Augmented Language Models (LLM Bootcamp)

New course announcement ✨
We're teaching an in-person LLM bootcamp in the SF Bay Area on November 14, 2023. Come join us if you want to see the most up-to-date materials building LLM-powered products and learn in a hands-on environment.
www.scale.bythebay.io/llm-wor...
Hope to see some of you there!
--------------------------------------------------------------------------------------------- In this video, Josh walks through the patterns for augmenting language models with external context: retrieval augmentation, chaining, and tool use.
Download slides from the bootcamp website here: fullstackdeeplearning.com/llm...
Intro and outro music made with Riffusion: github.com/riffusion/riffusion
Watch the rest of the LLM Bootcamp videos here: • LLM Bootcamp - Spring ...
0:00:00 Why augmented LMs?
0:06:40 Why retrieval augmentation?
0:08:25 Traditional information retrieval
0:13:05 Embeddings for retrieval
0:22:15 Embedding relevance and indexes
0:28:42 Embedding databases
0:38:50 Beyond naive embeddings
0:41:10 Patterns & case studies
0:46:16 What are chains and why do we need them?
0:52:50 LangChain
0:54:55 Tool use
0:59:17 Plugins
1:02:38 Recommendations for tool use
1:04:07 Recap & conclusions

[@jeromeeusebius]

Great resource for understanding RAG and the various ways to improve reliability and accuracy of LLM's. Thanks for sharing.

[@ayanghosh8226]

Love the logical sequence of presenting the complications in advanced LLM applications. One of the best resources on the web, if one wants a solid mental map of how and when to augment LLMs.

[@HarendraSingh-xw6hv]

💯

[@loic7572]

This is the best bootcamp I've ever watched. I only wish I had known about the CZcams channel before.

[@l501l501l]

Second that!

[@lukeliem9216]

This talk is very informative about building LLM-based apps with proprietary datasets.

[@robertcormia7970]

Another fantastic video (webinar) helping to build on foundational knowledge of LLMs. Clear explainations of chains, tools, APIs, and "process". Can't wait to watch the next one (LLMOPs)

[@za_daleko]

Thanx for this knowledge. Greetings from Poland.

[@RohanKumar-vx5sb]

u’re the best. this has been the singular most useful and up to date analysis of LLM advancements

Awesome! Thanks Josh for the presentation!

[@saratbhargavachinni5544]

Great talk! Thanks for sharing

[@fudanjx]

Quick Summary:
Introduction:
Language models are powerful but lack knowledge of the world. We can augment them by providing relevant context and data.
Witnesses:
- Retrieval: Searching a corpus and providing relevant documents as context.
- Chains: Using one language model to develop context for another.
- Tools: Giving models access to APIs and external data.
Testimonies:
Retrieval:
- Simplest way is adding relevant facts to context window.
- As corpus scales, treat it as an information retrieval problem.
- Embeddings and vector databases can improve retrieval.
Chains:
- Use one language model to develop context for another.
- Can help encode complex reasoning and get around token limits.
- Tools like Langchain provide examples of chain patterns.
Tools:
- Give models access to APIs and external data.
- Chains involve manually designing tool use.
- Plugins let models decide when to use tools.
Key Takeaways:
- Start with rules and heuristics to provide context.
- As knowledge base scales, think about information retrieval.
- Chains can help with complex reasoning and token limits.
- Tools give models access to external knowledge.
Conclusion:
Augmenting language models with relevant context and data can significantly improve their capabilities. There are a variety of techniques to provide that augmentation, each with trade-offs around flexibility, reliability,
and complexity.

[@deeplearningpartnership]

Cool

[@user-cq5ue1cj3n]

great. I had to listen at a 0,75 speed, not to miss anything.

[@domlahaix]

Crocodile, Ball.... unless you're working for Lacoste 😀

[@SavanVyas91]

What’s his name where can I find him?

[@kennethcarvalho3684]

isnt this a search like google