True ML Talks #12 The Future of Prompt Engineering, LLMs and LlamaIndex
Jerry Liu, Co-Founder, and creator of LlamaIndex, joins us on our 12th episode of
#TrueMLTalks. Learn about his experiences and passion for generative AI models, which led
him to creating LlamaIndex, an open-source tool that connects language models with private
data sources. In this chat, Jerry shares his expertise and sheds light on the dynamic world of
AI, providing valuable insights into the challenges, trends, and the future of LLMs.
In our conversation with Jerry, we covered the following aspects:
✅ What led to Jerry starting LlamaIndex?
✅ Features of LlamaIndex that users love
✅ Anthropic 100k window model
✅ Response synthesis model
✅ Retrieval-based approaches Vs fine-tuning approaches
✅ Combining retrieval-augmented generation and fine-tuning approaches
✅ Fine-tuning comparison between commercial vendors and open-source space
✅ General problem of LLM evaluations
✅ Differences between LlamaIndex and LangChain
✅ Most requested features from LlamaIndex users
✅ The technical challenges of building LlamaIndex
✅ Sources to stay up to date with LLMs
_____________________________________
00:00 Start.
02:00 Story of starting LlamaIndex?
07:24 Most loved features of LlamaIndex
10:17 Anthropic 100k window model
15:17 Response synthesis model and its challenges
19:24 Challenges of iteratively parsing context to the model
20:39 Retrieval-based approaches Vs fine-tuning approaches
24:05 Hybrid system of retrieval-augmented generation & fine-tuning
26:01 Fine-tuning: Commercial vendors Vs Open-source
28:41 Fine tuning in LlamaIndex?
29:57 Challenges of LLM evaluations
35:33 LlamaIndex Vs LangChain
39:10 Most requested features on LlamaIndex
42:29 Challenges of building LlamaIndex
45:23 Sources to stay up to date with LLMs
___________________________________
ABOUT OUR GUEST
Jerry Liu is the creator and co-founder of LlamaIndex. He brings his expertise in ML
research and engineering from esteemed companies like Uber, Quora, and Robust
Intelligence. With a strong focus on generative models and a passion for advancing AI
technologies, Jerry has pioneered the development of LlamaIndex, an open-source tool that
seamlessly connects language models with private data sources. Discover how he unravels
the power of LlamaIndex and its potential to revolutionise AI application experiences, and
much more, in this video.
⚡Reach out to Jerry at the below link - / jerry-liu-64390071
ABOUT OUR CHANNEL
TrueMLTalks is a video series in which we interview machine learning industry professionals
from companies such as Gong, Intuit, SalesForce, Facebook, DoorDash, and others. We
provide an insightful understanding of their experiences managing complex ML pipelines and
developing successful best practices, making it a valuable resource for professionals looking
to stay current on the latest advances in the field.
_____________________________________
ABOUT TRUEFOUNDRY
TrueFoundry is a cross-cloud machine learning deployment PaaS that enables enterprises
to speed up model testing and deployment while maintaining full security and control for the
Infra/DevSecOps team. We enable machine learning teams to deploy and monitor models in
15 minutes with 100% reliability and scalability, saving money and allowing models to be
released into production faster, resulting in genuine business value. We deploy on the
customer's infrastructure, taking data privacy and other security concerns into consideration.
⚡ A short ~4 min demo of the platform: https://t.ly/0fk1
Read our blog: https://blog.truefoundry.com/deep-div...
Subscribe to our newsletter: https://t.ly/oORp
Try our platform now - https://app.truefoundry.com/company-r...
Book a personalised demo - https://www.truefoundry.com/book-demo...
#LlamaIndex #generativeai #genai #gpt
Смотрите видео True ML Talks #12 The Future of Prompt Engineering, LLMs and LlamaIndex онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь TrueFoundry 01 Июнь 2023, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 443 раз и оно понравилось 14 людям.