Search Results for "construct" - Page 2
Sort By:
157 projects for "construct" with 1 filter applied:
-
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.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
Integrant
Micro-framework for data-driven architecture
Integrant is a minimalistic micro-framework for building applications following a data-driven architecture. It lets you define system components declaratively as configuration data and handles lifecycle actions (init, halt, resume) in dependency order, serving as a modern alternative to Component or Mount. Integrant was built as a reaction to fix some perceived weaknesses with Component. In Component, systems are created programmatically. Constructor functions are used to build records,... -
2
assistant-ui
Typescript/React Library for AI Chat
The assistant-ui project is an open-source TypeScript and React library designed to build production-grade AI chat interfaces quickly and efficiently. It provides a set of composable UI primitives that allow developers to construct fully customized conversational experiences without relying on monolithic components. The library handles complex behaviors such as streaming responses, auto-scrolling, accessibility, and real-time updates out of the box. It is designed to integrate with a wide range of AI backends and providers, making it highly flexible for different architectures. ... -
3
PeterCat
A conversational Q&A agent configuration system
...The system allows developers to build AI-powered bots that understand project documentation, GitHub issues, and other repository content in order to answer questions from users or contributors. By simply providing the repository name or URL, the platform can automatically collect relevant project information and construct a knowledge base that the agent uses to respond to inquiries. The framework also provides a configuration system that allows developers to customize how the conversational agent behaves and how it integrates with external services. PeterCat can be deployed as a self-hosted solution and offers an application SDK that enables integration with websites, developer portals, and community support platforms. -
4
Build Your Own OpenClaw
A step-by-step guide to build your own AI agent
Build Your Own OpenClaw is a step-by-step educational framework that teaches developers how to construct a fully functional AI agent system from scratch, gradually evolving from a simple chat loop into a multi-agent, production-ready architecture. The project is structured into 18 progressive stages, each introducing a new concept such as tool usage, memory persistence, event-driven design, and multi-agent coordination, with each step including both explanatory documentation and runnable code. ... -
Atera - an All-in-one platform for IT managementYour IT essentials, integrated & elevated. Take your IT management from automated to autonomous, download Atera's agent to start your free trial!
-
5
Text2Code for Jupyter notebook
A proof-of-concept jupyter extension which converts english queries
...The system uses natural language processing techniques to identify the intent of the query, extract relevant variables, and map the request to predefined code templates. Technologies such as sentence embeddings and named entity recognition are used to interpret user instructions and construct appropriate code outputs. -
6
TypeChat
Library for building type-safe natural language interfaces with LLMs
...TypeChat addresses these challenges by replacing traditional prompt engineering with a concept called schema engineering. Instead of writing complex prompts, developers define types that represent the intents supported by their applications. It then uses those type definitions to construct prompts for language models and translate user input into structured data that follows the defined schema. -
7
face.evoLVe
High-Performance Face Recognition Library on PaddlePaddle & PyTorch
...The project provides a comprehensive framework for building and training modern face recognition models using deep learning architectures. It includes components for face alignment, landmark localization, data preprocessing, and model training pipelines that allow developers to construct end-to-end facial recognition systems. The repository supports multiple neural network backbones such as ResNet, DenseNet, MobileNet, and ShuffleNet, enabling experimentation with different architectures depending on performance requirements. It also implements a wide range of loss functions commonly used in face recognition research, including ArcFace, CosFace, Triplet loss, and Softmax variants. ... -
8
SAG
SQL-Driven RAG Engine
...Documents are first decomposed into atomic semantic events, which are then represented using multidimensional natural language vectors. These vectors allow the system to identify relationships between concepts and construct a graph representation of knowledge at runtime. The architecture also includes a three-stage retrieval pipeline consisting of recall, expansion, and reranking steps to improve search accuracy. The engine integrates semantic vector similarity with traditional full-text search to improve both recall and precision. Because the knowledge graph is generated dynamically, the system can adapt to new information without requiring manual graph maintenance. -
9
LLMCompiler
An LLM Compiler for Parallel Function Calling
...Traditional LLM agent systems typically execute tool calls sequentially, which can create latency, higher costs, and reduced reliability when solving multi-step problems. LLMCompiler addresses this limitation by applying principles from classical compilers to analyze a task and construct an execution plan that allows multiple functions to run in parallel whenever possible. The framework builds a dependency graph of required operations, identifying which tasks must run sequentially and which can be executed simultaneously. Its architecture includes components such as a planning module that constructs the task graph, a task dispatcher that manages dependencies, and an executor that performs parallel calls. -
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.
