWS EKS)
16 Items
10.1
Overview
10.2
Pods and service in kubernetes
10.3
ELB, Deployment and HPA in kubernetes
10.4
VLLM
10.5
Components in server code
10.6
Need for Prometheus to expose semaphore metrics
10.7
Application code – gRPC setup
10.8
Application code – Traffic management and Streaming
10.9
Setting up AWS Infra using Terraform
10.10
Node Autoscaling using Karpenter
10.11
Deployment and HPA config
10.12
Service config and Load Balancers
10.13
Deploying of Stability 3B model on AWS EKS G5 instance GPU’s
10.14
Load testing for Scaling
10.15
Assignment – 5
10.16
Mock Interview – 3
Module-10 : CI/CD Pipeline for RAG based on Terraform
9 Items
11.1
Overview
11.2
CI/CD Stages
11.3
Code build and Code Deploy
11.4
Setting up infrastructure for CI/CD Pipeline
11.5
Configuring AWS Cloudwatch
11.6
RAG Pipeline and Redis Caching
11.7
Websocket Implementation Walkthrough
11.8
Websocket Implemention – 2
11.9
CI/CD execution (WIP)
Module-11 : Gen AI System design for interviews (WIP)
8 Items
12.1
Importance of system design for Interviews
12.2
Blueprint of ML system design
12.3
Design a Product Catalog for Ebay – 1
12.4
Design a Product Catalog for Ebay – 2
12.5
Design Quality evaluator for Product Content for Amazon – 1
12.6
Design Quality evaluator for Product Content for Amazon – 2
12.7
Design Product Insight Extraction from Raw Comments – 1
12.8
Design Product Insight Extraction from Raw Comments – 2
Module-12 : LLM Internals
19 Items
13.1
Training components of conversational Ai
13.2
What are Neural Networks?
13.3
Training Neural Network
13.4
Classification Vs Regression Problems?
13.5
Cross Entropy loss
13.6
LSTM overview
13.7
Sequence to Sequence models overview
13.8
Decoder only models
13.9
Encoder-Decoder models
13.10
Training Language models
13.11
Need for GPU’s
13.12
Parameters of language models
13.13
Need for Quantization
13.14
Why we need Reinforcement learning to build advanced conversational Ai?
13.15
Reward Model
13.16
Reinforcement learning through Human Feedback(RLHF)
13.17
Capabilities and limitations of LLM’s?
13.18
Open source Vs Paid LLM’s in different scenario’s
13.19
Final Mock interview
Advanced Gen AI Workflows
Search
Curriculum
This content is protected, please
login
and enroll in the course to view this content!
error:
Content is protected !!
Login with your site account
Lost your password?
Remember Me
Modal title
Main Content