HackerTrans
TopNewTrendsCommentsPastAskShowJobs

xfalcox

1,029 karmajoined 13 वर्ष पहले
[ my public key: https://keybase.io/falcofantastic; my proof: https://keybase.io/falcofantastic/sigs/_PKYsKf2wmCyt834lEh6N4POje9RoICd3Ta7qezTzJE ]

comments

xfalcox
·4 दिन पहले·discuss
Question to the OP, have you tested this on a machine where the entire model and context fit in RAM ?
xfalcox
·4 दिन पहले·discuss
README covers that

https://github.com/JustVugg/colibri#ssd-wear-warning
xfalcox
·पिछला माह·discuss
Given my dev machine has 32GB of RAM and 32GB of VRAM that sits mostly idle when I'm not running AI models, this is not that bad of an idea.
xfalcox
·3 माह पहले·discuss
Comparing a model you can downloads weights for with an API-only model doesn't make much sense.
xfalcox
·3 माह पहले·discuss
Our CEO did that at our company and found 33 CVEs. Rails also did that and found 7 or 8.
xfalcox
·6 माह पहले·discuss
I just made a new installer for Discourse on CharmRuby, now I gotta check this out and see if porting is feasible. Hopefully this reduces the app size, that is quite large with CharmRuby
xfalcox
·6 माह पहले·discuss
That is a great fit for the GIF integration in Discourse.

I was able to quickly add support for it at https://github.com/discourse/discourse-gifs/pull/107

Love to see WEBP support. Do you plan on adding support for AVIF?

Also, this is used by many Discourse sites, we should talk.
xfalcox
·6 माह पहले·discuss
First time I was in San Francisco and someone introduced themselves like that, going even beyond, was indeed a super weird experience being a brazilian.
xfalcox
·7 माह पहले·discuss
We have vLLM for running text LLMs in production. What is the equivalent for this model?
xfalcox
·8 माह पहले·discuss
I am partial to https://huggingface.co/Qwen/Qwen3-Embedding-0.6B nowadays.

Open weights, multilingual, 32k context.
xfalcox
·8 माह पहले·discuss
It's the Amazon own model. I'm baffled someone would pick it, even more that someone would test Llama 4 for a task in an age where Sonnet 4.5 is already out, so in the last 45 days.

Looks like they were limited by AWS Bedrock options.
xfalcox
·8 माह पहले·discuss
> what does the rag for uploaded files do in discourse?

You can upload files that will act as RAG files for an AI bot. The bot can also have access to forum content, plus the ability to run tools in our sandboxed JS environment, making it possible for Discourse to host AI bots.

> also, when i run a discourse search does it really do both a regular keyword search and a vector search? how do you combine results?

Yes, it does both. In the full page search it does keyword first, then vector asynchronously, which can be toggled by the user in the UI. It's auto toggled when keyword has zero results now. Results are combined using reciprocal rank fusion.

In the quick header search we simply append vector search to keyword search results when keyword returns less than 4 results.

> does all discourse instances have those features? for example, internals.rust-lang.org, do they use pgvector?

Yes, all use PGvector. In our hosting all instances default to having the vector features enabled, we run embeddings using https://github.com/huggingface/text-embeddings-inference
xfalcox
·8 माह पहले·discuss
We host thousands of forums but each one has its own database, which means we get a sort of free sharding of the data where each instance has less than a million topics on average.

I can totally see that at a trillion scale for a single shard you want a specialized dedicated service, but that is also true for most things in tech when you get to the extreme scale .
xfalcox
·8 माह पहले·discuss
I was taken back when I saw what was basically zero recall loss in the real world task of finding related topics, by doing the same thing you described where we over capture with binary embeddings, and only use the full (or half) precision on the subset.

Making the storage cost of the index 32 times smaller is the difference of being able to offer this at scale without worrying too much about the overhead.
xfalcox
·8 माह पहले·discuss
In Discourse embeddings power:

- Related Topics, a list of topics to read next, which uses embeddings of the current topic as the key to search for similar ones

- Suggesting tags and categories when composing a new topic

- Augmented search

- RAG for uploaded files
xfalcox
·8 माह पहले·discuss
Also worth mentioning that we use quantization extensively:

- halfvec (16bit float) for storage - bit (binary vectors) for indexes

Which makes the storage cost and on-going performance good enough that we could enable this in all our hosting.
xfalcox
·8 माह पहले·discuss
> Nobody’s actually run this in production

We do at Discourse, in thousands of databases, and it's leveraged in most of the billions of page views we serve.

> Pre- vs. Post-Filtering (or: why you need to become a query planner expert)

This was fixed in version 0.8.0 via Iterative Scans (https://github.com/pgvector/pgvector?tab=readme-ov-file#iter...)

> Just use a real vector database

If you are running a single service that may be an easier sell, but it's not a silver bullet.
xfalcox
·11 माह पहले·discuss
Depends on your needs. You surely don't want 32k long chunks for doing the standard RAG pipeline, that's for sure.

My use case is basically a recommendation engine, where retrieve a list of similar forum topics based on the current read one. As with dynamic user generated content, it can vary from 10 to 100k tokens. Ideally I would generate embeddings from an LLM generated summary, but that would increase inference costs considerably at the scale I'm applying it.

Having a larger possible context out of the box just made a simple swap of embeddeding models increase quality of recommendations greatly.
xfalcox
·11 माह पहले·discuss
Just migrated all embeddings to this same model a few weeks ago in my company, and it's a game changer. Having 32k context is a 64x increase when compared with our previous used model. Plus being natively multilingual and producing very standard 1024 long arrays made it a seamless transition even with millions of embeddings across thousands of databases.

I do recommend using https://github.com/huggingface/text-embeddings-inference for fast inference.
xfalcox
·11 माह पहले·discuss
Having a public tokenizer is quite useful, specially for embeddings. It allows you to do the chunking locally without going to the internet.