-
10
LLM Workflow Engine
Power CLI and Workflow manager for LLMs (core package)
...Instead of focusing solely on chat interactions, the system is built to embed LLM calls into larger automation pipelines where model outputs can drive decision making or trigger additional processes. Developers can construct structured workflows using configuration files and integrate them with tools such as Ansible playbooks or custom scripts to automate complex tasks. The engine supports multiple AI providers through a plugin architecture, allowing connections to services like OpenAI, Hugging Face, Cohere, or other compatible APIs. -
11
illness index
illness_index A Computer Program of a Medical Textbook.
A computer scientist has attempted to program a textbook of British general practice (primary care) medicine, that is, Hodgkin K (1978) "Towards Earlier Diagnosis....", 4th Edition, Churchill Livingstone. If a patient types presenting findings (such as headache, cough), the program prompts the user for expansion/denial of appropriate findings, in order to construct a list of patient findings. The program also calculates a list of likely diseases, which the user can use the web to find out more about. The program has more than 600 diseases and 1000 findings. Brought to you by Kit Free Software 2024 Ltd. Keywords - disease, health, healthcare, illnesses, illnessindex, illness_index. -
12
Classnames
A simple javascript utility for conditionally joining classNames
Classnames is a minimal JavaScript utility that helps you construct CSS class strings based on conditional logic. Instead of manually concatenating strings, developers can pass any combination of strings, arrays, or objects, and the library will output a clean, space-separated class list. When you provide an object, the keys represent class names and the boolean values determine whether each class should be included in the final string. -
13
RAGs
Build ChatGPT over your data, all with natural language
RAGs is an open-source application designed to simplify the creation of retrieval-augmented generation pipelines through an interactive interface. Built with Streamlit and powered by the LlamaIndex ecosystem, the tool allows users to construct AI assistants that answer questions using their own data sources. Instead of requiring extensive programming knowledge, the application allows users to configure and build a RAG system using natural language instructions. The system automatically generates pipeline configurations that control how documents are retrieved, processed, and summarized before being used by a language model to generate responses. ... -
14
ccgsl
Use Gnu Scientific Library as if it were writtem in C++.
The ccgsl provides simple C++ wrappers for the GNU Scientific Library. It uses Java-like shared-pointer classes in place of structs to avoid direct memory allocation/freeing and to work better with the STL. It lets you construct functions for optimisation, root-finding and the like from C++ member functions, making it easier to integrate with existing C++ code. It also provides C++ exceptions. -
15
EvidentialGene
Evidence Directed Gene Construction for Eukaryotes
EvidentialGene is a genome informatics project, "Evidence Directed Gene Construction for Eukaryotes", to construct high quality, accurate gene sets for animals and plants, developed by Don Gilbert at Indiana University, see http://arthropods.eugenes.org/EvidentialGene/ Construction refers to the combination of classical gene prediction, and more recent gene assembly (de-novo and genome-assisted) methods. The basic Evigene methods involve using available best-of-breed gene prediction and assembly software, combining all evidence for genes, from expressed sequences, genome assembly sequences, related species protein sequences, and any other, to annotate and score gene constructions. ... -
16
Learning Prompt
Free prompt engineering online course
Learning-Prompt is a curated repository of prompts, techniques, and instructional patterns designed to help people construct better prompts for AI systems, including generation, reasoning, and debugging tasks. It collects examples of effective prompt formats, chains of thought, strategy scaffolds, and comparative methods that help yield consistent, high-quality results. The project also includes meta-guidance: reflections on prompt failures, tips for prompt tuning, ways to mitigate model bias or misinterpretation, and how to adapt prompts for different AI capabilities. ... -
17
OK
Welcome to the future of programming languages
