CF

Systematically Improving RAG Applications - Bonus Content

24h 50m 24s
English
Paid

Systematically Improving RAG Applications - Bonus Content is a 28-lesson 24 hours 50 minutes self-paced course by Jason Liu. Systematically Improving RAG Applications: Bonus Content - Enrich your learning experience with access to exceptional materials from prior cohorts, including workshops , guest lectures , and Q&A sessions .

Course facts

Lessons
28
Duration
24 hours 50 minutes
Level
All levels
Language
English
Updated
Instructor
Jason Liu
Price
Premium

Systematically Improving RAG Applications: Bonus Content - Enrich your learning experience with access to exceptional materials from prior cohorts, including workshops, guest lectures, and Q&A sessions. Dive into a wealth of practical cases, best practices, and in-depth technical analyses.

Cohort 1

Workshops

Engage in six practical workshops from the first cohort that complement the main program:

  • Workshop 1
  • Workshop 2
  • Workshop 3
  • Workshop 4
  • Workshop 5
  • Workshop 6

Guest Lectures

Listen to insightful lectures from experts at leading AI companies:

  • Building Dynamic AI Memory Systems - Personalization by Sam Whitmore
  • Text Chunking in RAG - Insights by Anton from ChromaDB
  • Custom RAG Evaluations - With Vespa.ai
  • Multimodal RAG, Hybrid Search & Re-ranking Tips - With LanceDB and Unstructured
  • Leveraging User Feedback - Experiences from Zapier Central
  • Guide to RAG Complexity - Featured by Cohere and Modal Labs
  • Boosting BM25 with Generative AI - Doug Turnbull

Office Hours

Engage with experts through a series of Q&A sessions addressing practical challenges such as:

  • Building scalable RAG systems
  • Query optimization and routing
  • Fine-tuning re-rankers
  • Exploring alternative search methods: ColBERT, SPLADE
  • Implementing DAGs and serverless architecture
  • Specialized sessions for the APAC region

Cohort 2

Guest Lectures

New insights from the second cohort's guest expert sessions:

  • Evolving workflows for RAG optimization
  • Lexical Love - Shared by John Berriman
  • Common Mistakes with Evals - Clarified by Hamel Husain
  • Workflow Agents - A deep dive by Jerry Liu (LlamaIndex)
  • Query Routing - Perspective by Anton Troynikov (ChromaDB)
  • Fine-Tuning for Enterprise Search - Insights from the Glean team

Who teaches Systematically Improving RAG Applications - Bonus Content? Jason Liu

Jason Liu thumbnail

Jason Liu is a US ML engineer and the creator of Instructor (the most-used Python library for getting structured outputs from LLMs) and a long-running independent voice on the production-engineering side of LLM applications. He consults with companies on RAG implementations and is widely cited for the rigour of his approach to systematic RAG improvement.

His CourseFlix listing carries three Jason Liu courses: Systematically Improving RAG Applications, the accompanying Bonus Content module, and 3 Day AI Coding Accelerator. The RAG material is unusual for the depth it goes into the eval and feedback-loop side of production RAG systems — the parts of RAG work that separate a working RAG pipeline from one that hallucinates.

Material is paid and aimed at engineers running RAG in production who want to make the system measurably better rather than relying on prompt-engineering by intuition. For broader content, see CourseFlix's RAG category page.

What lessons are included in Systematically Improving RAG Applications - Bonus Content?

