Emerging architectures for LLM applications
HTML-код
- Опубликовано: 22 авг 2024
- Everything from training models from scratch and fine-tuning open-source models to using hosted APIs, with a particular emphasis on the design pattern of in-context learning.
Key topics we'll cover during the session include:
- Data preprocessing and embedding, focusing on the role of contextual data, embeddings, and vector databases in creating effective LLM applications.
- Strategies for prompt construction and retrieval, which are becoming increasingly complex and critical for product differentiation.
- Prompt execution and inference, analyzing the leading language model providers, their models, and tools used for logging, tracking, and evaluation of LLM outputs.
- Hosting solutions for LLMs, comparing the common solutions and emerging tools for easier and more efficient hosting of LLM applications.
Whether you're a seasoned AI professional, a developer beginning your journey with LLMs, or simply an enthusiast interested in the applications of AI, this webinar offers valuable insights that can help you navigate the rapidly evolving landscape of LLMs.
Follow along with the slides here go.superwise.a...
4k views and only 2 comments. This is the best RUclips video I've seen by far on these strategies. Great content - thank you so much for sharing your expertise!
🎯 Key Takeaways for quick navigation:
00:00 📚 Introduction to the topic of emerging architectures for LLM applications.
01:54 🧐 Why focus on LLM architectures.
04:02 📊 Audience poll on LLM use cases.
05:17 🧠 Retrieval Augmented Generation (RAG) as a design pattern.
08:05 💡 Advanced techniques in RAG and architectural considerations.
14:40 📦 Orchestration and addressing complex tasks with LLMs.
23:53 🧩 LLMs in Intermediate Summarization
26:43 📊 Monitoring in LLM Architecture
32:04 🛠️ LLM Agents and Tools
39:05 🔄 Improving LLM Inference Speed
49:26 🛡️ OpenAI's ChatGPT and its relevance in the field,
50:12 🌐 Evolution of ChatGPT and the AI landscape,
51:09 💼 OpenAI's models and their resource allocation,
52:16 🏢 Factors influencing model choice: Engineering, economy, and legal considerations,
Made with HARPA AI
crazy
This is one of the best webinars I have seen on this topic. Great slides and presenters!
it was awesome, thanks guys, keep up the good work.
I was very pleased to see how well everything was broken down! I was also shook to see a lot of the architecture strategies were things we were already implementing at our company so I'm happy to see we are on the right track 😅
This vieo was great! Thank you so much.
Very interesting, thanks for sharing
Nice to see these topics covered, these come up as soon as I was attempting to implement something with llms
I am curious to know what you are trying to implement.
Very informative. Several layers of LLM architectures need to be simplified like this. Maybe a standard for XAI should be developed based on a simplified architectural stack like this for LLMs.
Really great presentation.Keep up the good work
Really informative video. It will be interesting to see how different layers are formed throughout the coming months. Given the complexities of RAG, it'd be interesting to see hosted solutions that can offer competitive pricing on a RAG engine.
Wonderful video, learns a lot, thanks
That was very nice, thank you all
Informative video ... Waiting for next video :)
Wonderful video, learns a lot, thanks. This vieo was great! Thank you so much..
So informative, looking forward to seeing more
Very informative, thanks!
Great talk !
great ideas txs!
Great!
Excellent detailed information thanks, please share slide details,
Thank you!
You can access the slides here - go.superwise.ai/hubfs/PDF%20assets/LLM%20Architectures_8.8.2023.pdf
Can you make the slides available? I have an issue seeing them and following along.
No problem here you go - go.superwise.ai/hubfs/PDF%20assets/LLM%20Architectures_8.8.2023.pdf
Can someone provide an example of how one might introduce time as a factor in the embedding?
It would be in a meta field that you use to filter results, not in the vector embeddings itself.
Honestly. Not huge value for 55 minutes,,,
these videos seldom are.. lol.
Total gibberish in this video