Georgi Mammen Mullassery

Diagnose vector search problems in RAG/LLM systems. Hunt down why retrieval fails — embedding quality, vector search, BM25, reranker analysis.

Real-time LLM cost tracking and optimization — Rust core with Python API

Real-time LLM cost tracking and optimization — Rust core with Python API

Cost optimization middleware for multi-provider LLM usage

AI-Native LLM Training & Infrastructure Abstraction Library

Real-time LLM cost tracking and optimization — Rust core with Python API

Hunt down retrieval problems in RAG/LLM systems. Diagnose exactly which component failed and how to fix it.

Smart context provider for LLMs - Minimal, most-relevant knowledge based on query anticipation and semantic understanding

Multi-provider LLM token counter & cost calculator. Unified token counting and cost calculation across 20+ cloud providers and 10+ open-source APIs.

Intelligence engine for PDFs: selective retrieval, structure analysis, and token-efficient RAG