Search Results for "vector space"
Sort By:
Showing 61 open source projects for "vector space"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
UForm
Multi-Modal Neural Networks for Semantic Search, based on Mid-Fusion
UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space! It comes with a set of homonymous pre-trained networks available on HuggingFace portal and extends the transfromers package to support Mid-fusion Models. Late-fusion models encode each modality independently, but into one shared vector space. Due to independent encoding late-fusion models are good at capturing coarse-grained features but often neglect fine-grained ones. ... -
2
Vearch
A distributed system for embedding-based vector retrieval
Vearch is the vector search infrastructure for deep learning and AI applications. Vearch is a distributed vector storage and retrieval system which can be easily extended to billions scale. Vearch implements a high-performance, lockless real-time vector indexing subsystem that utilizes various optimization techniques to support millisecond vector update and retrieval. -
3
BasicBSpline.jl
Basic (mathematical) operations for B-spline functions
Basic (mathematical) operations for B-spline functions and related things with Julia. -
4
Linfa
A Rust machine learning framework
linfa aims to provide a comprehensive toolkit to build Machine Learning applications with Rust. Kin in spirit to Python's scikit-learn, it focuses on common preprocessing tasks and classical ML algorithms for your everyday ML tasks. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
gensim
Topic Modelling for Humans
Gensim is a Python library for topic modeling, document indexing, and similarity retrieval with large corpora. The target audience is the natural language processing (NLP) and information retrieval (IR) community. -
6
Semantic Router
Superfast AI decision making and processing of multi-modal data
Semantic Router is a superfast decision-making layer for your LLMs and agents. Rather than waiting for slow, unreliable LLM generations to make tool-use or safety decisions, we use the magic of semantic vector space — routing our requests using semantic meaning. Combining LLMs with deterministic rules means we can be confident that our AI systems behave as intended. Cramming agent tools into the limited context window is expensive, slow, and fundamentally limited. Semantic Router enables lightning-fast and cheap tool usage that can scale to many thousands of tools. ... -
7
export_fig
A MATLAB toolbox for exporting publication quality figures
export_fig is a MATLAB toolbox designed to simplify high-quality figure export from MATLAB, faithfully preserving visual appearance as seen on-screen—including size, colours, fonts, and layout—while offering precise control over output formats such as PNG, PDF, EPS, and more. Exporting a figure from MATLAB the way you want it (hopefully the way it looks on screen), can be a real headache for the unitiated, thanks to all the settings that are required, and also due to some eccentricities... -
8
PyMC3
Probabilistic programming in Python
...PyMC3 includes a comprehensive set of pre-defined statistical distributions that can be used as model building blocks. Sometimes an unknown parameter or variable in a model is not a scalar value or a fixed-length vector, but a function. A Gaussian process (GP) can be used as a prior probability distribution whose support is over the space of continuous functions. PyMC3 provides rich support for defining and using GPs. Variational inference saves computational cost by turning a problem of integration into one of optimization. PyMC3's variational API supports a number of cutting edge algorithms, as well as minibatch for scaling to large datasets. -
9
Qwen3-VL-Embedding
Multimodal embedding and reranking models built on Qwen3-VL
Qwen3-VL-Embedding (with its companion Qwen3-VL-Reranker) is a state-of-the-art multimodal embedding and reranking model suite built on the open-sourced Qwen3-VL foundation, developed to handle diverse inputs including text, images, screenshots, and videos. The core embedding model maps such inputs into semantically rich vectors in a unified representation space, enabling similarity search, clustering, and cross-modal retrieval. The reranking model then precisely scores relevance between a... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
HCubature.jl
Pure-Julia multidimensional h-adaptive integration
The HCubature module is a pure-Julia implementation of multidimensional "h-adaptive" integration. then hcubature(f, a, b) computes the integral, adaptively subdividing the integration volume into smaller and smaller pieces until convergence is achieved to the desired tolerance (specified by optional rtol and atol keyword arguments. Because hcubature is written purely in Julia, the integrand f(x) can return any vector-like object (technically, any type supporting +, -, * real, and norm: a Banach space). You can integrate real, complex, and matrix-valued integrands, for example. Note that HCubature assumes that your function f(x) can be computed at arbitrary points in the integration domain. (This is the ideal way to do numerical integration.) ... -
11
WavTokenizer
SOTA discrete acoustic codec models with 40/75 tokens per second
...The model uses a single-quantizer design together with temporal compression to achieve extreme compression without sacrificing reconstruction fidelity. Its architecture incorporates a broader vector-quantization space, extended contextual windows, and improved attention networks, combined with multi-scale discriminators and inverse Fourier transform blocks to enhance waveform reconstruction. Extensive experiments show that WavTokenizer matches or surpasses previous neural codecs across speech, music, and general audio on both objective metrics and subjective listening tests. -
12
Mapbox GL JS
Interactive, thoroughly customizable maps in the browser
Mapbox GL JS is a JavaScript library that uses WebGL to render interactive maps from vector tiles and Mapbox styles. It is part of the Mapbox GL ecosystem, which includes Mapbox Mobile, a compatible renderer written in C++ with bindings for desktop and mobile platforms. Mapbox GL JS is part of the cross-platform Mapbox GL ecosystem, which also includes compatible native SDKs for applications on Android, iOS, macOS, Qt, and React Native. Mapbox provides building blocks to add location... -
13
LDPatternCreator
Create and edit patterned parts quick and easy.
