{"id":14964496,"url":"https://github.com/lm-kit/lm-kit-net-samples","last_synced_at":"2025-10-25T07:31:24.458Z","repository":{"id":250201708,"uuid":"833778397","full_name":"LM-Kit/lm-kit-net-samples","owner":"LM-Kit","description":".NET samples for LM-Kit.NET","archived":false,"fork":false,"pushed_at":"2025-02-04T21:01:40.000Z","size":2628,"stargazers_count":16,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-04T22:18:32.451Z","etag":null,"topics":["ai","dotnet","genai","gpt","llama","llm","lm-kit","nlp"],"latest_commit_sha":null,"homepage":"https://lm-kit.com/","language":"C#","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/LM-Kit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-07-25T18:18:12.000Z","updated_at":"2025-02-04T21:01:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"c9b4ac02-ae48-47da-a9f2-5af3116d502a","html_url":"https://github.com/LM-Kit/lm-kit-net-samples","commit_stats":{"total_commits":36,"total_committers":1,"mean_commits":36.0,"dds":0.0,"last_synced_commit":"5b0b3deba40cdbacd012ea95da48e4b9f4d9fe02"},"previous_names":["lm-kit/lm-kit-net-samples"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LM-Kit%2Flm-kit-net-samples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LM-Kit%2Flm-kit-net-samples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LM-Kit%2Flm-kit-net-samples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LM-Kit%2Flm-kit-net-samples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LM-Kit","download_url":"https://codeload.github.com/LM-Kit/lm-kit-net-samples/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238104535,"owners_count":19417152,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","dotnet","genai","gpt","llama","llm","lm-kit","nlp"],"created_at":"2024-09-24T13:33:16.048Z","updated_at":"2025-10-25T07:31:24.452Z","avatar_url":"https://github.com/LM-Kit.png","language":"C#","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎉 Claim Your Free Community License!\n\nGet started with the **LM-Kit Community Edition** today and gain access to powerful AI tools for free. Whether you're a hobbyist, startup, or open-source developer, the Community Edition is here to help you innovate and experiment without limitations.\n\n👉 [Claim Your Free License Now!](https://lm-kit.com/products/community-edition/)\n\n---\n\n# 🚀 **What's New**\n\n*Listed from most recent to oldest*\n\n- 🔧 [Tool Calling for Local Agents](https://lm-kit.com/blog/tool-calling-for-local-agents/) - Build AI agents with state-of-the-art tool calling. Supports all modes (simple, multiple, parallel) with structured JSON schemas, safety policies, and human-in-the-loop controls.\n- 🎙️ [Speech-to-Text Support](https://lm-kit.com/solutions/language-processing/speech-to-text/) - Convert spoken audio into highly accurate text transcripts, supporting 100 languages.\n- 🛡️ [Multimodal PII Extraction](https://lm-kit.com/solutions/content-analysis/#pii-extraction) - Identify and extract personally identifiable information from text and images for compliance.\n- 🏷️ [Multimodal Named Entity Recognition](https://lm-kit.com/solutions/content-analysis/#ner) - Detect and classify entities (people, organizations, locations, etc.) across text and images.\n- 🌐 Multimodal RAG with Reranking Support - Improve accuracy with multimodal retrieval-augmented generation and reranking.\n- 🧬 [New Built-in Vector Database Engine](https://lm-kit.com/blog/lmkit-made-embedding-storage-effortless/) - Store and Retrieve Embeddings at Any Scale.\n- 🔗 [New Vector Database Connector (Open Source, Qdrant Support)](https://github.com/LM-Kit/lm-kit-net-data-connectors) - Easily integrate semantic search and hybrid RAG pipelines.\n- 🧠 [Semantic Kernel Integration (Open Source)](https://github.com/LM-Kit/lm-kit-net-semantic-kernel) - Build intelligent workflows with Microsoft's Semantic Kernel + LM-Kit.NET.\n- 👁️ [LM-Kit Goes Multimodal: Introducing Vision Support](https://lm-kit.com/blog/lmkit-goes-multimodal/) - Image understanding now available.\n- 🎮 Vulkan Backend - Accelerated multi-GPU support for AMD, Intel, and NVIDIA.\n- 🧩 Function Calling Support - Dynamically invoke functions directly from model outputs.\n- ✨ [Dynamic Sampling – Up to 75% Error Reduction and 2x Faster Processing for LLMs](https://lm-kit.com/blog/introducing-dynamic-sampling/)\n  \n👉 [See full changelog](https://docs.lm-kit.com/lm-kit-net/guides/changelog.html)\n\n---\n\n# Enterprise-Grade .NET SDK for Integrating Generative AI Capabilities | Demo Repository\n\n\u003e **With LM-Kit.NET, integrating or building AI is no longer complex.**\n\n**LM-Kit.NET** is a **cross-platform SDK** that brings together **LLMs (Large Language Models)** and **SLMs (Small Language Models)** for an extensive range of AI functionalities. It enables **Quick-Start AI Agents**, supports **multi-agent orchestration**, and offers a consistent API for C# and VB.NET. Whether you want to customize existing AI agents or build new ones, LM-Kit.NET provides a robust and streamlined approach to modern AI development.\n\n**AI Agent Runtime for .NET**  \n\n### **Product Overview \u0026 API Reference**\nLM-Kit.NET delivers **Multimodal Generative AI** solutions for .NET, facilitating the creation and customization of AI Agents as well as comprehensive multi-agent coordination. Its capabilities, ranging from data processing, text analysis, and translation to text generation and model optimization—integrate smoothly into your .NET projects. By leveraging cutting-edge AI techniques, LM-Kit.NET empowers developers to build advanced solutions with minimal complexity.\n\n👉 Find additional documentation and detailed guides in the **LM-Kit Docs**:  [https://docs.lm-kit.com](https://docs.lm-kit.com)\n\n---\n\n## **Extensive Feature Set**\n\nLM-Kit.NET offers a wide array of advanced AI features that can be seamlessly integrated into your .NET applications:\n\n- **Interactive Question \u0026 Answering**  \n  Deliver concise responses to user queries, handling both single-turn and multi-turn interactions.\n\n- **Automated Text Generation**  \n  Dynamically create context-appropriate content tailored to your needs.\n\n- **Structured Text Creation**  \n  Enforce output formats using JSON schemas, grammar constraints, templates, or other structural rules.\n\n- **Grammar \u0026 Spelling Correction**  \n  Automatically enhance content quality by fixing errors in spelling and syntax.\n\n- **Style-Specific Rewriting**  \n  Adjust the tone or style of text to align with specific communication goals.\n\n- **Seamless Language Translations**  \n  Convert text between different languages without compromising context or accuracy.\n\n- **Speech-to-Text**  \n  Convert spoken audio into highly accurate text transcripts, supporting 100+ languages.\n\n- **Accurate Language Identification**  \n  Determine the original language of any given text with high precision.\n\n- **Concise Text Summaries**  \n  Produce clear, focused summaries from extensive documents for faster comprehension.\n\n- **Quality Assessment**  \n  Evaluate text quality using various metrics, ensuring relevance and clarity.\n\n- **RAG-Enhanced Generation**  \n  Elevate text output by retrieving pertinent information from external repositories.\n\n- **Dynamic Function Invocation**  \n  Invoke specialized functions in your application on-demand to handle diverse tasks.\n\n- **Semantic Embeddings**  \n  Transform textual or image data into meaningful numeric representations for improved retrieval and analysis.\n\n- **Customizable Data Extraction**  \n  Extract and organize information from diverse sources using flexible schemas.\n\n- **Tailored Classification**  \n  Assign text to predefined categories, streamlining workflows and content management.\n\n- **Sentiment \u0026 Emotion Analysis**  \n  Detect the emotional stance of text and pinpoint specific feelings.\n\n- **Sarcasm Detection**  \n  Recognize ironic or sarcastic nuances in written material.\n\n- **Keyword Mining**  \n  Isolate critical terms and phrases from large datasets with ease.\n\n- **Code Processing**  \n  Analyze and transform programming code for enhanced development efficiency.\n\n- **Image Analysis (Vision Support)**  \n  Extend AI capabilities to interpret and evaluate images.