query-routing

Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da

DuckDB extension for system monitoring & intelligent SQL routing. 25+ functions for CPU, memory, disk, network, processes. Conditionally Route queries to PostgreSQL, MySQL, Snowflake, BigQuery with automatic dialect translation via SQLGlot. Pure Rust, cross-platform.

An intelligent, stateful Customer Support Agent built with LangGraph and LangChain. It categorizes incoming queries, analyses their sentiment, and either routes them to the right specialist handler or escalates negative-sentiment queries to a human agent.

Reference multi-tenant knowledge-base system using LlamaIndex, RAG, vector search, SQL generation, and query routing.

Reference architecture for legal contract intelligence, dual runtime (Azure / local docker)

Routes incoming prompts to the cheapest model tier that can handle them correctly, reducing inference cost while maintaining quality

Adaptive-AtomRAG

This project demonstrates the integration of multiple AI agents using Retrieval-Augmented Generation (RAG) and WikiSearch functionalities, along with Cassandra for data storage and retrieval.

Adaptive RAG pipeline with a lightweight DistilBERT query router for dynamic, latency-optimized retrieval strategies.

High-performance Hybrid RAG pipeline using LlamaIndex, MinerU, GLiNER, and LangExtract. Features advanced metadata enrichment, BM25-Vector fusion, and LaTeX-enabled synthesis for complex document analysis.

Routes queries to PostgreSQL, Redis, or pgvector by learning query intent instead of relying on hardcoded rules.

Database connection pooler and query router for the Servverse ecosystem — read/write splitting, slow query detection, multi-dialect support.

This repository implements an Advanced Retrieval-Augmented Generation (RAG) pipeline with context-aware query decomposition for high-quality information retrieval. It includes redundancy filtering, cross-encoder–based document reranking, and controlled generation.

An intelligent LLM routing system optimizing the cost-quality trade-off for RAG pipelines. Uses multi-tier semantic complexity scoring and embedding models to dynamically route queries.

A domain-agnostic, zero-dependency adaptive query router for RAG systems. Optimizes retrieval strategies using multi-signal statistical analysis of pilot scores.

An Adaptive Hybrid Retrieval Engine for Lexical, Sparse, Dense and Neural Search

Routes queries to the cheapest tier that answers correctly, cutting inference costs by over 50% while retaining 99.9% quality.

A Sports Club Management database project showcasing database design, SQL querying, data analysis, and a distributed sharding backend using SQLite, MySQL, and a Flask API router.

Search and relevance across four stores -- vector embeddings, graph, full-text and relational -- measuring the ROUTING DECISION rather than the retrieval alone: per-backend precision and recall, fan-out cost beside correctness, and the finding that a balanced evaluation set overstates federation by 2.4x versus a realistic query mix.