Come on, Google.
4,973 karma · joined October 20, 2014
I love chess, deadlifting, and Elden Ring.
Twitter: https://x.com/frankzliu
LinkedIn: https://www.linkedin.com/in/fzliu
Come on, Google.
I'm with you on that second point though - both websites look like they were designed by hardware engineers rather than "omg-UI-UX-is-so-important" SWEs.
Here's an architecture diagram for a production-ready vector database https://milvus.io/docs/architecture_overview.md. Not exactly something you can build in a month.
I agree that there's probably a better solution than pure embedding-based or mixed embedding/keyword search, but the "better" solution will still be based around semantics... aka embeddings.
Tree-based vector indexes aren't bad either, especially if we can find a way to make the random projections more efficient.
I unfortunately don't see how vector database would be able to help with this. The knowledge bases that they provide are meant to enable large-scale retrieval and vector search. One way to fix the problem you mention is perhaps to increase the proportion of features that draw human attention (e.g. faces) in the training dataset.
We (Milvus) also have `milvus-lite` if you'd like something pip installable: python3 -m pip install milvus
Zilliz is the company behind Milvus, the world's most popular open-source vector database. We're hiring engineers, developer advocates, product marketing, and product managers. You can view and apply for open roles at https://zilliz.com/careers, or feel free to reach out to me directly.
As most ML is inherently probabilistic, it seems reasonable to make an LLM cache both semantic and _stochastic_, i.e. you wouldn't want the same answer every time you use "pick me a color" as prompt. Injecting the original LLM (GPT, Bard, etc) response as prompt for alpaca or some other model could make this cache virtually invisible.
What's preventing us from taking something like convnext or a hybrid conv/attention model and hooking that up to a decoder stack? I fee like the results would be similar if not better.
EDIT: Clarifying that encoder/decoder refers to the transformer stack, not an autoencoder.
1) adding an "advanced" tab which enables the user to input more information about the document, e.g. formatting, length, etc...
2) learning the user's writing patterns and style - I'm not sure if this can be done by prompting, but my guess is that there are methods that you can use to steer the prose towards the user's default style
3) plagiarism detection - this would require a large document store and could be implemented using fuzzy/semantic search via Milvus followed by string matching
Keep up the good work.
Disclaimer: We - Milvus (https://milvus.io) and Zilliz (https://zilliz.com) - and we have integrations as a vector store in Langchain.
e.g. GPT-3.5 might not be able to write simple poems correctly, but does GPT-4 solve the disease or the symptom (by masking it with a bigger model and more data)? I'm not entirely convinced.
A lot of applications and developers these days take memory management for granted, so embedding a 4GB model to significantly enhance coding and writing capabilities doesn't seem too far-fetched.
Most vector databases focus on ANN because of scale. Once you get to around a million vectors or so, it becomes prohibitively expensive to perform brute-force querying and search.
You're right in that it's a bit heavyweight, so we're working to see how we can make pub/sub and other cluster components lighter and more efficient overall.