Skip to content
Web Search Node (using Langchain + Serper)Data Retrieval Node (using LlamaIndex with both a vector store and SQL database)Response Synthesis Node (combining all data sources into a cohesive answer)
Gen AI App Track
Gen AI Lesson Tracker
Topic
Lesson
Status
Topic
Lesson
Status
Understanding of a model and neural networks
9
What is a model?
Done
Understanding about training a model and doing prediction using Linear regression problem
Done
Understanding about logistic regression and activation functions
Done
Understand about What is a Neuron and how it works
Done
Understanding gradient descent basics and back propagation
Done
Understanding about an artificial neural network
Done
AI vs ML vs Deep Learning vs GEN AI
Done
Creating a model using Linear Regression
Done
Creating a model with Logistic Regression
Done
Understanding about Generative AI and ChatGPT
6
What is Generative AI?
Done
What are LLMs
Done
Introduction to OpenAI and ChatGPT
Done
Using ChatGPT for various tasks using manual prompting
Done
What kind of applications can be developed using these LLMs
Done
Creating a chatbot using OpenAI API and Streamlit/Gradio
Done
Prompt Engineering
15
Prompting guidelines
Done
Prompt components
Done
Dividing into sub tasks
Done
Iterative refinement framework
Done
Zero, one and few shot prompting
Done
Text classification
Done
Chain of thought prompting
Done
Auto COT
Done
Least to Most prompting
Done
ReAct Prompting
Done
Self-consistency
Done
Generate Knowledge prompting
Done
Tree of thought
Done
Reflection Prompting
Done
Using Open AI playground to try all the prompt engineering techniques
Done
Using Lang chain
15
How a typical AI enabled app works
Done
Why Langchain?
Done
Using Langchain for first time
Done
Understanding and creating a first chain
Done
Understanding Runnables in detail
Done
Chaining 2 chains
Done
Chat vs Completion style models
Done
Implementing a chat chain
Done
Understanding the use of memory and different types of memory
Done
Using Lang smith for tracing
Done
Using Chainlit and Gradio to develop a chatbot
Done
Creating a chatbot using langchain and streamlit
Done
Using runnables
Done
Financial Advisor App using streamlit demonstrating chain of chains
Done
Modifying the existing app to add memory
Done
Understanding embeddings, Vector store and RAG
6
Understanding the embedding flow
Done
Using Chroma DB as vector store
Done
Building a retriever chain
Done
Visualizing embeddings
Done
Using Pinecone as Vector store
Done
Updating Financial app use RAG using chroma
Done
Understanding tools and agents
11
Understanding how to configure tools
Done
Understanding ChatGPT functions
Done
Defining a tool to interact with Database
Done
Defining a tool to search the web
Done
Understanding how agents work
Done
Using an agent and agent executor
Done
Memory and agent scratch pad
Done
Recovering from errors in tools
Done
Understanding and implementing callbacks
Done
Creating a custom database tool
Done
Updating Financial Advisor app to use database tool
Done
Langserve
3
Understanding about Langserve
Done
Deploying using Langserve
Done
Exposing runnables as API
Done
Langgraph
17
Why Langgraph?
Done
Understanding Langgraph components
Done
Building your first agent with lang graph
Done
Understanding State of Graph and creating StateGraph
Done
Tool Node
Done
Conditional Branching in graph
Done
Adding Memory to graph
Done
Building React Agent executor with Langgraph
Done
Parallel processing in langgraph
Done
Multi Agentic Application using LangGraph
Done
SubGraphs
Done
Building SQL Agent
Done
Creating a state graph with memory
Done
Creating a custom React Agent using Lang Graph
Done
Understanding parallel processing
Done
Creating a multi agentic application using Langgraph
Done
Creating a customer support bot using subgraphs
Done
Llama index
19
Understanding Llama Index
Done
Building blocks of Llama index
Done
Creating Indexes with Llama index
Done
Querying with Llama index
Done
Integrating with Lang Fuse
Done
Using Llama Index with Pinecone
Done
Customizing the retriever, synthesizer and post processors
Done
Using Connectors in LlamaHub
Done
Hypothetical Document Embeddings
Done
Llama Parse
Done
Develop an app for Converting text to SQL using NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine
Done
Using RouterQueryEngine
Done
Combining Text to SQL with semantic Search
Done
Understanding Property Graphs in detail
Done
Creating Property graphs with neo4j as graph store and chroma as vector store
Done
Creating a chat bot which Converts Natural Language to SQL Query
Done
Using Router QueryEngine
Done
Combining Text to SQL with Semantic Search
Done
Creating and querying a knowledgeGraph
Done
Crew AI
16
Understanding about AI Agents
Done
Creating your first agent using crew AI
Done
Creating multi agentic application using Crew AI
Done
Understanding agentic tools , memory and cooperation
Done
Multi agent collaboration
Done
Building a crew finally
Done
Achieving fault tolerance
Done
Asynch tasks
Done
Hierarchical collaboration
Done
Creating a single agent with single task
Done
Creating a single agent with single task and tools
Done
Creating a single agent with multiple tasks
Done
Creating custom tool
Done
Creating a crew with Asynch tasks
Done
Using hierarchical process delegation
Done
Creating a flow with crews
Done
GEN AI - 1st Assessment
The first test was MCQ type, focused on general knowledge check.
