ngalstyan4

I am curious how you prevent private data from getting leaked to the auto-generated public docs. I imagine this problem does not exist in open source projects, but would become an issue if not everything discussed in company's private messenger should be used as context for generating docs.

Comment · 2 years ago

Author here.

> I don’t think “get moar ram” is a good response to that particular critique.

I do not think the blog post suggested "get more ram" as a response, but happy to clarify if you could share more details!

> Indexing in Postgres is legitimately painful

Lantern is here to make the process seamless and remove most of the pain for people building LLM/AI applications. Examples:

1. We build tools to remove the guesswork of HNSW index sizing. E.g. https://lantern.dev/blog/calculator

2. We analyze typical patterns people use when building LLM apps and suggest better practices. E.g. https://lantern.dev/blog/async-embedding-tables

3. We build alerts and triggers into our cloud database that automate the discovery of many issues via heuristics.

Comment · 2 years ago

Author here. We will benchmark this thoroughly in the future for our vector indexes.

But at least anecdotally, it made a ton of difference.

We met <200ms latency budget with Ubicloud NVMes but had to wait seconds to get an answer from the same query with GCP persistent disks or local SSDs

Comment · 2 years ago

I have tried CLIP on my personal photo album collection and it worked really well there - I could write detailed scene descriptions of past road trips, and the photos I had in mind would pop up. Probably the model is better for everyday photos than for icons

Comment · 2 years ago

We provide this functionality in Lantern cloud via our Lantern Extras extension: <https://github.com/lanterndata/lantern_extras>

You can generate CLIP embeddings locally on the DB server via:

  SELECT abstract,
       introduction,
       figure1,
       clip_text(abstract) AS abstract_ai,
       clip_text(introduction) AS introduction_ai,
       clip_image(figure1) AS figure1_ai
  INTO papers_augmented
  FROM papers;

Then you can search for embeddings via:

  SELECT abstract, introduction FROM papers_augmented ORDER BY clip_text(query) <=> abstract_ai LIMIT 10;

The approach significantly decreases search latency and results in cleaner code. As an added bonus, EXPLAIN ANALYZE can now tell percentage of time spent in embedding generation vs search.

The linked library enables embedding generation for a dozen open source models and proprietary APIs (list here: <https://lantern.dev/docs/develop/generate>, and adding new ones is really easy.

Comment · 2 years ago

ACIDRain: Concurrency-Related Attacks on Database-Backed Web Applications: http://www.bailis.org/papers/acidrain-sigmod2017.pdf

Comment · 2 years ago

Not sure what the approach of this library is, but can't you generate a nonce from a larger alphabet, hash the column values with the nonce `hash(nonce || column)`, and crypto-shred the nonce in the end.

Then, during hashing you just need a constant immutable state, which effectively expands the hash space, without incurring the mutable state overhead of replacement strings strategy.

Comment · 2 years ago

this is cool!

Does this only collect logs from frontend?

Or it can also collect the backend and DB latency data related to a frontend interaction?

ngalstyan4

Recent submissions

Select 1 Touches 5,583 Lines of Postgres Source Code n narekg.me

Debugging Hetzner: Uncovering failures with powerstat, sensors, and dmidecode u ubicloud.com

Select 1 Touches 5,583 Lines of Postgres Source Code narekg.me

Debugging Hetzner: Uncovering failures with powerstat, sensors, and dmidecode ubicloud.com