Skill UI

The official SDK for interacting with Azure AI Search service using Python. It provides comprehensive functionality for advanced search retrieval, including full-text search, vector similarity search (HNSW), hybrid search, and semantic ranking. Use this tool to build sophisticated enterprise search applications that require deep content understanding and precise information retrieval.

FAISS (Facebook AI Similarity Search) is a library designed for efficient similarity search and clustering of dense vectors. It supports indexing and searching on billions of vectors at scale, featuring GPU acceleration and multiple index types (Flat, IVF, HNSW, PQ) to balance speed and accuracy. It is essential for building high-performance, large-scale applications requiring fast k-NN retrieval or pure vector similarity matching, especially in fields like RAG and recommendation systems.

Expert capability for designing and implementing complex semantic search systems using vector databases. Proficient in embedding strategies, index optimization (HNSW, IVF), and advanced retrieval methods like RAG and hybrid search. Masters major platforms including Pinecone, Weaviate, Qdrant, Milvus, and pgvector for building sophisticated recommendation and similarity search applications.

This comprehensive guide outlines best practices for optimizing vector indexes for production systems. It covers critical techniques such as tuning HNSW parameters, implementing quantization strategies, and optimizing memory usage. Use this when you need to balance search latency, recall, and scalability for large-scale vector databases.

A comprehensive guide for optimizing query latency in Qdrant. This resource explains advanced performance tuning techniques, focusing on critical resource management like RAM utilization, segment count adjustments, and HNSW parameter tuning. It details strategies for scaling, quantization, and hardware considerations (e.g., local NVMe) to ensure consistently low-latency search performance, and outlines common pitfalls to avoid.

A comprehensive guide to diagnosing and fixing performance bottlenecks when using Qdrant. Covers optimizing slow uploads, resolving stuck optimizers, and tuning HNSW parameters, including best practices for sharding, bulk loading, and multi-tenant indexing to ensure efficient vector search performance.

A comprehensive guide for diagnosing and reducing high memory consumption in Qdrant. This resource is crucial when dealing with reports of 'memory leak', 'out of memory', or excessive RAM growth. It details how Qdrant manages resident memory and OS page cache, and provides advanced techniques such as quantization, using float16/int8 data types, and strategically storing components on disk (like HNSW indexes or sparse vectors) to minimize the memory footprint and ensure stable, scalable operation.

A comprehensive guide to diagnosing and enhancing search relevance within Qdrant. This skill addresses reported issues such as low precision, low recall, or irrelevant matches. It guides users through determining if the problem lies in the embedding model, Qdrant configuration, or the query strategy. Techniques covered include optimizing chunk splitting, tuning HNSW parameters, implementing hybrid search, and utilizing reranking for superior result quality.

Provides a systematic guide for diagnosing and improving poor search quality in vector databases like Qdrant. This guide covers troubleshooting issues such as low recall, when approximate search degrades, selecting optimal embedding models, and correctly tuning HNSW parameters, quantization, and filtering strategies. Essential for optimizing RAG and semantic search pipelines.

A comprehensive guide for diagnosing and resolving slow search performance in Qdrant. This resource covers issues related to low QPS (throughput), high latency for single queries, and slow filtered searches. Solutions include tuning HNSW parameters, managing memory pressure, implementing quantization, optimizing indexing, and configuring cluster settings for maximum efficiency.

This tool formats prompts for various Large Language Model (LLM) providers, including Anthropic, OpenAI, Gemini, and Ollama. It is essential for building robust Retrieval-Augmented Generation (RAG) pipelines. Users can format messages, create HNSW indexes from documents, route relevant context, and manage provider status, ensuring compatibility across different AI ecosystems.

This tool ingests raw market data (OHLCV) for a specified symbol. It normalizes the data into relative OHLCV vectors, converts these vectors into high-dimensional embeddings, and then stores and indexes them using HNSW. This process prepares the data for fast, similarity-based pattern detection and advanced financial time series analysis.