GEN AI 1st Scoresheet
Name
Full Marks
Score
Percentage
Name
Full Marks
Score
Percentage
Abhishek Panigrahi
40
32
80%
Advaidh Chandrabhanu
40
38
95%
Akshit Jain
40
38
95%
Anirudh Ganapathy P S
40
34
85%
Anubroto Ghose
40
32
80%
Anuvarshini S S
40
34
85%
Ayush U
40
36
90%
Balaharinath C
40
36
90%
Burlagadda Sai Nikhil
40
36
90%
Dhanush Duraipandian
40
32
80%
Anirudh G
40
32
80%
Gouri M P
40
32
80%
Gurram Venkata Saketh
40
36
90%
Harshit S
40
34
85%
Harunicshini Navarathiam
40
32
80%
Kavin Vimalnath
40
34
85%
Keerthana J
40
32
80%
Kesarikumaran S
40
38
95%
Madhulika Gopalakrishnan
40
36
90%
Oviya E
40
30
75%
Pranav Balaji
40
34
85%
Preti Sherine P
40
32
80%
Saamyukkth S
40
34
85%
Shashwata Samanta
40
34
85%
Shriram Kumar A N
40
34
85%
Shruthi B
40
36
90%
Sowmiya S
40
24
60%
Suryaa K S
40
34
85%
Swathi S
40
36
90%
Tamil Priya V
40
32
80%
Vasanth M
40
32
80%
Rishabh Prasad
40
38
95%
There are no rows in this table
GEN AI Final Test
The second and final was a complete practical test.
Exam file:
gen ai exam.pdf
71.8 kB
Students are expected to build a LangGraph-based Investment Research Assistant with three nodes:
Score Strategy:
Segment
Evaluation Criteria
Max Marks
Code Architecture
Proper LangGraph setup with nodes and flow
10
Web Search Node
Serper tool integration, relevance of results
10
Data Retrieval Node
Use of LlamaIndex for vector + SQL retrieval
15
Response Synthesis Node
Clarity, completeness, and quality of response
15
Functionality
Does the app run without error and give relevant outputs?
10
Accuracy of Responses
Investment recommendations grounded in retrieved data
10
Code Quality
Readability, comments, structure, use of typing
5
There are no rows in this table
Gen AI Final Test Scoresheet
Name
Code Architecture
Relevance of Results
Use of LlamaIndex for Vector + SQL Retrieval
Clarity, Completeness, and Quality of Response
App Execution and Output
Accuracy of Responses
Code Quality
Total Score
Percentage
Name
Code Architecture
Relevance of Results
Use of LlamaIndex for Vector + SQL Retrieval
Clarity, Completeness, and Quality of Response
App Execution and Output
Accuracy of Responses
Code Quality
Total Score
Percentage
Abhishek Panigrahi
9
9
14
13
9
9
4
67
89.33%
Advaidh Chandrabhanu
10
9
14
13
9
9
4
68
90.67%
Akshit Jain
10
9
14
13
9
9
4
68
90.67%
Anirudh Ganapathy P S
10
9
14
14
9
9
5
70
93.33%
Anubroto Ghose
10
9
14
14
9
9
4
69
92%
Anuvarshini S S
7
9
14
12
7
9
4
62
82.67%
Ayush U
10
9
14
12
9
9
4
67
89.33%
Balaharinath C
10
9
14
13
9
9
4
68
90.67%
Burlagadda Sai Nikhil
10
9
14
12
9
9
4
67
89.33%
Dhanush Duraipandian
10
9
14
13
9
9
4
68
90.67%
Anirudh G
10
9
14
13
9
9
4
68
90.67%
Gouri M P
10
9
14
13
9
9
4
68
90.67%
Gurram Venkata Saketh
9
9
14
12
9
9
4
66
88%
Harshit S
9
9
14
12
9
9
4
66
88%
Harunicshini Navarathiam
7
7
14
10
8
8
4
58
77.33%
Kavin Vimalnath
10
9
14
13
9
9
4
68
90.67%
Keerthana J
8
8
13
11
8
