query-planning

build your own query planner

A high-performance spatial query layer for Polars

Run the PostgreSQL Explain Visualizer 2 (pev2) from the command line.

Cost-based relational query optimizer (CBO) evaluating nested loop, hash join, and sort-merge joins.

Cost-based relational query optimizer (CBO) evaluating nested loop, hash join, and sort-merge joins.

Index-aware planning proxy for Apache Iceberg REST catalogs: prunes data files on token and substring predicates that min/max statistics cannot, with no engine changes.

Spanning Tree-based Query Plan Enumeration

AI revision platform for university past papers, with PDF ingestion, hierarchical chunking, vector semantic search, query planning, and citation-grounded RAG study guide generation.

Active web-search RAG workbench with provider routing, source extraction, citation verification, and extractive fallback.

Query planning for bucket-limited time-series APIs — aggregate long ranges with a handful of source requests instead of thousands of per-bucket queries. 混合递归阶梯算法：用少量请求聚合长时间序列区间，替代逐桶查询。

PostgreSQL planner path probing extension for planner-aware SQL agents

LLM query planner that compiles natural-language questions over 1M+ rows of Boston open data into typed SQL, retrieval, or cross-dataset plans, benchmarked at 86.7% accuracy vs 20% for RAG baselines

Deterministic planner that picks which MQO pillar tools an NL question needs, in order, with a reason per step

Hands-on PostgreSQL guide with Docker labs covering internals, performance, replication, HA, backup/recovery, and advanced SQL

🏥 Modular Agentic RAG Medical Assistant 🤖 built with LangGraph, Pinecone, Groq & Tavily. It intelligently routes queries between RAG, live web search, and direct answers. 🔬 Live tracing shows every agent step, while FastAPI + Streamlit deliver a production-ready full-stack experience. 🚀

Implementation of the Count-Min-Sketch datastructure for cardinallity estimation on knowelege Graphs. Including experiments on how to reduce noise and make the estimation better.

This module covers techniques to optimize query execution, such as creating indexes, and query planning, that improve performance. It will also introduce tools and techniques for terminating inefficient queries that are consuming our database resources.

Agentic pipeline for natural-language question answering over federated RDF graphs, with SPARQL endpoint discovery, schema-aware query planning, validation retries, and SPIDER4FedSPARQL benchmarking.

Hermes: Ontology-based natural-language querying over knowledge graphs

Intelligence layer for AI agents. Query planning, context discovery, cost optimization. 60-75% token reduction while maintaining quality.