MLOps / AI 工程

SQL Server MCP with RAG capabilities for Windows (native ODBC support)

Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

Transform rough prompts/ideas into production-ready LLM prompts. Use when crafting, refining, or optimizing prompts for any AI model (Claude, GPT, Llama, etc.) with advanced techniques like CoT, constitutional AI, RAG optimization.

Low-memory file2file quantization for very large safetensors LLMs that cannot be loaded whole. Use when the user wants to run file2file quantization, adapt a new safetensors checkpoint without loading the full model, register an external LLMTemplate, inspect sharded checkpoint naming, generate wrap…

PayPerQ AI API via Lightning. Use for LLM access without subscriptions or API key management.

MCP server for AI-enhanced prompt engineering and request conversion.

查询已发布智能体列表供 LLM 选择，再按指定智能体名称发起对话并返回回答。

Your purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, piping and intermediate processing where helpful. You can access the API directly, as well as use the hf command line tool.

AI-first application patterns, LLM testing, prompt management

3 asamali LLM Council pipeline - gorusler, peer review, baskan sentezi

Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastru…

Use for drafting service listings, landing pages, marketplace descriptions, case-study shells, and catalog entries.

Using ChatGoogleGenerativeAI, a chat model wrapper from langchain for Google Gemini series, for various applications including file processing.

Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.

Affine miners submit HuggingFace model snapshots. The validator-side scheduler deploys submitted models, samples them against the current champion, and writes winner-takes-all weights.

You are an expert in developing machine learning models for chemistry applications using Python, with a focus on scikit-learn and PyTorch.

Local episodic memory engine with Go sidecar for Gemini embeddings

TensorFlow and deep learning rules for building, training, evaluating, and deploying neural network models

RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.

Connect to Hugging Face Hub and thousands of Gradio AI Applications

Semantic document memory using Redis vector store. Save and recall files with natural language.

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

Tenant aggregation collects and summarizes LLM costs by tenant, feature, route, and time windows. It enables multi-tenant SaaS applications to track costs per customer, identify expensive features, and enforce budget limits.

- [[AI agents]] - [[AI engineering]] - [[Model context protocol]] - [[Retrieval augmented generation]] - [[Claude]] -

This file contains links and resources related to Agent Skills.

This document outlines the detailed skill sets and capabilities possessed by the Agentic RAG system, categorized by executive functions and data processing abilities.

Quantum machine learning and differentiable quantum computing

Fine-tunes LLMs and trains custom models using LoRA/QLoRA adapters, JSONL training datasets, hyperparameter configuration, RLHF, DPO, and model quantization.