8
3
59
78.67%
Kesarikumaran S
10
9
14
13
9
9
5
69
92%
Madhulika Gopalakrishnan
6
7
12
11
8
6
3
53
70.67%
Oviya E
6
7
13
12
7
8
3
56
74.67%
Pranav Balaji
10
9
14
13
9
9
4
68
90.67%
Preti Sherine P
9
9
14
13
9
9
4
67
89.33%
Saamyukkth S
9
8
14
13
8
9
4
65
86.67%
Shashwata Samanta
10
9
14
13
9
9
4
68
90.67%
Shriram Kumar A N
10
9
14
13
9
9
5
69
92%
Shruthi B
8
9
14
12
8
9
4
64
85.33%
Sowmiya S
9
9
14
13
9
9
4
67
89.33%
Suryaa K S
10
9
14
13
9
9
4
68
90.67%
Swathi S
9
9
14
13
9
9
4
67
89.33%
Tamil Priya V
9
9
14
12
9
9
4
66
88%
Vasanth M
9
9
14
12
9
9
4
66
88%
Rishabh Prasad
10
9
14
13
9
9
5
69
92%
There are no rows in this table
GEN AI Project
Project Description
In this project, students have built a comprehensive telecom service assistant that integrates multiple
AI frameworks:
• LangGraph: Orchestration layer that coordinates the flow between different components
• CrewAI: Specialized customer support for billing and account queries
• AutoGen: Network troubleshooting with multiple specialized agents
• LangChain: Service recommendations using ReAct agents
• LlamaIndex: Knowledge retrieval from documentation
This project brings together all the concepts that was taught throughout the course.
Score Structure
Section
Score
Project Execution
50
Documentation
15
There are no rows in this table
Download the complete project document as below:
project.pdf
110.7 kB
Gen AI Project Scores
Name
Project Score
Documentation Scores
Total Scores
Percentage
Comments and Observation
Name
Project Score
Documentation Scores
Total Scores
Percentage
Comments and Observation
Abhishek Panigrahi
41
14
55
84.62%
Open
Advaidh Chandrabhanu
42
15
57
87.69%
Open
Akshit Jain
42
14
56
86.15%
Open
Anirudh Ganapathy P S
42
14
56
86.15%
Open
Anubroto Ghose
42
14
56
86.15%
Open
Anuvarshini S S
41
14
55
84.62%
Open
Ayush U
44
14
58
89.23%
Open
Balaharinath C
41
14
55
84.62%
Open
Burlagadda Sai Nikhil
39
13
52
80%
Open
Dhanush Duraipandian
41
14
55
84.62%
Open
Anirudh G
41
14
55
84.62%
Open
Gouri M P
41
14
55
84.62%
Open
Gurram Venkata Saketh
42
14
56
86.15%
Open
Harshit S
41
14
55
84.62%
Open
Harunicshini Navarathiam
41
13
54
83.08%
Open
Kavin Vimalnath
40
14
54
83.08%
Open
Keerthana J
42
14
56
86.15%
Open
Kesarikumaran S
42
14
56
86.15%
Open
Madhulika Gopalakrishnan
41
14
55
84.62%
Open
Oviya E
0%
Open
Pranav Balaji
42
14
56
86.15%
Open
Preti Sherine P
42
14
56
86.15%
Open
Saamyukkth S
39
13
52
80%
Open
Shashwata Samanta
41
14
55
84.62%
Open
Shriram Kumar A N
41
14
55
84.62%
Open
Shruthi B
41
14
55
84.62%
Open
Sowmiya S
41
14
55
84.62%
Open
Suryaa K S
41
14
55
84.62%
Open
Swathi S
41
14
55
84.62%
Open
Tamil Priya V
40
14
54
83.08%
Open
Vasanth M
42
15
57
87.69%
Open
Rishabh Prasad
42
14
56
86.15%
Open
There are no rows in this table
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ··· in the right corner or using a keyboard shortcut (
CtrlP
) instead.