Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Jina AI launches open-source 8k text embedding

jina.ai

Post reply on HN
Print view View original

101–110 of 217 posts

Re: Jina AI launches open-source 8k text embedding

#101

Post by karxxm »

minimaxir wrote: post #34
jncraton wrote: post #14

This is great to see. It looks like the size of the embedding vector is half the size of text-embedding-ada-002 (768 vs 1536) while providing competitive performance. This will save space in databases and make lookups somewhat faster. For those unaware, if 512 tokens of context is sufficient for your use case, there are already many options that outperform text-embedding-ada-002 on common benchmarks: https://huggingf…

The 768D-sized embeddings compared to OpenAI's 1536D embeddings are actually a feature outside of index size. In my experience, OpenAI's embeddings are overspecified and do very poorly with cosine similarity out of the box as they match syntax more than semantic meaning (which is important as that's the metric for RAG). Ideally you'd want cosine similarity in the range of [-1, 1] on a variety of data but in my experi…

You wrote „out of the box“, did you find a way to improve this?

Re: Jina AI launches open-source 8k text embedding

#103

Post by mike_ivanov »

simonw wrote: post #21

I just shipped a new llm-embed-jina plugin for my LLM tool which provides access to these new Jina models: https://github.com/simonw/llm-embed-jina Here's how to try it out. First, install LLM. Use pip or pipx or brew: brew install llm Next install the new plugin: llm install llm-embed-jina You can confirm the new models are now available to LLM by running: llm embed-models You should see a list that includes "jina-e…

JFYI, this is what happens on my M1 Macbook:

$ brew install llm $ llm ModuleNotFoundError: No module named 'typing_extensions'

Not sure where to report it.

Re: Jina AI launches open-source 8k text embedding

#104

Post by teaearlgraycold »

karxxm wrote: post #101
minimaxir wrote: post #34

Earlier quoted context omitted.

The 768D-sized embeddings compared to OpenAI's 1536D embeddings are actually a feature outside of index size. In my experience, OpenAI's embeddings are overspecified and do very poorly with cosine similarity out of the box as they match syntax more than semantic meaning (which is important as that's the metric for RAG). Ideally you'd want cosine similarity in the range of [-1, 1] on a variety of data but in my experi…

You wrote „out of the box“, did you find a way to improve this?

You can do PCA or some other dimensionality reduction technique. That’ll reduce computation and improve signal/noise ratio when comparing vectors.

Re: Jina AI launches open-source 8k text embedding

#105

Post by simonw »

mike_ivanov wrote: post #103
simonw wrote: post #21

I just shipped a new llm-embed-jina plugin for my LLM tool which provides access to these new Jina models: https://github.com/simonw/llm-embed-jina Here's how to try it out. First, install LLM. Use pip or pipx or brew: brew install llm Next install the new plugin: llm install llm-embed-jina You can confirm the new models are now available to LLM by running: llm embed-models You should see a list that includes "jina-e…

JFYI, this is what happens on my M1 Macbook: $ brew install llm $ llm ModuleNotFoundError: No module named 'typing_extensions' Not sure where to report it.

Whoa, that is a weird one. Do you know what version of Python you have from Homebrew?

It looks like that package is correctly listed in the formula: https://github.com/Homebrew/homebrew-core/blob/a0048881ba9a2...

Re: Jina AI launches open-source 8k text embedding

#106

Post by richardw »

SOLAR_FIELDS wrote: post #71
jerpint wrote: post #67

Earlier quoted context omitted.

It definitely is open source even if they don’t disclose all details behind the training

The very definition of what constitutes open source is being called into question in these kinds of discussions about AI. Without the training details and the weights being made fully open it’s hard to really call something truly open, even if it happens to meet some arbitrary definition of “open source”. A good definition of “truly open” is whether the exact same results can be reproduced by someone with no extra in…

So if someone includes images in their project they need to tell you every brush stroke that led to the final image?

All sorts of intangibles end up in open source projects. This isn’t a science experiment that needs replication. They’re not trying to prove how they came up with the image/code/model.

Re: Jina AI launches open-source 8k text embedding

#107

Post by TeMPOraL »

mogwire wrote: post #75
selcuka wrote: post #74

Earlier quoted context omitted.

How do you define "source", then? By this logic any freely downloadable executable software (a.k.a. freeware) is also open source, even though they don't disclose all details on how to build it.

Source would be the way the data is produced so that you can replicate it yourself and make changes. If I hand you a beer for free that’s freeware. If I hand you the recipe and instructions to brew the beer that is open source. We muddy the waters too much lately and call “free” to use things “open source”.

> If I hand you a beer for free that’s freeware. If I hand you the recipe and instructions to brew the beer that is open source.

Yeah, but what those "open source" models are is like you handing me a bottle of beer, plus the instructions to make the glass bottle. You're open-sourcing something, just not the part that matters. It's not "open source beer", it's "beer in an open-source bottle". In the same fashion, those models aren't open source - they're closed models inside a tiny open-source inference script.

Re: Jina AI launches open-source 8k text embedding

#108

Post by TeMPOraL »

rolisz wrote: post #55
simonw wrote: post #48

Earlier quoted context omitted.

I imagine it's more useful for finding related articles and clustering things than for semantic search, which will work much better against smaller chunks - especially if you're implementing Retrieval Augmented Generation.

I think the point is: if you compress 25 pages of text into 1024 floats, you will lose a ton of information, regardless of what the use case is, so you're probably still better of with chunking.

> if you compress 25 pages of text into 1024 floats, you will lose a ton of information

Sure, but then if you do it one page at a time, or one paragraph at a time, you lose ton of meaning - after all, individual paragraphs aren't independent of each other. And meaning is kind of the whole point of the exercise.

Or put another way, squashing a ton of text loses you some high-frequency information, while chunking cuts off the low-frequency parts. Ideally you'd want to retain both.

Re: Jina AI launches open-source 8k text embedding

#109

Post by discordance »

simonw wrote: post #72
Grimburger wrote: post #70

Earlier quoted context omitted.

> Have links gone out of fashion? Yes. You wrote far more words than needed to answer the comment, I did it for you instead.

One of the reasons I write so much stuff is so I can provide links to things I've written to answer relevant questions.

Thanks so much for your writings and for posting the link (and also for Datasette!). I've learned in the past few months from your blog.
Post reply on HN