TorchPQ
faiss
Our great sponsors
TorchPQ | faiss | |
---|---|---|
3 | 70 | |
202 | 28,202 | |
- | 4.4% | |
3.5 | 9.4 | |
5 months ago | 1 day ago | |
Cuda | C++ | |
MIT License | MIT License |
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.
TorchPQ
-
[D] Is there an open-source implementation of the Retrieval-Enhanced Transformer (RETRO)?
if you're decided to run nearest neighbor search on GPU, you might wanna give TorchPQTorchPQ a try
-
[P] TorchPQ: Efficient Nearest Neighbor Search and Clustering on GPUs
TorchPQ is a python library for approximate nearest neighbor search on GPUs. It has efficient implementations of IVFPQ algorithm as well as some of its variants (e.g IVFPQ+R). The project is written mostly in python using pytorch library, with some custom CUDA kernels to accelerate clustering, searching and indexing.
-
Are there more practical tools for KNN searches and storing documents/embeddings?
If you're using GPU for search, You can give TorchPQ a try, it's an ANN search library implemented with PyTorch and CUDA. with TorchPQ, you can freely add / remove vectors with IDs, you can save/load them just like a regular PyTorch model. TorchPQ is still in development, and I'd love to hear any suggestion or feedback.
faiss
-
Show HN: Chromem-go – Embeddable vector database for Go
Or just use FAISS https://github.com/facebookresearch/faiss
- OpenAI: New embedding models and API updates
-
You Shouldn't Invest in Vector Databases?
You can try txtai (https://github.com/neuml/txtai) with a Faiss backend.
This Faiss wiki article might help (https://github.com/facebookresearch/faiss/wiki/Indexing-1G-v...).
For example, a partial Faiss configuration with 4-bit PQ quantization and only using 5% of the data to train an IVF index is shown below.
faiss={"components": "IVF,PQ384x4fs", "sample": 0.05}
-
Approximate Nearest Neighbors Oh Yeah
If you want to experiment with vector stores, you can do that locally with something like faiss which has good platform support: https://github.com/facebookresearch/faiss
Doing full retrieval-augmented generation (RAG) and getting LLMs to interpret the results has more steps but you get a lot of flexibility, and there's no standard best-practice. When you use a vector DB you get the most similar texts back (or an index integer in the case of faiss), you then feed those to an LLM like a normal prompt.
The codifer for the RAG workflow is LangChain, but their demo is substantially more complex and harder-to-use than even a homegrown implementation: https://news.ycombinator.com/item?id=36725982
-
Can someone please help me with this problem?
According to this documentation page, faiss-gpu is only supported on Linux, not on Windows.
-
Ask HN: Are there any unsolved problems with vector databases
Indexes for vector databases in high dimensions are nowhere near are effective as the 2-d indexes used in GIS or the 1-d B-tree indexes that are commonly used in databases.
Back around 2005 I was interested in similarity search and read a lot of conference proceedings on the top and was basically depressed at the state of vector database indexes and felt that at least for the systems I was prototyping I was OK with a full scan and later in 2013 I had the assignment of getting a search engine for patents using vector embeddings in front of customers and we got performance we found acceptable with full scan.
My impression today is that the scene is not too different than it was in 2005 but I can't say I haven't missed anything. That is, you have tradeoffs between faster algorithms that miss some results and slower algorithms that are more correct.
I think it's already a competitive business. You have Pinecone which had the good fortune of starting before the gold rush. Many established databases are adding vector extension. I know so many engineering managers who love postgresql and they're just going to load a vector extension and go. My RSS reader YOShInOn uses SBERT embeddings to cluster and classify text and certainly More Like This and semantic search are on the agenda, I'd expect it to take about an hour to get
https://github.com/facebookresearch/faiss
up and working, I could spend more time stuck on some "little" front end problem like getting something to look right in Bootstrap than it would take to get working.
I can totally believe somebody could make a better vector db than what's out there but will it be better enough? A startup going through YC now could spend 2-3 to get a really good product and find customers and that is forever in a world where everybody wants to build AI applications right now.
-
Code Search with Vector Embeddings: A Transformer's Approach
As the size of the codebase grows, storing and searching through embeddings in memory becomes inefficient. This is where vector databases come into play. Tools like Milvus, Faiss, and others are designed to handle large-scale vector data and provide efficient similarity search capabilities. I've wrtten about how to also use sqlite to store vector embeddings. By integrating a vector database, you can scale your code search tool to handle much larger codebases without compromising on search speed.
-
Unum: Vector Search engine in a single file
But FAISS has their own version ("FastScan") https://github.com/facebookresearch/faiss/wiki/Fast-accumula...
-
Introduction to Vector Similarity Search
https://github.com/facebookresearch/faiss
-
Any Suggestions on good open source model for Document QA which we can run on prod ? 13b + models?
Not a model, but I would use this Dense Passage Retrieval for Open Domain QA simply fine-tuning two BERT models, one for questions and one for queries, and then fine-tuning using contrastive loss between positive key/value pairs of document embeddings (the [CLS]) token. You can then use a vector database (Like Faiss, Elasticsearch, Vespa or similar) for querying the question.