This course uses Open AI GPT LLM, Google Gemini LLM, LangChain LLM Framework and Vector Databases and is intended to help you learn Langchain and build solid conceptual and hand-on proficiency to be able to develop RAG applications and projects. This course covers all the basics aspects to learn LLM and Frameworks like Agents, Tools, Chains, Retrievers, Output Parsers, Loaders and Splitters and so on in a very thorough manner with enough hands-on coding. It also takes a deep dive into concepts of Language Embeddings and Vector Databases to help you develop efficient semantic search and semantic similarity based RAG Applications. We will also cover multiple Prompt Engineering techniques that will make your RAG Applications more efficient.

Observability including Traces and Evaluations using LangSmith are also covered as part of this course.

List of Projects Included:

SQL RAG: Convert Natural Language to SQL Statements and apply on your MySQL Database to extract desired Results.

RAG with Conversational Memory: Create a simple RAG Application with Conversational Memory.

CV Analysis: Load a CV document and extract JSON based key information from the document.

Conversational HR Chatbot: Create a comprehensive HR Chatbot that is able to respond with answers from a HR Policy and Procedure database loaded into a Vector DB, and retain conversational memory like ChatGPT. Build UI using Streamlit.

Structured Data Analysis: Load structured data into a Pandas Dataframe and use a Few-Shot ReAct Agent to perform complex analytics.

Invoice Data Extractor: Upload multiple Invoices and extract key information into a CSV format. Build UI using Streamlit.

For each project, you will learn:

– The Business Problem

– What LLM and LangChain Components are used

– Analyze outcomes

– What are other similar use cases you can solve with a similar approach.

There are multiple Practice Assignments included in the Course that you can Practice upon.

Capstone Project:

You will also have the opportunity to complete a Capstone Project at the end of the course. This will help you learn Langchain better and develop RAG applications from scratch.