---
title: "RAG and Enterprise Search: Retrieval as a Platform, Not a Feature"
description: "Aleksandr Filippov builds retrieval-augmented generation and enterprise search systems — hybrid vector and full-text retrieval with reciprocal rank fusion, cross-encoder reranking, query decomposition and rewrites, two-layer parent-document storage, and multilingual query handling — shipped as shared platforms other products consume."
date: "2026-08-27T07:00:00Z"
last_updated: "2026-08-28"
build_time: "2026-08-28T03:11:43Z"
skill_name: "RAG & Enterprise Search"
skill_description: "Retrieval systems built as shared platforms — hybrid vector and full-text search fused with RRF, cross-encoder reranking, query decomposition, parent-document storage, and multilingual query handling, with quality calibrated from production retrieval telemetry."
skill_category: ["rag-search","ai-engineering"]
since: "2025-04-10"
last_used: "2026-08-28"
related_skills: ["artificial-intelligence","llm-engineering","langgraph","databases","python","mcp"]
related_projects: ["air-api","mcp-context-server","aila","agent-memory-context-benchmark"]
related_experience: ["ai-product-manager-at-spotware"]
keywords: ["Retrieval-Augmented Generation","RAG","Enterprise Search","Hybrid Search","Vector Search","Embeddings","Reciprocal Rank Fusion","Cross-Encoder Reranking","Query Decomposition","Semantic Search","Full-Text Search","Multilingual Retrieval","PostgreSQL","Python"]
license: "https://creativecommons.org/licenses/by/4.0/"
canonical: "https://www.alexfeel.info/skills/rag-enterprise-search/"
---

My retrieval skill is organized around a conviction the systems keep confirming: **the answer quality of a RAG product is decided in the retrieval layer, long before a model writes a word**. So that layer gets the engineering: chunking tuned to the corpus rather than a default window, embeddings chosen and swapped behind an abstraction, vector and full-text search run side by side and fused with **reciprocal rank fusion**, a **cross-encoder reranker** sharpening the fused top, and two-layer storage that matches on small semantic units while returning the parent document a reader actually needs. Queries get the same respect as documents — language detection, translation into the corpus language, complexity analysis, decomposition of compound questions, and multi-rewrite expansion, each as an explicit pipeline stage that can be observed and skipped rather than folded into one opaque prompt.

The proving ground is a **shared enterprise retrieval platform** that serves a company's knowledge corpus to support agents, analysts, developers, and other AI products through REST and MCP interfaces backed by one retrieval core — built as a platform deliberately, so every consumer inherits each retrieval improvement at once. The same discipline runs through my open-source work: a durable agent-memory server whose full-text, semantic, hybrid, and reranked retrieval modes are first-class and swappable, and — next — a benchmark that measures which of those modes actually earns its latency for agent memory workloads. Retrieval quality is watched rather than asserted: the pipeline's stages log their own score distributions, deduplication counts, and percentile bands, so quality is **calibrated from production evidence**; the reranking stage earned its place by raising relevance and cutting noise, and the benchmark I am designing next turns that calibration into measurement against ground truth. The systems are listed in the **Related Projects** and **Related Experience** panels above.


## Site index

- [llms.txt](https://www.alexfeel.info/llms.txt)
- [Complete index](https://www.alexfeel.info/llms-index.txt)