Online Course trending topic
Build Chat Applications with OpenAI and LangChain

Name: Build Chat Applications with OpenAI and LangChain Course
Price: 36 USD

with Hristina Hristova

Gain cutting-edge AI skills: Master the LangChain framework to build and deploy real-world AI applications

4.8

862 reviews on

Start for free

5,543 students already enrolled

Skill level:

Advanced

Duration:

7 hours

Lessons (4 hours)

Practice exams (3 hours)

Projects (8 hours)

CPE credits:

8

CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of professionals must earn to maintain their licenses and stay current with regulations and best practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's official website: www.nasbaregistry.org

Accredited

certificate

What you learn

Master LangChain to integrate applications with powerful LLMs.
Learn to connect to OpenAI’s language and embedding models.
Develop prompt engineering skills for optimal AI response.
Apply Retrieval‑Augmented Generation (RAG) with a knowledge base.
Leverage rare AI engineering skills to enhance career prospects.

Topics & tools

OpenAI ModelsLangChain FrameworkChat Prompt TemplatesFew-Shot PromptingEnvironment VariablesOpenAI API KeyConversation MemoryOutput ParsersRetrieval Augmented GenerationLangChain Expression LanguageAgent ToolingAILangchain

Your instructor

Hristina Hristova

Head of Data Content at 365 Data Science | Theoretical Physicist | Educator in Physics, Mathematics, and Programming

Track record

Bringing real-world expertise from leading global companies

Academic background

Master's degree, Theoretical and Mathematical Physics

Ask Hristina a question

Course overview

Accredited certificates

Course OVERVIEW

Description

CPE Credits: 8 Field of Study: Information Technology
Delivery Method: QAS Self Study

In this Build Chat Applications with OpenAI and LangChain course, we’ll unravel the LangChain framework that has gained massive popularity in AI. One of the components in this ever-growing ecosystem is the LangChain Python library, which we’ll use to leverage OpenAI’s potent language models and build the foundations for developing intriguing LLM-powered applications in our LangChain course. We’ll employ the power of the LangChain Expression Language to create stateful, context-aware, reasoning chatbots that remember past conversations, answer questions about unseen data, and take action to solve more complex problems. This course is part of our advanced deep learning courses, focusing on practical applications of AI.

Prerequisites

Python (version 3.8 or later), OpenAI API key, LangChain library, and a code editor or IDE (e.g., VS Code or Jupyter Notebook)
Intermediate Python skills are required.
Basic concepts in natural language processing (NLP) is helpful but not mandatory.

Advanced preparation

Introduction to Python

Curriculum

51 lessons 1 project 4 exams

1. Introduction to the Course

21 min

In this introductory section, we outline the agenda and prerequisites for the LangChain course. We provide an overview of what LangChain represents and how it’s been used in real-life use cases.

21 min

In this introductory section, we outline the agenda and prerequisites for the LangChain course. We provide an overview of what LangChain represents and how it’s been used in real-life use cases.

Introduction to the Course Free

Business Applications of LangChain Free

What Makes LangChain Powerful? Free

What Does the Course Cover? Free
2. Tokens, Models, and Prices

9 min

The smallest building block of a language model is the token. The collection of all unique tokens represents the vocabulary of a language model. In this section, we’ll discuss how a token is defined in the context of OpenAI’s language models and how tokens determine a model’s price. Additionally, we’ll spend a few minutes presenting the different models OpenAI offers. Understanding token management is vital for optimizing the use of OpenAI models.

9 min

The smallest building block of a language model is the token. The collection of all unique tokens represents the vocabulary of a language model. In this section, we’ll discuss how a token is defined in the context of OpenAI’s language models and how tokens determine a model’s price. Additionally, we’ll spend a few minutes presenting the different models OpenAI offers. Understanding token management is vital for optimizing the use of OpenAI models.

Tokens

Models and Prices
3. Setting Up the Environment

13 min

This section lays the groundwork for the course’s practical segment. We’ll cover creating a separate virtual environment with its own Python version and package set. Next, we’ll explain API key management and how to acquire an OpenAI API key—enabling our projects to use OpenAI’s expansive language models. Lastly, we’ll demonstrate setting this API key as an environment variable.

13 min

This section lays the groundwork for the course’s practical segment. We’ll cover creating a separate virtual environment with its own Python version and package set. Next, we’ll explain API key management and how to acquire an OpenAI API key—enabling our projects to use OpenAI’s expansive language models. Lastly, we’ll demonstrate setting this API key as an environment variable.

Setting Up a Custom Anaconda Environment for Jupyter Integration

Obtaining an OpenAI API Key

Setting the API Key as an Environment Variable
4. The OpenAI API

17 min

Before discussing the LangChain framework, we’ll first explore the OpenAI API basics—using various roles in prompts, setting the model temperature to adjust response randomness, limiting completion tokens, and streaming responses. This will later serve as a steppingstone towards understanding LangChain’s integration with OpenAI.

17 min

Before discussing the LangChain framework, we’ll first explore the OpenAI API basics—using various roles in prompts, setting the model temperature to adjust response randomness, limiting completion tokens, and streaming responses. This will later serve as a steppingstone towards understanding LangChain’s integration with OpenAI.

First Steps

System, User, and Assistant Roles

Creating a Sarcastic Chatbot

Temperature, Max Tokens, and Streaming
5. Model Inputs

38 min

We now enter the realm of LangChain, starting with model inputs. We’ll distinguish between prompts, prompt templates, and chat prompt templates and explore the few-shot prompting—a technique that enhances model responses by training on tailored question-answer examples. We’ll also introduce the invoke() method—essential for the upcoming LangChain Expression Language section.

38 min

We now enter the realm of LangChain, starting with model inputs. We’ll distinguish between prompts, prompt templates, and chat prompt templates and explore the few-shot prompting—a technique that enhances model responses by training on tailored question-answer examples. We’ll also introduce the invoke() method—essential for the upcoming LangChain Expression Language section.

The LangChain Framework

ChatOpenAI

System and Human Messages

AI Messages

Prompt Templates and Prompt Values

Chat Prompt Templates and Chat Prompt Values

Few-Shot Chat Message Prompt Templates

Practice exam
6. Output Parsers

8 min

As we’ve seen in previous sections, the output from a language model in LangChain comes as an AI message. This format, however, often doesn’t come in handy as we can’t pass it to other methods or applications. Therefore, LangChain offers what is known as output parsers—making it possible to parse an AI message to a different object: a string, a CSV, a DateTime object, or whatnot.

8 min

As we’ve seen in previous sections, the output from a language model in LangChain comes as an AI message. This format, however, often doesn’t come in handy as we can’t pass it to other methods or applications. Therefore, LangChain offers what is known as output parsers—making it possible to parse an AI message to a different object: a string, a CSV, a DateTime object, or whatnot.

String Output Parser

Comma-Separated List Output Parser

Datetime Output Parser
7. LangChain Expression Language (LCEL)

52 min

We now arrive at the crux of our practice journey—a discussion allowing us to build the most essential objects in LangChain: the chains. The foundational idea behind the LangChain Expression Language is that the output of one chain component serves as the input to the next one, making the chains modular objects that can be quickly composed and combined. Additionally, we’ll discuss Runnable objects—the type of objects that can be entered as chain components.

52 min

We now arrive at the crux of our practice journey—a discussion allowing us to build the most essential objects in LangChain: the chains. The foundational idea behind the LangChain Expression Language is that the output of one chain component serves as the input to the next one, making the chains modular objects that can be quickly composed and combined. Additionally, we’ll discuss Runnable objects—the type of objects that can be entered as chain components.

