Skip to content

97310 96750
support@promptlyai.in

Home
Courses
About Us
Gallery
Testimonial
Blog
Contact

Home
Courses
About Us
Gallery
Testimonial
Blog
Contact

Agentic AI : Knowledge Systems

Promptly AI - Courses - Agentic AI : Knowledge Systems

Agentic AI : Knowledge Systems

Curriculum

46 Sections
274 Lessons
2 Weeks

Expand all sectionsCollapse all sections

🧠 Introduction to LLMs
1
- 1.1
  Fruits analogy to explain LLM basics
🛠️ Setup
2
- 2.1
  Accessing LLMs via standard API
- 2.2
  Connecting with Google Vertex AI
💬 Basic Interactions with LLMs
2
- 3.1
  Crafting effective input prompts
- 3.2
  Analyzing basic LLM output
🐍 Python Essentials
9
- 4.1
  Working with strings
- 4.2
  Using dictionaries
- 4.3
  Writing simple prompts
- 4.4
  Handling file inputs with prompts
- 4.5
  Chunking large content
- 4.6
  Reading content from PDFs
- 4.7
  Reading PDFs from Google Cloud
- 4.8
  Listing GitHub blobs using API
- 4.9
  Understanding exception handling
🧩 Model Selection
2
- 5.1
  Choosing the right LLM for your use case
- 5.2
  Evaluating model performance and cost
✍️ Text Generation
11
- 6.1
  Basic Hello World with LLMs
- 6.2
  Dissecting LLM response structures
- 6.3
  Managing a chat session
- 6.4
  Switching between multiple models
- 6.5
  Generating multiple content types
- 6.6
  Streaming responses from LLMs
- 6.7
  Simple textual generation
- 6.8
  Understanding tokenization
- 6.9
  To-do ideas for further generation
- 6.10
  Using dataclasses in LLM output
- 6.11
  Common utility functions for generation
📄 PDF Processing
8
- 7.1
  Extracting text from PDFs
- 7.2
  Generating Q&A from PDFs
- 7.3
  Finding keywords in documents
- 7.4
  Producing structured outputs
- 7.5
  Translating PDF content
- 7.6
  Auto-generating quizzes from PDFs
- 7.7
  Creating flashcards from documents
- 7.8
  Building a chatbot over a PDF
🖼️ Image Processing
9
- 8.1
  Image processing basics
- 8.2
  Counting people in an image
- 8.3
  Comparing two images
- 8.4
  Running inference on images
- 8.5
  Identifying book titles
- 8.6
  Book title recognition with finetuned model (v1)
- 8.7
  Book title recognition with finetuned model (v2)
- 8.8
  Object identification in images
- 8.9
  Utility and scrap scripts for image processing
🔊 Audio Processing
2
- 9.1
  Transcribing audio to text
- 9.2
  Audio classification with LLMs
🎥 Video Processing
2
- 10.1
  Extracting and analyzing video frames
- 10.2
  Summarizing video content using LLMs
🧠 Multimodal Processing
2
- 11.1
  Combining image and text inputs
- 11.2
  Designing workflows across modalities
💡 Understanding Prompts
2
- 12.1
  Types of prompts and their structures
- 12.2
  Best practices for crafting LLM prompts
⚠️ Limitations of LLMs
2
- 13.1
  When LLMs fail and why
- 13.2
  Handling hallucination and bias
🔍 Understanding Embeddings
6
- 14.1
  Understanding point-based embeddings
- 14.2
  String to vector conversions
- 14.3
  Semantic similarity using strings
- 14.4
  Comparing distance and similarity
- 14.5
  RAG fundamentals and architecture overview
- 14.6
  RAG vs fine-tuning vs prompt engineering
🧠 Embeddings & RAG Pipeline
28
- 15.1
  Listing files for embeddings
- 15.2
  Fetching GitHub files
- 15.3
  Embedding PDFs from GitHub
- 15.4
  Understanding chunk overlap
- 15.5
  Converting strings to embeddings
- 15.6
  Embedding full PDF documents
- 15.7
  Embedding individual PDF pages
- 15.8
  Chunking and embedding content
- 15.9
  Creating and storing in vectorDB
- 15.10
  CRUD operations with ChromaDB
- 15.11
  Text-to-vector database integration
- 15.12
  Producer pattern for PDF embeddings
- 15.13
  Reading embedded records
- 15.14
  Running simple vector queries
- 15.15
  Querying with multiple questions
- 15.16
  Batch embedding of multiple PDFs
- 15.17
  Searching with context using vectorDB
- 15.18
  Building end-to-end RAG pipeline
- 15.19
  Combining retrieval with LLM generation
- 15.20
  Response synthesis from multiple chunks
- 15.21
  Handling user queries in RAG workflow
- 15.22
  RAG with conversation history
- 15.23
  Multi-turn context management
- 15.24
  Hybrid search (semantic + keyword)
- 15.25
  Re-ranking retrieved documents
- 15.26
  Query expansion and rewriting
- 15.27
