Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM...
cat ~/신규
마켓플레이스에 추가된 최신 스킬 둘러보기
17,526 스킬
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating...
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local...
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse...
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats,...
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems...
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic...
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG...
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense +...
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors,...
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text...
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors),...
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI,...
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents...
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents,...
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps,...
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile...
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments...
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production...
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production...
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs,...
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment,...
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend...
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking...