Search Results for "augmented" - Page 4
Sort By:
Showing 255 open source projects for "augmented"
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.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
AI Engineering Academy
Mastering Applied AI, One Concept at a Time
...The project aims to make complex AI concepts accessible by structuring them into progressive learning modules covering topics such as prompt engineering, retrieval-augmented generation, LLM deployment, and AI agents. Rather than focusing purely on theoretical explanations, the repository emphasizes hands-on understanding of how modern AI systems are designed, built, and deployed in real-world applications. It aggregates tutorials, conceptual explanations, diagrams, and example workflows that guide learners through the process of creating AI-powered products. ... -
2
JUDI.jl
Julia Devito inversion
...Wave equations in JUDI are solved with Devito, a Python domain-specific language for automated finite-difference (FD) computations. JUDI's modeling operators can also be used as layers in (convolutional) neural networks to implement physics-augmented deep learning algorithms thanks to its implementation of ChainRules's rrule for the linear operators representing the discre wave equation. -
3
BCEmbedding
Netease Youdao's open-source embedding and reranker models
BCEmbedding is NetEase Youdao’s open-source embedding and reranker model project for retrieval-augmented generation workflows. It includes an EmbeddingModel for semantic vector generation and a RerankerModel for refining and ordering search results. The project is optimized for bilingual and cross-lingual retrieval, especially across Chinese and English. It is used as a foundation for RAG systems such as QAnything and other Youdao products. -
4
Text Embeddings Inference
High-performance inference server for text embeddings models API layer
...It focuses on delivering fast and scalable embedding generation by leveraging optimized inference techniques and modern hardware acceleration. It is built to support transformer-based embedding models, making it suitable for tasks such as semantic search, clustering, and retrieval-augmented systems. It provides an API interface that allows developers to integrate embedding capabilities into applications without managing model internals directly. Text Embeddings Inference is optimized for throughput and low latency, enabling it to handle large volumes of requests reliably. It also emphasizes ease of deployment, often using containerization and configurable runtime options to adapt to different infrastructure setups. -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
DeepWiki Open
AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories
DeepWiki Open is an open-source, AI-powered wiki generator that automatically creates fully navigable, richly structured wiki documentation for GitHub, GitLab, or Bitbucket repositories by combining code analysis, vector embeddings, retrieval-augmented generation (RAG), and visualization tools. Users can enter a repository URL and the system will clone the project, build semantic embeddings of its codebase, extract architecture and relationships, generate human-readable documentation, and produce visual diagrams to help explain complex code structure. DeepWiki’s output turns raw repositories into interactive, web-style wikis complete with navigable sections, diagrams, and contextual explanations, making it easier for developers and collaborators to understand unfamiliar code. ... -
6
RAG Anything
RAG-Anything: All-in-One RAG Framework
RAG-Anything is an open-source unified framework that extends the Retrieval-Augmented Generation (RAG) paradigm to fully multimodal document and knowledge retrieval, enabling systems to ingest, parse, represent, and query rich content that includes text, images, tables, formulas, and other structured or visual elements. Traditional RAG systems are typically limited to text and cannot effectively work across heterogeneous document layouts, but RAG-Anything addresses this by modeling multimodal content in ways that preserve cross-modal relationships and semantic context, often treating content elements as interconnected knowledge entities rather than separate data silos. ... -
7
PaperQA2
High accuracy RAG for answering questions from scientific documents
PaperQA2 is a package for doing high-accuracy retrieval augmented generation (RAG) on PDFs or text files, with a focus on the scientific literature. See our recent 2024 paper to see examples of PaperQA2's superhuman performance in scientific tasks like question answering, summarization, and contradiction detection. In this example we take a folder of research paper PDFs, magically get their metadata - including citation counts and a retraction check, then parse and cache PDFs into a full-text search index, and finally answer the user question with an LLM agent. -
8
Advanced + Agentic RAG Cookbooks
Advanced RAG cookbooks for building accurate LLM applications
Athina AI’s RAG Cookbooks is a GitHub repository that showcases advanced and agentic Retrieval-Augmented Generation techniques for building more accurate AI applications. It provides ready-to-use notebooks, implementations, and explanations that help developers move from basic RAG setups to more sophisticated workflows. Athina AI’s RAG Cookbooks covers the full RAG pipeline, including indexing, retrieval, augmentation, and generation, while also addressing evaluation to measure accuracy and relevance. ... -
9
WebGLM
An Efficient Web-enhanced Question Answering System
WebGLM is a web-enhanced question-answering system that combines a large language model with web search and retrieval capabilities to produce more accurate answers. The system is based on the General Language Model architecture and was designed to enable language models to interact directly with web information during the question-answering process. Instead of relying solely on knowledge stored in the model’s training data, the system retrieves relevant web content and integrates it into the... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. ... -
11
Easy DataSet
A powerful tool for creating datasets for LLM fine-tuning
Easy DataSet is a comprehensive open-source tool designed to make creating high-quality datasets for large language model fine-tuning, retrieval-augmented generation (RAG), and evaluation as easy and automated as possible by providing intuitive interfaces and powerful parsing, segmentation, and labeling tools. It supports ingesting domain-specific documents in a wide range of formats — including PDF, Markdown, DOCX, EPUB, and plain text — and can intelligently segment, clean, and structure content into rich datasets tailored for downstream LLM training needs. ... -
12
Ciphey
Decrypt encryptions without knowing the key or cipher