  Multi-query retrieval strategies
- 15.28
  Metadata filtering during retrieval
🧰 Embedding & RAG Utilities
7
- 16.1
  Helper functions for ChromaDB
- 16.2
  Data dumping tools
- 16.3
  Embedding utility methods
- 16.4
  Setup utilities for vector operations
- 16.5
  RAG response formatting utilities
- 16.6
  Context window optimization helpers
- 16.7
  RAG caching and performance utilities
📏 Context Limitations with VectorDBs & RAG
4
- 17.1
  Chunk overlap and context window design
- 17.2
  Understanding embedding context leakage
- 17.3
  Managing context in RAG conversations
- 17.4
  Optimizing retrieval for long conversations
🔧 Function Tools Basics
6
- 18.1
  Defining a regular is-even function
- 18.2
  Exploring limitations of is-even
- 18.3
  Calling is-even with LLM
- 18.4
  Analyzing edge cases in is-even
- 18.5
  Basic usage of function tools
- 18.6
  Using LLM function tools in prompts
🔧 Function Tools
7
- 19.1
  Enhancing function tools with power
- 19.2
  Adding numbers using LLM tools
- 19.3
  Simple functional workflows
- 19.4
  Defining multiple tools together
- 19.5
  Calling multiple tools in sequence
- 19.6
  Follow-up prompt generation using functions
- 19.7
  Building iterative tool call patterns
🔬 Function Tools Advanced
8
- 20.1
  Validating functions
- 20.2
  Chat-driven function validation
- 20.3
  Matching valid functions
- 20.4
  Creating synthetic LLM responses
- 20.5
  Handling invalid function matches
- 20.6
  Using multiple functions together
- 20.7
  Advanced multi-function workflows
- 20.8
  Geo-location using tool-based prompts
🔢 Function Tool Types
7
- 21.1
  Single parameter function patterns
- 21.2
  Handling multiple parameters
- 21.3
  Passing list parameters to tools
- 21.4
  Auto mode in function calling
- 21.5
  Using “any” mode for flexible arguments
- 21.6
  Fallback to “none” mode when required
- 21.7
  Building currency exchange tools
🤖 Agent: Act - Observe - Reason
7
- 22.1
  Creating a basic agent
- 22.2
  Improving agent flow with versioning
- 22.3
  Looping agent decisions
- 22.4
  Full agent logic with memory
- 22.5
  Distribution bonus for agents
- 22.6
  Bonus prompts for agent logic
- 22.7
  Temporary experiments
🔗 LangChain Basics
8
- 23.1
  Basic LangChain hello world
- 23.2
  Invoking a LangChain pipeline
- 23.3
  Using the Runnable interface
- 23.4
  Applying output parsers
- 23.5
  Using prompt templates
- 23.6
  Maintaining memory in chains
- 23.7
  Providing additional context
- 23.8
  Integrating embeddings
🔁 LangGraph Basics
7
- 24.1
  Is-even check with LangGraph
- 24.2
  Comparing multiple LangGraph flows
- 24.3
  Single-node LangGraph agent
- 24.4
  Two-node LangGraph workflow
- 24.5
  Three-node LangGraph flow
- 24.6
  If-else branching logic in LangGraph
- 24.7
  LangGraph utility functions
🧪 LangGraph Explore
12
- 25.1
  Conditional branching with pass/fail
- 25.2
  Number classifier with branching
- 25.3
  E-commerce order flow example 1
- 25.4
  E-commerce order flow example 2
- 25.5
  Intent-based chatbot using LangGraph
- 25.6
  Retry logic and looping patterns
- 25.7
  Loan eligibility decision logic
- 25.8
  Linear fallback decision-making
- 25.9
  Handling dynamic input in LangGraph
- 25.10
  Using random choice nodes
- 25.11
  Selecting tools in workflows
- 25.12
  LangGraph utility functions
📨 LangGraph Messages
8
- 26.1
  Understanding LangGraph message types
- 26.2
  Creating message chains
- 26.3
  Maintaining string-based state
- 26.4
  Managing custom message state
- 26.5
  Using LLM with message states
- 26.6
  Basic tool calls with messages
- 26.7
  Advanced tool call workflows
- 26.8
  Message utility helpers
🤝 LangGraph with LLMs
5
- 27.1
  Integrating LLMs with LangGraph
- 27.2
  Conditional branching with LLM
- 27.3
  Building a LangGraph agent
- 27.4
  Streaming response agent logic
- 27.5
  Shared LangGraph utilities
🛍️ Ordering Agent
14
- 28.1
  Getting item IDs from prompts
- 28.2
  Mapping item names to IDs
- 28.3
  Choosing quantities for products
- 28.4
  Generating quotes (version 1)
- 28.5
  Generating quotes (version 2)
- 28.6
  Placing orders from quotes
- 28.7
  Handling quantity limits
- 28.8
  Placing multi-vendor orders
- 28.9
  Enhanced version of multi-vendor orders