\n\n- **Multimodal Named Entity Recognition**  \n  Detect and classify entities (people, organizations, locations, etc.) across text and images.\n\n- **Multimodal PII Extraction**  \n  Identify and extract personally identifiable information from text and images for compliance.\n\n- **Model Quantization \u0026 Optimization**  \n  Streamline both LLMs and SLMs for faster inference and lower computational overhead.\n\n- **Fine-Tuning \u0026 LoRA Integration**  \n  Adapt base models to meet domain-specific needs, incorporating Low-Rank Adaptation (LoRA) for efficient training.\n\n- **And More…**  \n  Explore additional features to supercharge your AI-driven solutions.\n\n---\n\n## **Run Local LLMs and SLMs on Any Device**\n\nLM-Kit.NET is powered by [llama.cpp](https://github.com/ggerganov/llama.cpp), ensuring best-in-class performance across a variety of hardware setups with minimal configuration and zero external dependencies.  \nAll processing happens **on-device** (edge computing), giving you full control and tunability for inference. Additionally, LM-Kit.NET supports an expanding list of model architectures, including **GPT-OSS**, **Qwen**, **Gemma**, **DeepSeek**, **Granite**, **Llama**, **Phi**, and more.\n\n---\n\n## **Maximized Performance**\n\n### 1. 🚀 Optimized for a Variety of GPUs and CPUs\nLeverage **CUDA** on NVIDIA GPUs, **Metal** on Apple devices, and **Vulkan** for multi-GPU setups (AMD, Intel, NVIDIA), ensuring top-tier performance regardless of your hardware.\n\n### 2. ⚙️ Advanced Architectural Foundations\nEnjoy a core system optimized for diverse scenarios, with advanced caching and resource recycling that enables consistent high performance in single or multi-instance environments.\n\n### 3. 🌟 Unmatched Performance\nExperience up to **5x faster** inference speeds, backed by continuous refinements and rigorous benchmarking to keep you ahead of the competition.\n\n---\n\n## **Retain Complete Control Over Your Data**\n\nAll inference is performed locally, meaning **no data ever leaves your device**. This ensures:\n\n1. **Enhanced Privacy**  \n   Eliminates the need to send sensitive data to external servers.\n\n2. **Increased Security**  \n   Minimizes risks of interception or unauthorized access.\n\n3. **Faster Response Times**  \n   Reduces latency by avoiding remote server round trips.\n\n4. **Lower Bandwidth Usage**  \n   Cuts down on internet data transfer, ideal for limited connectivity.\n\n5. **Regulatory Compliance**  \n   Helps satisfy GDPR, HIPAA, and other data protection requirements by keeping data on-premises.\n\n---\n\n## **Easy Integration and Simple Deployment**\n\nLM-Kit.NET is distributed as a single **NuGet** package, making it incredibly easy to include in your .NET applications:\n\n1. **Streamlined Integration**  \n   No need for containers or complex setup—just a few clicks in Visual Studio or your preferred .NET IDE.\n\n2. **Direct In-Process Execution**  \n   Avoid the overhead of additional services or containers, reducing latency and simplifying deployments.\n\n3. **Efficient Resource Management**  \n   Operates within your existing .NET process, making it suitable for resource-constrained environments.\n\n4. **Enhanced Reliability**  \n   By steering clear of external dependencies, LM-Kit.NET offers stable and predictable performance.\n\n---\n\n## **Supported Operating Systems**\n\n- **Windows**: From Windows 7 to the latest release  \n- **macOS**: macOS 11 and above  \n- **Linux**: Distributions with glibc 2.27 or newer  \n\n---\n\n## **Supported .NET Frameworks**\n\n- **.NET 4.6.2** through **.NET 9**\n\n---\n\n## **Model Catalog**\n\nBrowse the [LM-Kit Model Catalog](https://docs.lm-kit.com/lm-kit-net/guides/getting-started/model-catalog.html) for a comprehensive list of **quantized models** tested and optimized for LM-Kit.NET. You can also seamlessly load models from Hugging Face repositories using the Hugging Face API, simplifying model discovery and deployment.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flm-kit%2Flm-kit-net-samples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flm-kit%2Flm-kit-net-samples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flm-kit%2Flm-kit-net-samples/lists"}