..... - RAM: 500 MB - Video-Memory: 256 MB - Free Disk Space: 5 MB - .NET-Framework (Version >= 2.0) Recommended Requirements: - Operating System: Windows 7 or 10 - CPU: Multicore-Processor e.g. Intel Core 2 Duo or AMD Athlon II (>=2,0Ghz) - RAM: >1.500 MB - Video-Memory: 256 MB - Free Disk Space: 100 MB - .NET-Framework (Version >= 2.0 until 1.4.7 / 4.0 for >1.5.0) Note to users of versions lesser than 1.5.7: You’ll need administrator privileges to install the software. -- Developed in Germany by Nils Schmidt - nilsschmidt1337 -
14
C++ Eigenvectors
C++ matrix class template with eigenvectors
...x*I - A = Q*B where Q is unitary and B is upper triangular. If x is an eigenvalue of A, there must be at least one zero on the diagonal of B. An eigenvector of A will be a vector in the null space of B. The upper triangular form of B makes finding its null vectors easy. For a zero on the diagonal of B, make the eigenvector have a 1 at that row, zeros below, and work upwards. -
15
Fosite - advection problem solver
numerical simulation code for solving transport equations in 1D/2D/3D
...This allows for high performance on modern architectures (SIMD). It is parallelized and vectorized. The software is thereby optimized for the NEC SX-Aurora TSUBASA Vector Engine . -
16
...Zgoubi simulates beam dynamics and polarization in a variety of accelerators (storage ring, synchrotron, cyclotron, betatron, microtron, FFAG, multi-pass ERL, etc) and optical systems (beam lines, magnetic and electrostatic optical components, time-of-flight and mass spectrometers, etc). The code includes built-in fitting procedures with a wide variety of constraints; stochastic SR energy loss; the tracking of synchrotron radiation (SR) Poynting vector; space charge models; various Monte Carlo procedures, etc. Contact: francoisgmeot@gmail.com Documentation (History of accelerators that zgoubi deals with, theory, tutorials): https://link.springer.com/book/10.1007/978-3-031-59979-8 https://link.springer.com/book/10.1007/978-3-031-16715-7, Chap. 14.
-
17
Photon
A graphing calculator that's both powerful and easy to use.
Photon is a fully functional graphing calculator capable of numeric calculations as well as graphing functions, including parametric and polar graphs. In addition to regular graphing, Photon can plot integrals, first and second derivatives, tracing, animation, matrix math, and degree / radian mode. Photon can find roots, minimums and maximums, points of inflection, and it can fit several types of best fit lines and curves to data sets. Log and semi-log graphing are also... -
18
LakhCleanAnalysis
Tools to analyze the Lakh Clean Midi Dataset
...Presently, we are analyzing the note onset distribution, the pitch class distribution, and the midi program assignments for the entire dataset. Each of these entities are represented by a separate vector for each midi file. These vectors were clustered using the kmeans and HDBSCAN algorithms. The vectors (midi files) were projected into a two dimensional space using the UMAP algorithm. A user interface, umapPlot.tcl is provided to explore this space. -
19
RAGxplorer
Open-source tool to visualise your RAG
RAGxplorer is an open-source visualization tool designed to help developers analyze and understand Retrieval-Augmented Generation (RAG) pipelines. Retrieval-augmented generation combines language models with external document retrieval systems in order to produce more accurate and grounded responses. However, RAG systems can be complex because they involve multiple components such as embedding models, vector databases, and retrieval algorithms. RAGxplorer provides visual tools that allow... -
20
Annoy
Approximate Nearest Neighbors in C++/Python optimized for memory usage
Annoy (Approximate Nearest Neighbors Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mmapped into memory so that many processes may share the same data. There are some other libraries to do nearest neighbor search. Annoy is almost as fast as the fastest libraries, (see below), but there is actually another feature that really sets Annoy apart: it has the... -
21
Pattern
Web mining module for Python, with tools for scraping
...In addition to data mining features, the library offers natural language processing functionality including part-of-speech tagging, sentiment analysis, and n-gram extraction. The framework also includes machine learning algorithms that support classification, clustering, and vector space modeling for text analysis tasks. Another component of the library provides tools for analyzing and visualizing networks, making it useful for studying relationships between entities in large datasets. -
22
Frappe Charts
Simple, responsive, modern SVG Charts with zero dependencies
GitHub-inspired simple and modern SVG charts for the web with zero dependencies. An axis chart is generally a 2D rendition of data, where a set of values corresponds to every point in a dataset. That's why, data is the most important component for a chart. A chart can have multiple datasets. In an axis chart, every dataset is represented individually. Frappe Charts are responsive, as they rerender all the data in the current available container width. In order to set the bar width, instead... -
23
vue-content-loader
SVG component to create placeholder loading
vue-content-loader provides SVG “skeleton screen” components for Vue applications, letting you show animated placeholders that mimic your layout while real content loads. Skeletons reduce perceived waiting time and help prevent layout shifts by reserving space for images, text blocks, and cards. The library exposes composable, declarative shapes so you can approximate your final UI without pixel-perfect templates. Because it renders as vector graphics, the output is crisp on all screens and cheap to animate. It’s easy to theme and reuse across a design system, keeping loading states consistent throughout a product. ... -
24
hora
Efficient approximate nearest neighbor search algorithm collections
...These vectors are commonly generated by neural networks to represent images, text, audio, or other data types in a mathematical embedding space. The library is written in Rust and emphasizes performance, safety, and efficient memory management, making it suitable for production-grade applications requiring low latency and high throughput. -
25
The library provids two services: 1. Orientational analysis, i.e. compile time analysis for dimensions indicating a direction in space. 2. Aggregation of values carrying orientational dimensions into a data structure suitable to represent vectors