OK? is a modern, dynamically typed programming language created with a strong opinion: to remove needless complexity and help programmers write code that matters. It eliminates many common language features (e.g., ternary operators) in favour of a consistent, minimal syntax: for example it uses only switch statements for control flow and has only one comparison operator. OK? also treats errors as plain values (strings/arrays) and removes inheritance in favour of what it calls “evolution over... -
18
CoolingPower
Print Steam Tables; Plot diagrams and cycles from equations of state
...A couple of bugs have been discovered that severely affect the calculation accuracy. While I troubleshoot, use at your own risk. Once completed, CoolingPower will have the capability to plot diagrams of thermodynamic properties, construct Steam Tables, and plot thermodynamic cycles. Initial fluid will be water/steam, but functionality will extend to include a variety of working fluids. CoolingPower operates in GUI format and, for Unix-based machines, from the terminal. Fluid state properties and Steam Tables can be printed to the screen or to file. Compiling and execution utilizes the GNU Scientific Library derivative functions and the Boost.signals2 and Boost.bind libraries. ... -
19
Glicol
Graph-oriented live coding language and music/audio DSP library
Glicol is a graph-oriented live coding language and audio engine designed for real-time music creation and digital signal processing, written entirely in Rust. It introduces a unique paradigm where audio synthesis and sequencing are represented as interconnected nodes, allowing developers and musicians to construct complex sound pipelines through declarative code. The language is designed to be accessible to beginners while still offering powerful capabilities for advanced users, enabling both quick experimentation and precise control over audio generation. Glicol’s engine operates without garbage collection and is optimized for real-time performance, achieving sample-accurate audio synthesis across multiple platforms. ... -
20
MarvelHeroes
A sample Marvel heroes application based on MVVM
MarvelHeroes is a demo application based on modern Android application tech-stacks and MVVM architecture. Fetching data from the network and integrating persisted data in the database via repository pattern. -
21
joi-router
Configurable, input and output validated routing for koa
Easy, rich, and fully validated koa routing. koa-joi-router returns a constructor that you use to define your routes. The design is such that you construct multiple router instances, one for each section of your application which you then add as koa middleware. The route definition for the currently matched route is available via ctx.state.route. This object is not the exact same route definition object that was passed into koa-joi-router, nor is it used internally - any changes made to this object will not have an effect on your running application but is available to meet your introspection needs. ... -
22
Tux Math Scrabble
12÷16×3=9÷4
Latest version 0.9.1 runs on Python3. Date: June 15, 2023 Online/touch-screen version: https://www.asymptopia.com/tuxmathscrabble Encourages kids to construct compound equations and consider multiple abstract possibilities. -
23
Pinject
A pythonic dependency injection library
Pinject is a lightweight dependency-injection library for Python that favors explicit wiring and testability over magic. Instead of global singletons, you declare providers (bindings) that describe how to construct objects, and Pinject resolves the graph by inspecting call signatures. Its container supports constructor injection and fine-grained scoping so you can share expensive resources while keeping tests isolated. The library leans on Python’s introspection to minimize boilerplate, making it natural to adopt in codebases that already rely on type hints or keyword arguments. ... -
24
magicCss
CSS3 whimsy, single label implements various graphics
...The project serves primarily as an educational and inspirational collection for developers who want to push the boundaries of what can be achieved with native CSS capabilities. It explores advanced techniques such as gradients, blend modes, clip-path usage, and animation timing to construct visually rich UI elements without relying on images or JavaScript-heavy solutions. The repository is organized as a gallery of experiments, each illustrating a specific visual trick or pattern that can be studied and reused. By emphasizing minimal markup and clever styling, it encourages performance-conscious and elegant front-end design practices. ... -
25
Machine Learning with TensorFlow
Accompanying source code for Machine Learning with TensorFlow
...Many examples are structured as standalone scripts or notebooks that can be executed directly to reproduce the results described in the book. The code demonstrates how TensorFlow can be used to construct training pipelines, prepare datasets, and evaluate model performance.
