Dexa/This Week in ML & AI

Published Nov 11, 2024

Why Your RAG Pipeline Is Broken, and How to Fix It with Jason Liu - 709

Freelance AI consultant Jason Liu delves into diagnosing and fixing 'broken' retrieval-augmented generation (RAG) systems, discussing optimization through embedding and chunking strategies, data-driven experimentation, and his approaches to effective AI consulting.

Episode Highlights

Topics covered

Questions from this episode

- What's next in large language models (LLMs)?
  Asked by 34 people
- What techniques are used with large language models (LLMs)?
  Asked by 27 people
- What are the next advancements in large language models (LLMs)?
  Asked by 23 people
- Do you use retrieval-augmented generation (RAG) or a chatbot?
  Asked by 20 people
- What is the best insight on prompt engineering and engaging large language models (LLMs)?
  Asked by 16 people
- What are the challenges in machine learning?
  Asked by 12 people
- How can marketers leverage data?
  Asked by 10 people
- Do I get it right that a Retrieval Augmented Generation (RAG) system can retrieve data in addition to its training data?
  Asked by 9 people
- What challenges arise in data sets?
  Asked by 9 people
- What are the most recent developments and trends in AI, large language models (LLMs), retrieval-augmented generation (RAG), etc., as discussed in the episode 📅 ThursdAI - May 16 - OpenAI GPT-4o, Google IO recap, LLama3 hackathon, Yi 1.5, Nous Hermes Merge & more AI news and the clip AI Advancements Unveiled?
  Asked by 8 people
- What problems do developers face when building AI applications as discussed in the episode Augmenting Incident Response with LLMs and the clip Embracing AI Integration?
  Asked by 8 people
- What problems do developers face when building AI applications as discussed in the episode Augmenting Incident Response with LLMs and the clip AI Infrastructure Insights?
  Asked by 7 people
- How does structured output work in large language models (LLMs)?
  Asked by 6 people
- How can AI summarize conversations?
  Asked by 6 people
- How does one understand the underlying data?
  Asked by 4 people

Episode Highlights

Related Episodes

AI Agents and Data Integration with GPT and LLaMa with Jerry Liu - 628
Answers 383 questions
Why Agents Are Stupid & What We Can Do About It with Dan Jeffries - 713
Answers 383 questions
Visual Generative AI Ecosystem Challenges with Richard Zhang - 656
Answers 383 questions
AI Agents for Data Analysis with Shreya Shankar - 703
Answers 383 questions
AI Engineering Pitfalls with Chip Huyen - 715
Answers 383 questions
Building a Unified NLP Framework at LinkedIn with Huiji Gao - #481
Answers 383 questions
A Social Scientist’s Perspective on AI with Eric Rice - #511
Answers 383 questions
AI Agents: Substance or Snake Oil with Arvind Narayanan - 704
Answers 383 questions
Engineering the Future of AI with Ruchir Puri - #21
Answers 383 questions
Engineering A ML-Powered Developer-First Search Engine with Richard Socher - #582
Answers 383 questions
Pragmatic Deep Learning for Medical Imagery with Prashant Warier - TWiML Talk #165
Answers 383 questions
Reinforcement Learning for Personalization at Spotify with Tony Jebara - 609
Answers 383 questions
Information Extraction from Natural Document Formats with David Rosenberg - #126
Answers 383 questions
Hyper-Personalizing the Customer Experience with AI, w/ Rob Walker - #127
Answers 383 questions
AI for Network Management with Shirley Wu - 710
Answers 383 questions