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 28 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Cohort 1 Guest Lectures Building Dynamic AI Memory Systems Sam Whitmore's Approach to Personalization
All Course Lessons (28)
#Lesson TitleDurationAccess
1
Cohort 1 Guest Lectures Building Dynamic AI Memory Systems Sam Whitmore's Approach to Personalization Demo
55:45
2
Cohort 1 Guest Lectures Text Chunking in RAG Essential Guide with Anton from ChromaDB
01:01:30
3
Cohort 1 Guest Lectures Custom RAG Evaluations w Vespa.ai
53:38
4
Cohort 1 Guest Lectures Multimodal RAG, Hybrid Search & Re-ranking Tips with LanceDB and Unstructured
59:05
5
Cohort 1 Guest Lectures Leveraging User Feedback for Better RAG Systems Lessons from Zapier Central
55:17
6
Cohort 1 Guest Lectures Cohere's Guide to RAG Complexity and Tips from Modal Labs
01:08:24
7
Cohort 1 Guest Lectures Boosting BM25 with Generative AI Insights from Doug Turnbull
58:12
8
Cohort 1 Office Hours Beyond Dense Embeddings Exploring Colbert, SPLADE, & Advanced Retrieval Techniques Office Hours
25:32
9
Cohort 1 Office Hours Building Resilient RAG Systems for Large-Scale Data Office Hours
01:00:09
10
Cohort 1 Office Hours Building Scalable Systems with DAGs and Serverless for RAG APAC Office Hours
59:01
11
Cohort 1 Office Hours Data Flywheels & Fine-Tuning Re-Rankers for Retrieval Systems Office Hours
29:17
12
Cohort 1 Office Hours Evaluating Agent Performance and Planning Reliability in AI Systems APAC Office Hours
47:42
13
Cohort 1 Office Hours Handling Real-Time Insights & Advanced Retrieval Challenges APAC Office Hours
51:37
14
Cohort 1 Office Hours Optimizing Planner and Feedback Mechanisms in RAG Systems APAC Office Hours
44:25
15
Cohort 1 Office Hours Smart Routing and Query Optimization for Advanced Retrieval Systems Office Hours
42:23
16
Cohort 1 Office Hours Using AI to Streamline Query Understanding & User Feedback Office Hours
44:33
17
Cohort 2 Guest Lectures Building document workflow agents with Jerry Liu from Llama Index
44:28
18
Cohort 2 Guest Lectures Building scalable RAG applications Evolving workflows for sharing and optimization [Ankur Goyal]
45:20
19
Cohort 2 Guest Lectures Common Mistakes People Make with Evals [Hamel Husain]
40:34
20
Cohort 2 Guest Lectures Inside Glean Fine-Tuning Embedding Models for Optimized AI and Enterprise Search
47:25
21
Cohort 2 Guest Lectures Lexical Love Rediscovering the Power of Text in RAG [John Berryman]
46:28
22
Cohort 2 Guest Lectures Organizing Your Data for Query Routing [Anton Troynikov from ChromaDB]
44:55
23
RAG Cohort 1 - Workshop 1
01:00:00
24
RAG Cohort 1 - Workshop 2
01:38:02
25
RAG Cohort 1 - Workshop 3
01:05:01
26
RAG Cohort 1 - Workshop 4
58:20
27
RAG Cohort 1 - Workshop 5
57:37
28
RAG Cohort 1 - Workshop 6
01:05:44
Unlock unlimited learning

Get instant access to all 27 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

What courses are similar to Systematically Improving RAG Applications - Bonus Content?

  • Introduction to RAG thumbnailUpdated 1y ago

    Introduction to RAG

    By: DAIR.AI (Elvis Saravia)
    Unlock the potential of Retrieval-Augmented Generation (RAG) as you delve into this comprehensive course designed to equip you with the skills to create.
    2h 23m5/5
  • RAG: Beyond Basics thumbnailUpdated 8mo ago

    RAG: Beyond Basics

    By: Prompt Engineering
    Explore the cutting-edge world of Retrieval-Augmented Generation (RAG) in this comprehensive course designed to deepen your understanding of both the.
    2h 40m5/5
  • RAG for Real-World AI Applications thumbnailUpdated 6mo ago

    RAG for Real-World AI Applications

    By: Vue School, Justin Schroeder, Daniel Kelly, Garrison Snelling
    Study the RAG approach to enhance AI with your own data. Learn about vectors, embeddings, and integration. Apply the approach in real projects.
    26m

Frequently asked questions

What are the prerequisites for enrolling in this course?
While there are no formal prerequisites, a basic understanding of Retrieval-Augmented Generation (RAG) systems and familiarity with AI concepts will be beneficial. The course includes advanced topics like building scalable RAG systems and fine-tuning re-rankers, which are best understood with some prior knowledge.
What practical projects or systems will I work on during the course?
Participants will engage in six practical workshops that complement the main program. These workshops are designed to provide hands-on experience with systems such as building scalable RAG systems with DAGs and serverless architectures and exploring alternative search methods like ColBERT and SPLADE.
Who is the target audience for this course?
The course is ideal for AI practitioners, data scientists, and developers interested in enhancing their skills in RAG applications. It is particularly suited for those looking to learn about dynamic AI memory systems, multimodal RAG, and leveraging user feedback in AI systems.
How does the depth and scope of this course compare to similar courses?
This course offers a unique blend of workshops, guest lectures, and office hours that cover a broad range of advanced topics. Unlike many courses that focus solely on theory, this course provides practical insights into building and optimizing RAG systems with contributions from experts at AI companies like ChromaDB, Vespa.ai, and Zapier Central.
What specific tools and platforms are covered in the course?
The course includes insights into tools and platforms such as Vespa.ai for custom RAG evaluations, LanceDB for multimodal RAG, and strategies for boosting BM25 with generative AI. These tools are discussed in guest lectures and office hours, providing a comprehensive understanding of their applications.
What topics are not covered in this course?
While the course covers a wide range of advanced RAG topics, it does not delve into basic AI or machine learning concepts. Participants looking for introductory material on AI will need to seek out other resources to gain foundational knowledge.
How can the skills learned in this course benefit my career?
The skills acquired from this course are applicable to various roles in AI and data science. Understanding scalable RAG systems, dynamic AI memory systems, and query optimization techniques can enhance your ability to design robust AI applications, making you a valuable asset in the tech industry.