EVA

Data

ai-relational database

SHOW HN2023

237points
36comments
#212of 3,109 in 2023
Top 7%of 2023 by points

How HN took it

CuriousMostly questions and neutral comments

1 positive, 14 neutral or asking, 1 mixed, 0 critical, out of 16 comments about the project. Thread score +0.02.

Idea: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Declarative SQL composition of models is a useful idea

    From 2 comments
    • I'm having trouble understanding what this does. Does it let you compose models via a SQL-like syntax?
      potatoman22 on HN
    • Is the benefit here that EVA supports a declarative style of composition over LangChain's (or similar) imperative style?
      heyzk on HN
  • Caching and token-cost optimization are interesting

    From 1 comment
    • You can cache function results yourself in Python if you want to - my implementation also sums up the tokens used by the calls to the functions. Influencing optimization isn't…
      simonw on HN

Objections

  • Lacks obvious SQL-based demos; examples are hard to find

    From 1 comment
    • I personally wouldn’t put the Emotion one first on the GitHub README, that was the only one I opened, before clicking the license plate one and a) see it was a whole other GitHub…
      dmix on HN
  • Unclear whether it is a new database engine or a caching layer

    From 2 comments
    • Could you turn this into a psql extension? If this is integrated into an actual database that can be used in production, this may have a future. Otherwise no one will touch this,…
      startupsfail on HN
    • Nice. I’ve skimmed over the documentation and it wasn’t clear. It looked like the database was designed from scratch. If this is a caching/syntactic sugar over a mix of DB and…
      startupsfail on HN
  • No prompt injection safeguards

    From 1 comment
    • How are you guarding against prompt injection attacks, e.g. either in the queried data, or in untrusted query parameters?
      catiopatio on HN

Requests

  • Support for self-hosted local LLMs

    From 2 comments
    • Very nice… any plans for supporting self hosted LLMs like BERT LLAMA etc?
      la64710 on HN
    • Great but personally I am interested in locally runnable LLM models instead of sending data to the cloud service like chatGPT.
      la64710 on HN
  • Weighted similarity search

    From 1 comment
    • Do you support weighted similarly search? I.e. when I have several embeddings and need to put a weight factor in front of the cosine similarity when I’m performing a query? Faiss…
      startupsfail on HN
  • Remote GPU support

    From 1 comment
    • thanks, that's great! I guess though I was curious if the GPU has to be on the server itself, or if it's able to harness a remote GPU. Since the database server is likely to be…
      zmmmmm on HN
  • NLP pipeline examples

    From 1 comment
    • It appears from initial reading that it must be possible to support pure NLP tasks with this, but there weren't examples for these in the documentation, so I'm not sure. Does it…
      shrikrishna on HN

Questions

  • Does it support NLP models?

    From 2 comments
    • It appears from initial reading that it must be possible to support pure NLP tasks with this, but there weren't examples for these in the documentation, so I'm not sure. Does it…
      shrikrishna on HN
    • Great question! Yes, EVA supports NLP pipelines thanks to our recent integration of Hugging Face pipelines last month. Here is an illustrative text classification application:…
      jarulraj on HN
  • What is the data privacy policy for uploaded files?

    From 2 comments
    • This looks very interesting. I am thinking of testing it out to see its accuracy for text detection and extraction in multiple PDFs. This will sound like an amateur question, but…
      amunutep on HN
    • We are in the process of supporting a native `LOAD PDF` command. Meanwhile, you could convert each PDF into a series of images and load them using the `LOAD IMAGE` command. You…
      jarulraj on HN
  • Can it run on a remote or cloud GPU?

    From 2 comments
    • Does this rely on local GPU compute on the database server? or can it integrate with cloud based or external GPU servers?
      zmmmmm on HN
    • Thanks for the clarification. EVA currently does not support remote GPUs. Our ongoing integration [1] of the Ray distributed compute framework [2] into EVA will soon allow us to…
      jarulraj on HN

Alternatives named

  • LangChain

    From 2 comments
    • Is the benefit here that EVA supports a declarative style of composition over LangChain's (or similar) imperative style?
      heyzk on HN
    • Great question! Besides improving usability, the key feature of the EVA database system is the query optimizer that seeks to speed up exploratory queries over a given dataset and…
      jarulraj on HN
  • txtai

    From 1 comment
    • Great question! Besides improving usability, the key feature of the EVA database system is the query optimizer that seeks to speed up exploratory queries over a given dataset and…
      jarulraj on HN
  • pgvector

    From 1 comment
    • Do you support weighted similarly search? I.e. when I have several embeddings and need to put a weight factor in front of the cosine similarity when I’m performing a query? Faiss…
      startupsfail on HN
  • Datasette ChatGPT SQLite function

    From 1 comment
    • The approaches look pretty similar. My chatgpt() function is pretty much the most basic possible implementation of that pattern - it's just a SQLite custom-SQL function written…
      simonw on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/35764355)