sentence-transformers VS HyperTag

txtai is an open-source first system. Given it's own open-source roots, like-minded projects such as sentence-transformers are prioritized during development. But that doesn't mean txtai can't work with Embeddings API services.

Ok great. My use case is not very specific, but rather general. I am looking for a model that can perform asymmetric semantic search for the languages I mentioned earlier (Urdu, Persian, Arabic etc.). I have also looked into the sentence-transformer training documentation. Do you think it would be a good idea to use the XNLI dataset for fine-tuning? Or maybe you can suggest much better dataset. Furthermore, I am not sure if fine-tuning is suitable for my task. Because my use case is general so I can use already trained model.

The task you are looking for is semantic textual similarity. There are a few models and datasets out there that can do this. I'd probably start with the SemEval2017 Task 1 task description and competition entries here and then work outward from there (using something like SemanticScholar or Papers With Code to find newer state of the art works that cite these models if needed). For what it's worth you might find that Sentence Bert (SBERT) gives good vectors for cosine similarity comparison out of the box for this task.

Check out the sentence-transformers implementation. If I don't miss anything they don't exclude CLS when the pooling strategy is set to 'mean'

Break up transcript into shorter segments and convert segments to a 768 vector array. Use a process known as embedding using our second ML model, UKP Labs BERT’s sentence transformer model.

Not sure what kind of texts you have, but these models have a max sequence limit of 512 (approx 350 words or so). If you're texts are longer than that, consider splitting them up into chunks or creating a summary and taking an embedding of that. Some clustering algorithm may be the way to go here. Here's a bunch of examples. I use agglomerative for my use case.

https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/data_augmentation (Augmented Encoding)

For vector representation you can take the mean and then pca to get the size that you want, but if you have time then use sentence transformers to train a vector representation instead.

I found a related tool a while back that I've wanted to try and integrate, as soon as I get into the habit of making more notes & such:

https://github.com/Ravn-Tech/HyperTag#overview

I guess my ideal tool would be able to recognize the different "contexts" that I'm in, and build a searchable, tagged timeline of my browsing and googling and work history in each of these contexts. Provide the capability to cross-link with notes in an athens/roam-like fashion and it'd be gold

https://github.com/SeanPedersen/HyperTag

HyperTag helps humans intuitively express how they think about their files using tags and machine learning. Represent how you think using tags. Find what you look for using semantic search for your text documents (yes, even PDF's) and images. Instead of introducing proprietary file formats like other existing file organization tools, HyperTag just smoothly layers on top of your existing files without any fuss.

Interesting, I just realized I should market my project as a personal knowledge management system as well. Thanks a bunch!

https://github.com/SeanPedersen/HyperTag

Github Repo: https://github.com/SeanPedersen/HyperTag