marqo VS extension

We (Marqo) are doing a lot on 1 and 2. There is a huge amount to be done on the ML side of vector search and we are investing heavily in it. I think it has not quite sunk in that vector search systems are ML systems and everything that comes with that. I would love to chat about 1 and 2 so feel free to email me (email is in my profile). What we have done so far is here -> https://github.com/marqo-ai/marqo

Marqo.ai (https://github.com/marqo-ai/marqo) is doing some interesting stuff and is oss. We handle embedding generation as well as retrieval (full disclosure, I work for Marqo.ai)

Take a look here https://github.com/marqo-ai/local-image-search-demo. It is based on https://github.com/marqo-ai/marqo. We do a lot of image search applications. Feel free to reach out if you have other questions (email in profile).

That sounds much longer than it should. I am not sure on your exact use-case but I would encourage you to check out Marqo (https://github.com/marqo-ai/marqo - disclaimer, I am a co-founder). All inference and orchestration is included (no api calls) and many open-source or fine-tuned models can be used.

Try this https://github.com/marqo-ai/marqo which handles all the chunking for you (and is configurable). Also handles chunking of images in an analogous way. This enables highlighting in longer docs and also for images in a single retrieval step.

As others have correctly pointed out, to make a vector search or recommendation application requires a lot more than similarity alone. We have seen the HNSW become commoditised and the real value lies elsewhere. Just because a database has vector functionality doesn’t mean it will actually service anything beyond “hello world” type semantic search applications. IMHO these have questionable value, much like the simple Q and A RAG applications that have proliferated. The elephant in the room with these systems is that if you are relying on machine learning models to produce the vectors you are going to need to invest heavily in the ML components of the system. Domain specific models are a must if you want to be a serious contender to an existing search system and all the usual considerations still apply regarding frequent retraining and monitoring of the models. Currently this is left as an exercise to the reader - and a very large one at that. We (https://github.com/marqo-ai/marqo, I am a co-founder) are investing heavily into making the ML production worthy and continuous learning from feedback of the models as part of the system. Lots of other things to think about in how you represent documents with multiple vectors, multimodality, late interactions, the interplay between embedding quality and HNSW graph quality (i.e. recall) and much more.

Marqo provides automatic, configurable chunking (for example with overlap) and can allow you to bring your own model or choose from a wide range of opensource models. I think e5-large would be a good one to try. https://github.com/marqo-ai/marqo

Marqo has a similar API to Meilisearch's standard API but uses vector search in the background: https://github.com/marqo-ai/marqo

Have you tried Marqo? check the repo : https://github.com/marqo-ai/marqo

I notice the Ledger STX wallet is 39 characters where web wallet (leather.io) generates a 41 characters wallet address which is accepted by Binance.

How to Buy ULIT Coin With Bitcoin   One of the mega excitements of the last few days has been the launch of the ULIT Coin. What is described as the ultimate Wealth creator and the portal to Ultainfinity’s ginormous wealth can now be purchased, withdrawn, invested, lent and do several other things once considered unimaginable for a BRC20 or BEP20 token.   ● ULIT Coin is available on the unisat.io marketplace, accessible through https://unisat.io/market?tick=ULIT&tab=1. You would only need to click the Buy button to purchase. Further instructions are provided as a prompt after clicking on Buy. ● You can make direct purchases (and trade, invest or even borrow) on the ULIT dedicated website - https://ulitcoin.com. Upon visiting the web page, click on Buy ULIT coin, although, at this time, the website is still being expanded to include many more features and multiple tools.   Essentially, a few wallets are considered compatible and operational with the ULIT Coin. They include, but are not limited to, ● Unisat Wallet: https://unisat.io ● XVerse Wallet: https://www.xverse.app ● Hiro Wallet: https://wallet.hiro.so ● Ordinals Wallet: https://ordinalswallet.com ● Bitkeep Wallet: https://bitkeep.com/en/index

Essentially, a few wallets are considered compatible and operational with the ULIT Coin. They include, but are not limited to, ● Unisat Wallet: https://unisat.io ● XVerse Wallet: https://www.xverse.app ● Hiro Wallet: https://wallet.hiro.so ● Ordinals Wallet: https://ordinalswallet.com ● Bitkeep Wallet: https://bitkeep.com/en/index #ulit#ULC#Uniswap#UniSad#Crypto#Bitcoin#BRC20#XVerseWallet#OrdinalsWallet#bitkeepwallet#cryptonews#cryptonewsdaily#cryptotrading#finance#investmentstrategies#hirowallet#hiro#BEP20#ultainfinity#

https://wallet.hiro.so/ wallet

Hiro Wallet | Software Engineer | Full-time | Remote | $130–160k | https://wallet.hiro.so

Hiro Wallet is a cryptocurrency wallet that brings utility to Bitcoin. We need developers and designers to help us continue advancing our Web Extension, and bringing the wallet to new platforms. It's open-source and built with Typescript. You can check out our codebase here: https://github.com/hirosystems/wallet

Frontend developer: https://boards.greenhouse.io/trustmachines/jobs/4833863004

Product designer: https://boards.greenhouse.io/trustmachines/jobs/4603570004

To apply, email [email protected]

You need to download a wallet. Hiro will be the easier option based on the fact that you already have STX in your account. When you enter your pass phrase, it may give you a new one for Stacks 2, if that happens, definitely write it down and keep it

I know that there is an open github issue https://github.com/hirosystems/stacks-wallet-web/issues/951 regarding ledger support for the extension wallet.

Checked Github and didn't see any open or closed pull requests/issues on this. https://github.com/blockstack/stacks-wallet-web

There's no way to change this label without registering a name, though we're tracking this possible enhancement here: https://github.com/blockstack/stacks-wallet-web/issues/1703