Fully automated decryption/decoding/cracking tool using natural language processing & artificial intelligence, along with some common sense. You don't know, you just know it's possibly encrypted. Ciphey will figure it out for you. Ciphey can solve most things in 3 seconds or less. Ciphey aims to be a tool to automate a lot of decryptions & decodings such as multiple base encodings, classical ciphers, hashes or more advanced cryptography. If you don't know much about cryptography, or you want... -
13
React Force Graph
React component for 2D, 3D, VR and AR force directed graphs
React Force Graph is a collection of React components for displaying force-directed graph data across 2D, 3D, virtual reality, and augmented reality environments. It provides separate packages with consistent APIs for each visualization mode. Canvas and WebGL rendering are combined with force-based physics for dynamic graph layouts. Users can zoom, pan, drag nodes, and respond to hover or click interactions. Developers can customize node shapes, text, images, link styles, directional particles, geometries, and graph behavior. ... -
14
PixelRAG
The beginning of scalable pixel-native search
PixelRAG is a visual retrieval-augmented generation system that searches documents by how they look, not only by the text they contain. It renders web pages, PDFs, and images into screenshot tiles, then performs retrieval over those visual representations. This approach preserves layout, tables, charts, diagrams, infographics, and other visual structure that traditional HTML or text parsing can miss. -
15
React Native RAG
Private, local RAGs. Supercharge LLMs with your own knowledge base
React Native RAG is a local retrieval-augmented generation library for React Native applications. It lets mobile apps enhance language models with the user’s own knowledge base while keeping retrieval local. The library is modular, so developers can choose pieces such as LLM, embeddings, vector store, and text splitter components. It is also extensible, allowing teams to implement their own interfaces when they need custom model or storage behavior. -
16
LLPhant
A comprehensive PHP Generative AI Framework
...The framework focuses on usability by offering straightforward APIs for tasks like embeddings, question answering, and vector search, which are commonly required in real-world applications. It includes support for vector stores, enabling developers to build retrieval-augmented generation systems using structured or unstructured data. LLPhant also allows integration with external services and tools, making it possible to extend model capabilities beyond text generation into actionable workflows. -
17
MindWork AI Studio
Independent cross-platform desktop app for local and cloud LLMs
...The platform introduces a concept of “assistants,” which abstract prompting into reusable tools for tasks like translation, summarization, or document analysis, making it easier for non-technical users to leverage AI capabilities. It also incorporates advanced features such as retrieval-augmented generation, plugin extensibility, and support for multiple data sources, allowing users to integrate their own files and knowledge bases into conversations. -
18
NeMo Retriever Library
Document content and metadata extraction microservice
...It supports multiple extraction strategies for different document formats, balancing accuracy and throughput depending on the use case. Additionally, it can generate embeddings for extracted content and integrate with vector databases like Milvus, making it well-suited for retrieval-augmented generation pipelines. -
19
VideoRAG
"VideoRAG: Chat with Your Videos
VideoRAG is a retrieval-augmented generation (RAG) framework tailored for video content that enables AI systems to answer questions, summarize, and reason over long videos by combining visual embeddings with contextual search. The system works by first breaking video into clips, extracting visual and audio-textual features, and indexing them into embeddings, then using an LLM with a retriever to pull relevant segments on demand. -
20
TruLens
Evaluation and Tracking for LLM Experiments
...An easy-to-use interface that allows developers to compare different versions of their applications, facilitating informed decision-making and optimization. TruLens supports various use cases, including question-answering, summarization, retrieval-augmented generation, and agent-based applications. -
21
Generative AI Examples
Generative AI Examples is a collection of GenAI examples
...Detailed framework of composable building blocks for state-of-the-art generative AI systems including LLMs, data stores, and prompt engines. Architectural blueprints of retrieval-augmented generative AI component stack structure and end-to-end workflows. A four-step assessment for grading generative AI systems around performance, features, trustworthiness and enterprise-grade readiness. -
22
zola (né Gutenberg)
Fast static site generator in a single binary with everything built-in
A fast static site generator in a single binary with everything built in. Forget dependencies. Everything you need in one binary. Zola comes as a single executable with Sass compilation, syntax highlighting, table of contents and many other features that traditionally require setting up a dev environment or adding some JavaScript libraries to your site. The average site will be generated in less than a second, including Sass compilation and syntax highlighting. Zola renders your whole site... -
23
RuoYi AI
Enterprise AI platform for building, deploying, and managing apps
...It provides a unified framework for integrating multiple AI models from different providers, allowing teams to switch or combine models through a consistent interface without vendor lock-in. RuoYi AI includes built-in support for retrieval-augmented generation, enabling organizations to create secure, private knowledge bases with high-accuracy search and reasoning capabilities. It also offers visual workflow orchestration tools that allow users to design complex AI pipelines, automate tasks, and coordinate multi-agent systems for advanced decision-making scenarios. In addition to backend capabilities, RuoYi AI includes frontend components and administrative dashboards built with modern web technologies, making it a complete end-to-end solution. -
24
OpenAI .NET
The official .NET library for the OpenAI API
...It supports tool/function calling, structured outputs via JSON schema, audio input/output, image generation, embeddings, Whisper transcription, and assistants with retrieval augmented generation. -
25
VoltAgent
Open Source TypeScript AI Agent Framework
An AI Agent Framework provides the foundational structure and tools needed to build applications powered by autonomous agents. These agents, often driven by Large Language Models (LLMs), can perceive their environment, make decisions, and take actions to achieve specific goals. Building such agents from scratch involves managing complex interactions with LLMs, handling state, connecting to external tools and data, and orchestrating workflows. VoltAgent is an open source TypeScript framework...
