yding

When you evaluated the tools, what stood out between which ones were better or worse?

Makes sense. I wonder if it affects the model output performance (sans quotes), as I could imagine that splitting up the model output to add the quotes could cause it to lose attention on what it was saying.

Thanks Simon. I think this might solve one of the most common questions people ask me: how do I get Perplexity-like inline citations on my LLM output?

This looks like model fine tuning rather than after the fact pseudo justification. Do you agree?

As someone who interned at Palm, love this so much!

Depends on the language/standard library. For example in C if your library includes its own HTTP library that's probably not a plus.

Congrats Taranjeet and Deshraj!

So after using Mem0 a bit for a hackathon project, I have sort of two thoughts: 1. Memory is extremely useful and almost a requirement when it comes to building next level agents and Mem0 is probably the best designed/easiest way to get there. 2. I think the interface between structured and unstructured memory still needs some thinking.

What I mean by that is when I look at the memory feature of OpenAI it's obviously completely unstructured, free form text, and that makes sense when it's a general use product.

At the same time, when I'm thinking about more vertical specific use cases up until now, there are very specific things generally that we want to remember about our customers (for example, for advertising, age range, location, etc.) However, as the use of LLMs in chatbots increases, we may want to also remember less structured details.

So the killer app here would be something that can remember and synthesize both structured and unstructured information about the user in a way that's natural for a developer.

I think the graph integration is a step in this direction but still more on the unstructured side for now. Look forward to seeing how it develops.

The short answer is he works at Cohere. But longer answer is that the model probably doesn’t matter that much.

Looks great! thanks for sharing your architecture choices here.

Congrats on the launch!

Very cool!

Absolutely makes sense!

Congrats! Well deserved achievement by one of the best executing teams.

Training a model with multiple billion floating point parameters on only 100 billion data points feels like a bad idea.

This is really cool! Starred and look forward to seeing how this develops further!

Congrats! Amazing milestone.

Great to see. Not only a wonderful mathematician but also a wonderful human being.

Very cool! Will check it out!

What were the issues you ran into with running LlamaIndex?

Congrats on the launch!

Great explanation!

I’m going to be a contrarian and say that I really appreciate that they went for a high performing/more expensive SoC this time.

When I had to buy a SBC last time I couldn’t bring myself to get the Pi 4 because it was missing core features (4K HDR decode) vs the alternatives. But I love the community around Raspberry Pi and it’ll definitely increase my options with this SBC.

Should go without saying to run these only in the most secure sandbox you can find?

The data questions are exactly the things we are working through right now!

I think Streamlit is a great way to get started quickly. Would love to talk more about your thoughts around data ingest for prod use cases. yiding@runllama.ai

Congrats on the launch!

Currently all of LlamaIndex's text splitters were/are Langchain compatible.

This is really cool and a much needed contribution to helping LLMs run better on large code bases.

Very cool Ishaan!

Here's a stat I heard a few years back: WeChat has over 50% time share in China. Meaning people in China are on WeChat more than all other apps on their phones combined.

Good job Will!

Good job Yoko!