Piping a Prompt, Model, and an Output Parser

Batching

Streaming

The Runnable and RunnableSequence Classes

Piping Chains and the RunnablePassthrough Class

Graphing Runnables

RunnableParallel

Piping a RunnableParallel with Other Runnables

RunnableLambda

The @chain Decorator

Practice exam
8. Retrieval Augmented Generation (RAG)

86 min

In this course section, we address retrieval augmented generation—a technique that efficiently supplies context-specific information to a model. This process involves loading and segmenting personal data, embedding these segments, storing them in a vector store, and selectively retrieving and delivering only the relevant segments to the model. We’ll start with a theoretical discussion on this topic, then apply our knowledge to develop a basic 365 Q&A chatbot using transcripts from two 365 lectures.

86 min

In this course section, we address retrieval augmented generation—a technique that efficiently supplies context-specific information to a model. This process involves loading and segmenting personal data, embedding these segments, storing them in a vector store, and selectively retrieving and delivering only the relevant segments to the model. We’ll start with a theoretical discussion on this topic, then apply our knowledge to develop a basic 365 Q&A chatbot using transcripts from two 365 lectures.

How to Integrate Custom Data into an LLM

Introduction to RAG

Introduction to Document Loading and Splitting

Introduction to Document Embedding

Introduction to Document Storing, Retrieval, and Generation

Indexing: Document Loading with PyPDFLoader

Indexing: Document Loading with Docx2txtLoader

Indexing: Document Splitting with Character Text Splitter (Theory)

Indexing: Document Splitting with Character Text Splitter (Code Along)

Indexing: Document Splitting with Markdown Header Text Splitter

Indexing: Text Embedding with OpenAI

Indexing: Creating a Chroma Vector Store

Indexing: Inspecting and Managing Documents in a Vector Store

Retrieval: Similarity Search

Retrieval: Maximal Marginal Relevance Search

Retrieval: Vector Store-Backed Retriever

Generation: Stuffing Documents

Generation: Generating a Response

Practice exam
9. Course project and exam

570 min

570 min

Create a Q&A Chatbot with LangChain Project

Course exam

Free lessons

1.1 Introduction to the Course

5 min

1.2 Business Applications of LangChain

5 min

1.3 What Makes LangChain Powerful?

5 min

1.4 What Does the Course Cover?

6 min

2.1 Tokens

6 min

2.2 Models and Prices

3 min

Start for free

365 Data Science was absolutely essential in getting me where I am today. The curriculum gave me a solid foundation in data analysis, data science, machine learning, and deep learning—both theory and practice. The structured approach and hands-on projects made complex topics easy to understand and apply. Earning certificates boosted my confidence and LinkedIn profile, helping me stand out in interviews. That momentum led me to internships and, ultimately, to my current role as an AI Engineer.

Mohamed Sherif E.

Before 365: Data Science Intern

After 365: AI Engineer at Quality Standards | Information Technology – QSIT

See all reviews

9 in 10

people walk away career-ready

with practical data and AI skills.

With a background in economics and over five years of experience in project management across private and international organizations—including a European Union project in Sudan—I sought new opportunities after relocating to the UAE. Transitioning into data analytics, I began my journey with the 365 Data Science platform, which provided an outstanding and well-structured learning experience. The platform's practical approach and high-quality courses helped me progress from a beginner to a proficient data analyst.

Rabab A.

Before 365: Project Coordinator | SOFRECO

After 365: Freelance Data Analyst

See all reviews

9 in 10

of our graduates landed a new AI & data job

after enrollment

After more than 200 days of consistent learning, I’ve completed over 30 courses, earned 14 certifications, and reached level 10 on 365 Data Science. The gamified XP system keeps me motivated, while expert-led, real-world-focused content has built my skills through hands-on projects and downloadable resources. The personalized learning path has guided me toward my final career path exam with confidence. For anyone serious about building a data career, 365 makes learning engaging, practical, and rewarding.