Master Agentic AI with LangGraph, Streamlit and OpenAI
Agentic AI has become more disruptive than Generative AI these days.Organisations are rushing to transform their business models to implement agentic ai applications to unlock business value to stay ahead of the curve. As organisations transform their readily available workflows to leverage agentic AI they will come across new business workflows that might exponentially add value to their revenue streams. So agentic ai has already impacted profoundly across sectors and verticles. As technology and solution providers we have to stay ahead of the curve on disruptive modern technologies such as in order to be relavant to our customers and guide them in the Gen Ai and Agentic AI adoption journey.LangGraph, LangChain, Streamlit, OpenAI, Python is an ideal blend of technologies to implement most of the agentic ai business work flows robust, reliable and secure manner in highly agile product and development environments.Features such as data streaming, LLM tool calling, LLM structured output, short term context windows, long term stateful knowledge graphs, Time Travel etc are invaluable features to implement highly scalable, fast, robust, reliable and trustworthy agentic applications. Human in the loop is vital when agentic ai is infused into mission critical workflows to safeguard data layer.LangGraph interrupts, event systems and state preservation mechanism foundationally enable LangGraph to be equipped with reliable human in the loop implementations.Primary technologies used in this course are as below.
Read more
Agentic AI has become more disruptive than Generative AI these days.Organisations are rushing to transform their business models to implement agentic ai applications to unlock business value to stay ahead of the curve. As organisations transform their readily available workflows to leverage agentic AI they will come across new business workflows that might exponentially add value to their revenue streams. So agentic ai has already impacted profoundly across sectors and verticles. As technology and solution providers we have to stay ahead of the curve on disruptive modern technologies such as in order to be relavant to our customers and guide them in the Gen Ai and Agentic AI adoption journey.LangGraph, LangChain, Streamlit, OpenAI, Python is an ideal blend of technologies to implement most of the agentic ai business work flows robust, reliable and secure manner in highly agile product and development environments.Features such as data streaming, LLM tool calling, LLM structured output, short term context windows, long term stateful knowledge graphs, Time Travel etc are invaluable features to implement highly scalable, fast, robust, reliable and trustworthy agentic applications. Human in the loop is vital when agentic ai is infused into mission critical workflows to safeguard data layer.LangGraph interrupts, event systems and state preservation mechanism foundationally enable LangGraph to be equipped with reliable human in the loop implementations.Primary technologies used in this course are as below.
Agentic AI has become more disruptive than Generative AI these days.Organisations are rushing to transform their business models to implement agentic ai applications to unlock business value to stay ahead of the curve. As organisations transform their readily available workflows to leverage agentic AI they will come across new business workflows that might exponentially add value to their revenue streams. So agentic ai has already impacted profoundly across sectors and verticles. As technology and solution providers we have to stay ahead of the curve on disruptive modern technologies such as in order to be relavant to our customers and guide them in the Gen Ai and Agentic AI adoption journey.LangGraph, LangChain, Streamlit, OpenAI, Python is an ideal blend of technologies to implement most of the agentic ai business work flows robust, reliable and secure manner in highly agile product and development environments.Features such as data streaming, LLM tool calling, LLM structured output, short term context windows, long term stateful knowledge graphs, Time Travel etc are invaluable features to implement highly scalable, fast, robust, reliable and trustworthy agentic applications. Human in the loop is vital when agentic ai is infused into mission critical workflows to safeguard data layer.LangGraph interrupts, event systems and state preservation mechanism foundationally enable LangGraph to be equipped with reliable human in the loop implementations.Primary technologies used in this course are as below.
Agentic AI
Generative AI
LangGraph
LangChain
Streamlit
Python
OpenAI
VsCode
What's inside
Learning objectives
- Understand agentic ai workflows and systems
- Implement agentic ai systems with langgraph, openai and streamlit
- Automate complex business workflows with agentic ai
- Human in the loop interactions with mission critical work flows
- Langgraph event streams
- Llm tool calling workflow agents with structured output
- Agentic design patterns
- Implement fast, robust and reliable streaming ai applications
- Understand agentic ai workflows and systems
- Implement agentic ai systems with langgraph, openai and streamlit
- Automate complex business workflows with agentic ai
- Human in the loop interactions with mission critical work flows
- Langgraph event streams
- Llm tool calling workflow agents with structured output
- Agentic design patterns
- Implement fast, robust and reliable streaming ai applications
Syllabus
Introduction to Agentic AI and setup environment
Highlevel introduction to agentic ai and course
Detailed explanation agentic ai and business model
Read more
Syllabus
Highlevel introduction to agentic ai and course
Detailed explanation agentic ai and business model
Required softwares and tools for the course
Detailed guidence on setting up the vscode environment with Python
Design of the single node agent with langgraph
Langgraph implementation of a single node graph
Langraph event streams
Streamlit ui implementation
Enable debugging in Python with Streamlit
Testing the Streamlit Langgraph chatbot end to end
Designing multi agent systems with orchestrator design pattern
Define multi agent systems with LangGraph
Define general edges and conditional edges in a graph
Execute a multiagent application through Streamlit chat interface
Understand Langgraph execution flow through code debugger interaction
Design human in the loop interactions with interupts and deeply nested work flows
Impelement data model with Pydantic and Data Dictionaries for domain objects and structured output
Implement deeply nested langgraph branches with human in the loop
Human in the loop, Sentiment analysis with Structured output
Event handling with streams and interrupts in LangGraph
Handle human the loop UI interactions with Streamlit
Execute multi agent and human in the loop Streamlit and LangGraph based application
Code walk through on multiagent,orchestration,human in the loop, interrupts,event streams based graph structure.
Save this course
Save
Activities
Career center
Reading list
Save
Save
Save
Save
Share
Similar courses
OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.
Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.
Find this site helpful? Tell a friend about us.
We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.
Your purchases help us maintain our catalog and keep our servers humming without ads.
Thank you for supporting OpenCourser.
