We may earn an affiliate commission when you visit our partners.
Alfredo Deza
In this 2-hour project-based course, you will learn how to import data into Pandas, create embeddings with SentenceTransformers, and build a retrieval augmented generation (RAG) system with your data, Qdrant, and an LLM like Llamafile or OpenAI. This hands-on course will teach you to build an end-to-end RAG system with your own data using open source tools for a powerful generative AI application.
Register for this course and see more details by visiting:
OpenCourser.com/course/p2ncsx/introduction
What's inside
Syllabus
Project Overview
In this project you learn how to implement RAG
Good to know
Good to know
Know what's good ,
what to watch for , and
possible dealbreakers
Build an end-to-end Retrieval Augmented Generation (RAG) system with your own data
Students learn a hands-on approach to using open source tools for a powerful generative AI application
Save this course
Save Introduction to Retrieval Augmented Generation (RAG) to your list so you can find it easily later:
Save
Save
Activities
Be better prepared
before
your course. Deepen your understanding
during
and
after
it. Supplement your coursework and achieve mastery of the topics covered
in Introduction to Retrieval Augmented Generation (RAG) with these
activities:
Review the fundamentals of natural language processing (NLP)
Show steps
Understand the concepts of NLP to prepare for the course's in-depth exploration of RAG systems.
Browse courses on
NLP
Show steps
-
Review online materials on NLP concepts
-
Go through tutorials on basic NLP tasks like text classification and sentiment analysis
Explore SentenceTransformers library
Show steps
Gain familiarity with the SentenceTransformers library, which will be used to create embeddings in the course.
Show steps
-
Follow tutorials on installing and using SentenceTransformers
-
Experiment with different pre-trained models for sentence embeddings
-
Create custom sentence embeddings for a small dataset
Practice using Qdrant for vector similarity search
Show steps
Gain proficiency in using Qdrant, a vector database essential for building RAG systems.
Browse courses on
Qdrant
Show steps
-
Create a Qdrant instance
-
Insert and search vectors in Qdrant
-
Optimize queries for better performance
Four other activities
Expand to see all activities and additional details
Show all seven activities
Build a simple text embedding model
Show steps
Apply the concepts learned in the course by building a basic text embedding model from scratch.
Browse courses on
Embeddings
Show steps
-
Choose a pre-trained word embedding model
-
Develop a simple neural network architecture for text embedding
-
Train the model on a small dataset
-
Evaluate the model's performance
Attend a peer discussion session on RAG applications
Show steps
Engage with peers to discuss and learn about practical applications of RAG systems.
Browse courses on
RAG
Show steps
-
Join a peer discussion group
-
Share knowledge and experiences
-
Provide and receive feedback
Contribute to an open-source RAG project
Show steps
Immerse in the practical aspects of RAG development by collaborating on an open-source project.
Browse courses on
RAG
Show steps
-
Identify an open-source RAG project
-
Familiarize with the project's codebase
-
Contribute bug fixes or improvements
Develop a complete RAG system for a specific domain
Show steps
Integrate all the concepts covered in the course by building a comprehensive RAG system for a real-world application.
Browse courses on
RAG
Show steps
-
Define the problem statement and domain
-
Collect and prepare data
-
Create embeddings using SentenceTransformers
-
Build a retrieval model using Qdrant
-
Develop a generative model using an LLM like Llamafile or OpenAI
-
Evaluate the system's performance
Review the fundamentals of natural language processing (NLP)
Show steps
Understand the concepts of NLP to prepare for the course's in-depth exploration of RAG systems.
Browse courses on
NLP
Show steps
Show steps
Show steps
- Review online materials on NLP concepts
- Go through tutorials on basic NLP tasks like text classification and sentiment analysis
Explore SentenceTransformers library
Show steps
Gain familiarity with the SentenceTransformers library, which will be used to create embeddings in the course.
Show steps
Show steps
Show steps
- Follow tutorials on installing and using SentenceTransformers
- Experiment with different pre-trained models for sentence embeddings
- Create custom sentence embeddings for a small dataset
Practice using Qdrant for vector similarity search
Show steps
Gain proficiency in using Qdrant, a vector database essential for building RAG systems.