- 28.10
  Handling oversized orders
- 28.11
  Amazon API integrations
- 28.12
  Flipkart API logic
- 28.13
  Shared LangGraph utilities
- 28.14
  Sapna API integrations
🚚 Delivery Agent
6
- 29.1
  Parsing and managing addresses
- 29.2
  Amazon delivery API
- 29.3
  Flipkart delivery flow
- 29.4
  Building a delivery agent
- 29.5
  Shared delivery utilities
- 29.6
  Sapna delivery API logic
🧠 LangGraph Custom State
4
- 30.1
  Building a custom state system
- 30.2
  Summarizing agent state
- 30.3
  Initializing state values
- 30.4
  Utility functions for custom states
🏗️ Agent Architecture
3
- 31.1
  Shared state schemas
- 31.2
  Supervisor with synthetic graph
- 31.3
  Supporting LangGraph utilities
🔀 Multi-Agent Data Sharing
4
- 32.1
  Agent A implementation
- 32.2
  Agent B logic
- 32.3
  Central orchestrator design
- 32.4
  Main application logic
🤖 Order Agent (Synthetic)
9
- 33.1
  Creating agent graph
- 33.2
  Extracting vendor details
- 33.3
  Extracting full order information
- 33.4
  Vendor communication module
- 33.5
  Single vendor contact
- 33.6
  Contacting all vendors
- 33.7
  Comparing vendor responses
- 33.8
  Final order agent logic
- 33.9
  LangGraph utility support
🧠 Single Agent
4
- 34.1
  Common APIs for order agents
- 34.2
  Shared LangGraph utilities
- 34.3
  Managing message state
- 34.4
  Sapna order processing logic
🧠 Multiple Agents
5
- 35.1
  Amazon agent implementation
- 35.2
  Common API usage
- 35.3
  Flipkart agent logic
- 35.4
  Sapna-specific agent flow
- 35.5
  Message state and LangGraph logic
🧠 Multiple Agents Orchestrator
7
- 36.1
  Defining agent state
- 36.2
  Amazon order agent
- 36.3
  Orchestrator configurations
- 36.4
  Flipkart agent
- 36.5
  Main orchestrator controller
- 36.6
  Message and orchestration utilities
- 36.7
  Amazon, Flipkart, and Sapna integrations
🧠 Agent Memory
3
- 37.1
  Purpose of agent memory
- 37.2
  Agent memory implementation
- 37.3
  LangGraph memory utilities
🧪 MCP Helloworld
8
- 38.1
  MCP server interaction basics
- 38.2
  MCP client interaction
- 38.3
  Debugging server logic
- 38.4
  Debugging client logic
- 38.5
  Standard I/O handling for server
- 38.6
  Standard I/O handling for client
- 38.7
  Extended server logic
- 38.8
  Extended client behavior
🧪 MCP LLM LangGraph
6
- 39.1
  Server logic with LangGraph
- 39.2
  Client logic with LangGraph
- 39.3
  LLM pipeline in MCP
- 39.4
  LangGraph and LLM combined
- 39.5
  Multi-server orchestration
- 39.6
  Multi-server with LLM
📦 MCP Sapna
5
- 40.1
  Sapna MCP configuration
- 40.2
  Sapna API integration
- 40.3
  Sapna MCP server
- 40.4
  System prompt definition for Sapna
- 40.5
  Setup and test scripts
📦 MCP Flipkart
3
- 41.1
  Flipkart MCP API
- 41.2
  Flipkart MCP server logic
- 41.3
  System prompts for Flipkart
📦 MCP Amazon
3
- 42.1
  Amazon API integration
- 42.2
  Amazon MCP server logic
- 42.3
  Amazon system prompts
🧠 MCPC Orchestrator Agents
7
- 43.1
  Managing agent states
- 43.2
  Amazon orchestration
- 43.3
  Shared configuration
- 43.4
  Flipkart orchestration
- 43.5
  LangGraph utilities
- 43.6
  Orchestration control
- 43.7
  Vendor APIs for orchestrator
🧪 Google ADK
2
- 44.1
  Hello world agent with ADK
- 44.2
  Math agent built using ADK
🌐 Streamlit
3
- 45.1
  REST server for AI backend
- 45.2
  Viewing conversation history
- 45.3
  Main Streamlit interface
🎛️ Prompt Tuning Parameters - Top PK
4
- 46.1
  Adjusting temperature, top-p, and other settings
- 46.2
  Balancing creativity and accuracy
- 46.3
  Prompt example 1
- 46.4
  Prompt example 2

This content is protected, please login and enroll in the course to view this content!

Accessing LLMs via standard API

PromptlyAI

Providing industry-leading IT training and upskilling programs to help professionals advance their careers and organizations build stronger teams.

Featured Links

About Us
Courses
Testimonials
Contact
Term Conditions
Blog
FAQ’s

Information

Location :
PromptlyAI, 77/1, Marathahalli, Bengaluru - 560103
Call Us :
97310 96750
Mail Us :
support@promptlyai.in

Location

© Copyright PromptlyAI 2025. Designed and Developed by StartupIcons

×

You must be logged in before using WishList. To login click here

Join Demo

Modal title

Main Content