ann-benchmarks
CPython
Our great sponsors
ann-benchmarks | CPython | |
---|---|---|
50 | 1,310 | |
4,568 | 59,431 | |
- | 1.5% | |
8.1 | 10.0 | |
4 days ago | 4 days ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
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.
ann-benchmarks
- ANN Benchmarks
-
Approximate Nearest Neighbors Oh Yeah
https://ann-benchmarks.com/ is a good resource covering those libraries and much more.
-
pgvector vs Pinecone: cost and performance
We utilized the ANN Benchmarks methodology, a standard for benchmarking vector databases. Our tests used the dbpedia dataset of 1,000,000 OpenAI embeddings (1536 dimensions) and inner product distance metric for both Pinecone and pgvector.
-
Vector database is not a separate database category
Data warehouses are columnar stores. They are very different from row-oriented databases - like Postgres, MySQL. Operations on columns - e.g., aggregations (mean of a column) are very efficient.
Most vector databases use one of a few different vector indexing libraries - FAISS, hnswlib, and scann (google only) are popular. The newer vector dbs, like weaviate, have introduced their own indexes, but i haven't seen any performance difference -
Reference: https://ann-benchmarks.com/
-
How We Made PostgreSQL a Better Vector Database
(Blog author here). Thanks for the question. In this case the index for both DiskANN and pgvector HNSW is small enough to fit in memory on the machine (8GB RAM), so there's no need to touch the SSD. We plan to test on a config where the index size is larger than memory (we couldn't this time due to limitations in ANN benchmarks [0], the tool we use).
To your question about RAM usage, we provide a graph of index size. When enabling PQ, our new index is 10x smaller than pgvector HNSW. We don't have numbers for HNSWPQ in FAISS yet.
- Do we think about vector dbs wrong?
-
Vector Search with OpenAI Embeddings: Lucene Is All You Need
In terms of "All You Need" for Vector Search, ANN Benchmarks (https://ann-benchmarks.com/) is a good site to review when deciding what you need. As with anything complex, there often isn't a universal solution.
txtai (https://github.com/neuml/txtai) can build indexes with Faiss, Hnswlib and Annoy. All 3 libraries have been around at least 4 years and are mature. txtai also supports storing metadata in SQLite, DuckDB and the next release will support any JSON-capable database supported by SQLAlchemy (Postgres, MariaDB/MySQL, etc).
-
Vector databases: analyzing the trade-offs
pg_vector doesn't perform well compared to other methods, at least according to ANN-Benchmarks (https://ann-benchmarks.com/).
txtai is more than just a vector database. It also has a built-in graph component for topic modeling that utilizes the vector index to autogenerate relationships. It can store metadata in SQLite/DuckDB with support for other databases coming. It has support for running LLM prompts right with the data, similar to a stored procedure, through workflows. And it has built-in support for vectorizing data into vectors.
For vector databases that simply store vectors, I agree that it's nothing more than just a different index type.
-
Vector Dataset benchmark with 1536/768 dim data
The reason https://ann-benchmarks.com is so good, is that we can see a plot of recall vs latency. I can see you have some latency numbers in the leaderboard at the bottom, but it's very difficult to make a decision.
As a practitioner that works with vector databases every day, just latency is meaningless to me, because I need to know if it's fast AND accurate, and what the tradeoff is! You can't have it both ways. So it would be helpful if you showed plots showing this tradeoff, similar to ann-benchmarks.
-
Numbers every LLM Developer should know
There are very efficient algorithms for doing this, but of course it may still be expensive if your dataset is very large. See https://ann-benchmarks.com/ for some of the algorithms
CPython
-
PEP 744 – JIT Compilation
> It provides a meaningful performance improvement for at least one popular platform (realistically, on the order of 5%).
At first it will not provide a large boost, but it will set the foundations for larger gains in subsequent releases. They link a list of some proposed improvements already underway, with improvement estimates, at https://github.com/python/cpython/issues/115802
-
Featured Mod of the Month: Phil Ashby
After that, with the basics of software engineering understood, I would move on to a wider use language, with a bigger ecosystem to employ, most likely Python. This would expose me to large system design / distributed systems and architectural challenges...
-
Convert Images Into Pencil Sketch
Have you ever felt like your photos needed a little extra touch to stand out? Well, get ready because we're about to learn a cool Python trick! We're going to take ordinary photos and turn them into awesome pencil sketches using Python and OpenCV. This will make your pictures look like they were drawn by hand!
-
Crafting an Image to PDF Converter App Using Python
Have you ever found yourself in a situation where you needed to convert a bunch of images into a PDF file quickly and efficiently? Imagine the convenience of converting a series of images from your recent trip into a single PDF album with just a few clicks. In this article, we will cover the process of building an Image PDF Converter App using Python. With the help of libraries like tkinter, os, and Python Imaging Library (PIL), we'll walk through the process of creating a powerful tool that can streamline this task for you.
-
Calculator with GUI Using Python Tkinter
If you've ever wanted to learn how to use Python or if you already know a bit and want to try something new, then you're in the right place! In this article, we'll show you step-by-step how to make your very own calculator using Python's Tkinter library, a renowned Python library for creating graphical user interfaces. Tkinter stands out for its simplicity, versatility, and widespread use in the Python community. It doesn't matter if you're a total beginner or an experienced coder looking for a fun project, we'll guide you through everything you need to know.
-
Back to Basics - Pandas #1
Pandas is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language.
-
Backdoor in upstream xz/liblzma leading to SSH server compromise
Python for Windows bundles liblzma from this project, but it appears to be version 5.2.5 [0] vendored into the Python project's repo on 2022-04-18 [1], so that should be fine, right?
[0] https://github.com/python/cpython/blob/main/PCbuild/get_exte...
-
How to Develop a User Data Storage Registration Form Using Python.
When working in Visual Studio Code (VS Code), start by creating a new Python file for your registration form project. It's helpful to have separate files for different parts of your project.
-
Python Crash Course: A Beginner's Guide with Code Examples
Before we dive into coding, you'll need to install Python on your computer if you haven't already. Visit the official Python website at python.org and download the latest version for your operating system. Follow the installation instructions, and you'll be ready to go.
-
UUID or ULID: Awesomeness of Unique Identifiers!
Let's look briefly at each and peek at it's Python implementation...
What are some alternatives?
pgvector - Open-source vector similarity search for Postgres
RustPython - A Python Interpreter written in Rust
faiss - A library for efficient similarity search and clustering of dense vectors.
ipython - Official repository for IPython itself. Other repos in the IPython organization contain things like the website, documentation builds, etc.
Milvus - A cloud-native vector database, storage for next generation AI applications
Vulpix - Fast, unopinionated, minimalist web framework for .NET core inspired by express.js
tlsh
Visual Studio Code - Visual Studio Code
vald - Vald. A Highly Scalable Distributed Vector Search Engine
Automatic-Udemy-Course-Enroller-GET-PAID-UDEMY-COURSES-for-FREE - Do you want to LEARN NEW STUFF for FREE? Don't worry, with the power of web-scraping and automation, this script will find the necessary Udemy coupons & enroll you for PAID UDEMY COURSES, ABSOLUTELY FREE!
pgANN - Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.
Pandas - Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more