Browse courses on
Qdrant
Show steps
Show steps
Show steps
- Create a Qdrant instance
- Insert and search vectors in Qdrant
- Optimize queries for better performance
Four other activities
Expand to see all activities and additional details
Show all seven activities
Build a simple text embedding model
Show steps
Apply the concepts learned in the course by building a basic text embedding model from scratch.
Browse courses on
Embeddings
Show steps
Show steps
Show steps
- Choose a pre-trained word embedding model
- Develop a simple neural network architecture for text embedding
- Train the model on a small dataset
- Evaluate the model's performance
Attend a peer discussion session on RAG applications
Show steps
Engage with peers to discuss and learn about practical applications of RAG systems.
Browse courses on
RAG
Show steps
Show steps
Show steps
- Join a peer discussion group
- Share knowledge and experiences
- Provide and receive feedback
Contribute to an open-source RAG project
Show steps
Immerse in the practical aspects of RAG development by collaborating on an open-source project.
Browse courses on
RAG
Show steps
Show steps
Show steps
- Identify an open-source RAG project
- Familiarize with the project's codebase
- Contribute bug fixes or improvements
Develop a complete RAG system for a specific domain
Show steps
Integrate all the concepts covered in the course by building a comprehensive RAG system for a real-world application.
Browse courses on
RAG
Show steps
Show steps
Show steps
- Define the problem statement and domain
- Collect and prepare data
- Create embeddings using SentenceTransformers
- Build a retrieval model using Qdrant
- Develop a generative model using an LLM like Llamafile or OpenAI
- Evaluate the system's performance
Career center
Learners who complete Introduction to Retrieval Augmented Generation (RAG) will develop knowledge and skills
that may be useful to these careers:
Data Scientist
Data Scientist
Data Scientists combine programming ability with a deep understanding of data analysis to extract meaningful insights from data. Graduates with experience with embeddings, sentence transformers, and generative AI models may be especially well-suited to this role. This course gives an overview of how to use these tools and a hands-on implementation to build a retrieval augmented generation (RAG) system.
Machine Learning Engineer
Machine Learning Engineer
Machine Learning Engineers develop and deploy machine learning models. Graduates with experience in building RAG systems will find the material on building embeddings, especially relevant. This course will also help build a foundation for working with large datasets and training models.
Natural Language Processing Engineer
Natural Language Processing Engineer
Natural Language Processing Engineers develop and deploy models that understand and generate human language. Graduates with experience with sentence transformers and generative AI models may be especially well-suited to this role. This course will help build a foundation in these areas and provide hands-on experience building a RAG system.
Data Analyst
Data Analyst
Data Analysts collect, clean, and analyze data to identify trends and patterns. This course will provide a solid foundation in data analysis techniques, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the tech industry, especially for those interested in building data-driven products.
Software Engineer
Software Engineer
Software Engineers design, develop, and maintain software systems. This course will provide a foundation in software engineering principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is in high demand across a variety of industries.
Quantitative Analyst
Quantitative Analyst
Quantitative Analysts use mathematical and statistical models to analyze financial data. This course will provide a foundation in quantitative analysis techniques, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the financial industry, especially for those interested in building data-driven trading strategies.
Product Manager
Product Manager
Product Managers define and manage the development of software products. This course will provide a foundation in product management principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is in high demand across a variety of industries.
Business Analyst
Business Analyst
Business Analysts analyze business processes and systems to identify opportunities for improvement. This course will provide a foundation in business analysis techniques, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the tech industry, especially for those interested in building data-driven products.
Project Manager
Project Manager
Project Managers plan and execute projects to achieve specific goals. This course will provide a foundation in project management principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is in high demand across a variety of industries.
Technical Writer
Technical Writer
Technical Writers create documentation and other materials to explain technical concepts. This course will provide a foundation in technical writing principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the tech industry, especially for those interested in building data-driven products.
