Viewing profile — jn2clark

How does it compare to previous work on learning to learn? I don't see it referenced https://arxiv.org/abs/1606.04474

Is it just write the repo(s) to a text file and upload to Claude with some instructions? Specifically, looking to port ML models between frameworks. For example, JAX PyTorch, but c…

With binary representations you still get 2^D possible configurations so its entirely possible from a representation perspective. The main issue (I think at least) is around determ…

That's a great question. I think regimes like that could offer better trade-offs of memory/latency/retrieval performance, although I don't know what they are right now. It also ass…

I would love an LLM agent that could generate small api examples (reliably) from a repo like this for the various different models and ways to use them.

What is accuracy in this case? is it meant to be recall or is it some evaluation metric?

We (Marqo) are doing a lot on 1 and 2. There is a huge amount to be done on the ML side of vector search and we are investing heavily in it. I think it has not quite sunk in that v…

Take a look here https://github.com/marqo-ai/local-image-search-demo . It is based on https://github.com/marqo-ai/marqo . We do a lot of image search applications. Feel free to rea…

Can anyone comment on an open source multi-modal LLM that can produce structured outputs based on an image? I have not found a good open source one yet (this included), seems to be…

Fair enough, apologies for the confusion!

That sounds much longer than it should. I am not sure on your exact use-case but I would encourage you to check out Marqo ( https://github.com/marqo-ai/marqo - disclaimer, I am a c…

Try this https://github.com/marqo-ai/marqo which handles all the chunking for you (and is configurable). Also handles chunking of images in an analogous way. This enables highlight…

As others have correctly pointed out, to make a vector search or recommendation application requires a lot more than similarity alone. We have seen the HNSW become commoditised and…

Thanks for the feedback and questions - really appreciate it.

At the moment you would need to do this yourself. It would be possible to have additional preprocessing to accommodate this though. Feel free to add a feature request here https://…

Regarding metric and dimension - it is really problem dependent as is throughput. Recall and latency numbers reported in benchmarks are typically on very well curated and structure…

I think it depends a bit on the definition of search here. It might satisfy a literal definition of search but not search as users would expect - which I think is the important poi…

Good question! At the moment if you have the abstraction of data -> model -> vector then it is amenable to searching like this. It will depend a bit on the use case though.

Marqo is an end-to-end vector search engine. It contains everything required to integrate vector search into an application in a single API. Here is a code snippet for a minimal ex…

In the quest for ultimate speed, I started developing a vector database in assembly using gpt4 as a side project https://github.com/jn2clark/GPT4Memory .