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.

Production-ready intelligent knowledge management system built with LlamaIndex. Enables organizations to query, analyze, and extract insights from multiple data sources (documents, databases, APIs) through natural language using advanced RAG capabilities, multi-tenant architecture, and specialized query engines: SQL generation /intelligent routing.

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

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.

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.

A sophisticated AI Agent combining RAG and Text-to-SQL via an LLM-based router. Built with LangChain and gpt-4o-mini to seamlessly toggle between unstructured AWS documentation (ChromaDB) and structured GitHub/StackOverflow analytics (SQLite).

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.

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

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.

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.

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