Information Architect
Information Architect
Information Architects design and organize websites and other digital products. This course will provide a foundation in information architecture principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the tech industry, especially for those interested in building data-driven products.
Data Engineer
Data Engineer
Data Engineers design and build data pipelines to collect, clean, and store data. This course will provide a foundation in data engineering principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the tech industry, especially for those interested in building data-driven products.
Database Administrator
Database Administrator
Database Administrators manage and maintain databases. This course will provide a foundation in database administration principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models. This combination of skills is increasingly valuable in the tech industry, especially for those interested in building data-driven products.
Systems Engineer
Systems Engineer
Systems Engineers design and build computer systems. This course may be useful for Systems Engineers interested in building data-driven systems. The course will provide a foundation in systems engineering principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models.
Network Engineer
Network Engineer
Network Engineers design and build computer networks. This course may be useful for Network Engineers interested in building data-driven networks. The course will provide a foundation in network engineering principles and practices, as well as experience with embeddings, sentence transformers, and generative AI models.
For more career information including salaries, visit:
OpenCourser.com/course/p2ncsx/introduction
Reading list
We've selected six books
that we think will supplement your
learning. Use these to
develop background knowledge, enrich your coursework, and gain a
deeper understanding of the topics covered in
Introduction to Retrieval Augmented Generation (RAG).
This textbook provides a comprehensive introduction to deep learning techniques for NLP. It covers neural network architectures, training methods, and evaluation metrics specific to NLP tasks. It valuable resource for students and researchers interested in building deep learning models for NLP.
This website provides comprehensive information about OpenAI, its mission, and its research and development efforts. It also includes documentation for OpenAI's various products and services, including its language models.
Practical guide to using Python for data analysis. It covers essential topics such as data manipulation, visualization, and machine learning. It useful resource for students and practitioners who need to work with data in Python.
A practical guide to using TensorFlow for deep learning, including a section on natural language processing.
A comprehensive introduction to deep learning, providing a foundation for understanding the techniques used in RAG models.
A comprehensive overview of natural language processing using Python, providing a foundation for understanding the techniques used in RAG models.
For more information about how these books relate to this course, visit:
OpenCourser.com/course/p2ncsx/introduction
Share
Similar courses
Here are nine courses similar to
Introduction to Retrieval Augmented Generation (RAG).
Building Multimodal Search and RAG
OpenCourser.com/course/ntocez/building
Building Multimodal Search and RAG
Most relevant
Getting Started with Mistral
OpenCourser.com/course/zwc6sb/getting
Getting Started with Mistral
JavaScript RAG Web Apps with LlamaIndex
OpenCourser.com/course/6k2jo6/javascript
JavaScript RAG Web Apps with LlamaIndex
Building Applications with Vector Databases
OpenCourser.com/course/k7wk65/building
Building Applications with Vector Databases
Gen AI - RAG Application Development using LangChain
OpenCourser.com/course/kbrxwl/gen
Gen AI - RAG Application Development using LangChain
Building Agentic RAG with LlamaIndex
OpenCourser.com/course/2k8tta/building
Building Agentic RAG with LlamaIndex
Haystack - Build customizable LLM pipelines with AI Tools
OpenCourser.com/course/7daf7p/haystack
Haystack - Build customizable LLM pipelines with AI Tools
Preprocessing Unstructured Data for LLM Applications
OpenCourser.com/course/absfr4/preprocessing
Preprocessing Unstructured Data for LLM Applications
Vector Databases: from Embeddings to Applications
OpenCourser.com/course/r98yx2/vector
Vector Databases: from Embeddings to Applications
Effort
2 hours
Level
Intermediate
Via
Coursera
Institution
Duke University
Instructor
Alfredo Deza
Language
English
Good to know
Build an end-to-end Retrieval Augmented Generation (RAG) system with your own data
Students learn a hands-on approach to using open source tools for a powerful generative AI application
Our mission
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.
Affiliate disclosure
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.
© 2016 - 2024 OpenCourser