sentence-transformers
hnswlib
sentence-transformers | hnswlib | |
---|---|---|
45 | 12 | |
13,842 | 4,026 | |
2.4% | 1.8% | |
9.2 | 6.2 | |
3 days ago | 23 days ago | |
Python | C++ | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sentence-transformers
-
External vectorization
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.
-
[D] Looking for a better multilingual embedding model
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.
- Best pathway for Domain Adaptation with Sentence Transformers?
-
Syntactic and Semantic surprisal using a LLM
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.
-
Mean pooling in BERT
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'
-
I Built an AI Search Engine that can find exact timestamps for anything on Youtube using OpenAI Whisper
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.
-
Seeking advice on improving NLP search results
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.
-
Dev Diary #12 - Finetune model
https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/data_augmentation (Augmented Encoding)
-
[R] Customize size of Bio-BERT pre-trained embeddings
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.
- SentenceTransformer producing different sentence embedding results in Docker
hnswlib
-
Show HN: A fast HNSW implementation in Rust
How does this compare to hsnwlib - is it faster? https://github.com/nmslib/hnswlib
-
Show HN: Moodflix – a movie recommendation engine based on your mood
Last week I released Moodflix (https://moodflix.streamlit.app), a movie recommendation engine based to find movies based on your mood.
Moodflix was created on top of a movie dataset of 10k movies from The Movie Database. I vectorised the films using Hugging Face's T5 model (https://huggingface.co/docs/transformers/model_doc/t5) using the film's plot synopsis, genres and languages. Then I indexed the vectors using hnswlib (https://github.com/nmslib/hnswlib). LLMs can understand a movie's plot pretty well and distill the similarities between a user's query (mood) to the movie's plot and genres.
I have got feedback from close friends around linking movies to other review sites like IMDB or Rotten Tomatoes, linking movies to sites to stream the movie and adding movie posters. I would also love to hear from the community what things you like, what you want to see and what things you consider can be improved.
-
Hierarchical Navigable Small Worlds
Actually the "ef" is not epsilon. It is a parameter of the HNSW index: https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md...
-
Vector Databases 101
If you want to go larger you could still use some simple setup in conjunction with faiss, annoy or hnsw.
-
[P] Compose a vector database
Many vector databases are using Hnswlib and that is a supported vector index alongside Faiss and Annoy.
-
Faiss: A library for efficient similarity search
hnswlib (https://github.com/nmslib/hnswlib) is a strong alternative to faiss that I have enjoyed using for multiple projects. It is simple and has great performance on CPU.
After working through several projects that utilized local hnswlib and different databases for text and vector persistence, I integrated hnswlib with sqlite to create an embedded vector search engine that can easily scale up to millions of embeddings. For self-hosted situations of under 10M embeddings and less than insane throughput I think this combo is hard to beat.
https://github.com/jiggy-ai/hnsqlite
-
Storing OpenAI embeddings in Postgres with pgvector
https://github.com/nmslib/hnswlib
Used it to index 40M text snippets in the legal domain. Allows incremental adding.
I love how it just works. You know, doesn’t ANNOY me or makes a FAISS. ;-)
-
Seeking advice on improving NLP search results
3000 texts doesn't sound like to many, so may be a brute force cos calculation to find the most similar vector would work. If that's taking too much time, may be look at KNN or ANN modules to speed up finding the most similar vector. I use hsnwlib in knn mode for this. SOrt through about 350,000 vectors in about 30-50 msec.
-
How to Build a Semantic Search Engine in Rust
hnswlib is in cpp and has python bindings (you should be able to make your own for other languages).
https://github.com/nmslib/hnswlib
-
Anatomy of a txtai index
embeddings - The embeddings index file. This is an Approximate Nearest Neighbor (ANN) index with either Faiss (default), Hnswlib or Annoy, depending on the settings.
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
faiss - A library for efficient similarity search and clustering of dense vectors.
onnx - Open standard for machine learning interoperability
annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Top2Vec - Top2Vec learns jointly embedded topic, document and word vectors.
awesome-vector-search - Collections of vector search related libraries, service and research papers
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
semantic-search-through-wikipedia-with-weaviate - Semantic search through a vectorized Wikipedia (SentenceBERT) with the Weaviate vector search engine
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools