Skill UI

Expert in designing and implementing advanced Retrieval-Augmented Generation (RAG) pipelines. This role focuses on optimizing the entire information retrieval process—from document chunking and embedding model selection to vector database architectures and hybrid search strategies. The goal is to bridge the gap between raw knowledge documents and accurate LLM understanding, drastically reducing hallucination and enhancing context relevance for enterprise applications.

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.

gget is a CLI/Python client that unifies querying over 20+ bioinformatics databases, letting researchers fetch gene info, sequences, BLAST results, structures, and enrichment data interactively or within scripts.

Leverages PubChem’s PUG-REST API or PubChemPy to search 110M+ compounds by name, CID, or structure, fetch properties, perform similarity/substructure lookups, and access bioactivity or format conversions for cheminformatics workflows.

Provides access to USPTO PatentSearch, PEDS, TSDR, and related APIs for patent and trademark searches, examination history, assignments, citations, and litigation data, with helper scripts for Python-based IP research and portfolio insights.

gget is a CLI/Python client that unifies querying over 20+ bioinformatics databases, letting researchers fetch gene info, sequences, BLAST results, structures, and enrichment data interactively or within scripts.

A comprehensive guide to implementing advanced user behavior tracking and real-time data synchronization with Algolia. This guide demonstrates how to use the Insights API to track clicks, conversions, and views, and how to build event-driven pipelines using database change listeners (e.g., Prisma middleware) to keep your Algolia index perfectly synced with your core application data. Essential for deep search analytics and relevance tuning.

This comprehensive guide provides a production-ready reference architecture for implementing scalable search using Algolia. It details best practices for index design (including multi-index strategies), establishing robust data pipelines from source databases, structuring the service layer (search, indexing, settings), and integrating the frontend for optimal performance.

This guide provides three fundamental examples for integrating with the Notion API. It demonstrates how to search for existing pages, create new content within a database, and retrieve the newly created page's metadata. Ideal for developers starting a new Notion integration or implementing basic automated workflows.

A comprehensive tool for interacting with Notion via its API. It allows users to perform workspace-wide searches, run complex queries against structured databases using compound filters (AND/OR), retrieve specific pages, and deeply traverse and extract all nested block content. Supports pagination for handling large datasets, enabling full data visibility and structured data extraction.

This comprehensive guide details advanced strategies for managing time-series data and data retention in vector databases (like Qdrant). It is designed for scenarios where only recent data is relevant (e.g., social media feeds, news articles). Three core methods are presented: Shard Rotation (recommended for natural time boundaries), Collection Rotation (for per-period configuration needs), and Filter-and-Delete (for simple cleanup). The guide also covers hot/cold tiering to optimize performance.