# rag-decline-context-windows-2025-10-08

## Veille

RAG decline - Expansion of AI context windows - LinkedIn

## Titre Article

From RAG to Rigor Mortis: Why Retrieval-Augmented Generation looks like dying

## Date

2025-10-08

## URL

https://www.linkedin.com/pulse/from-rag-rigor-mortis-why-retrieval-augmented-looks-like-ensarguet-txide/

## Keywords

Retrieval-Augmented Generation (RAG), AI context windows, Agentic AI, Large Language Models (LLMs), AI technology evolution, Context search strategies

## Authors

Philippe Ensarguet

## Ton

**Profile:** Professional | Analytical with strong opinion | Opinion-Analytical | Intermediate-Accessible

Ensarguet adopts a more provocative tone than in his other LinkedIn articles. A punchy title ("From RAG to Rigor Mortis") and a controversial thesis (RAG decline) reveal a thought leader taking a firm stance. Language remains accessible despite technical concepts (context windows, LLMs). Characteristic style of LinkedIn posts aiming for engagement through counterintuitive theses rather than cautious consensus. Targets a tech audience curious about forward-looking analyses.

## Pense-betes

- RAG was a temporary solution to limited context windows
- Context windows are evolving from 8K to potentially millions of tokens
- 5 major RAG challenges: chunking, embeddings, hybrid search, reranking, infrastructure complexity
- Key quote: "RAG was never the destination—it was a temporary detour"
- Emergence of IA agentique and direct in-context search
- The skills for building AI systems are evolving rapidly

## RésuméDe400mots

The article examines the potential decline of Retrieval-Augmented Generation (RAG) in the face of the rapid evolution of AI technology. The author explains how RAG emerged as a solution to the limited context windows of early AI models, enabling systems to retrieve and use relevant document fragments. However, with the rapid expansion of context windows in modern AI models (growing from 8K to potentially millions of tokens), RAG could become obsolete.

The article highlights five key challenges of RAG that contribute to its potential decline. First, document chunking loses contextual meaning, artificially fragmenting information. Second, embedding technologies have inherent limitations in their ability to fully capture the semantic richness of content.

Third, hybrid search adds unnecessary complexity to the information retrieval process. Fourth, reranking introduces additional latency and costs into the processing pipeline. Finally, managing RAG infrastructure is becoming increasingly complex and costly to maintain.

The author argues that emerging technologies such as Claude Code demonstrate a shift toward direct, context-rich search, without complex retrieval mechanisms. Since AI models can now handle entire documents within their context windows, elaborate RAG infrastructure could become superfluous.

This evolution represents a paradigm shift in how AI systems are designed and built. Rather than fragmenting and retrieving information, future systems will be able to process vast amounts of context directly, enabling a more holistic and nuanced understanding.

The article notes that this transition has significant implications for organizations and developers who have invested heavily in RAG infrastructure. The skills required to build AI systems are evolving, shifting from complex retrieval engineering toward designing agentic systems capable of intelligently navigating large contextual spaces.

The author suggests that organizations must prepare for this technological transition, recognizing that RAG was only an intermediate stage in the evolution of AI. Future systems will favor full-context understanding over fragmented retrieval.

The central quote perfectly captures this perspective: "RAG was never the destination—it was a temporary detour." This statement encapsulates the idea that RAG was a pragmatic solution to technical limitations that are now being overtaken by rapid technological innovation.

In conclusion, the article calls for a reassessment of current AI architectures and anticipation of emerging paradigms that will replace traditional RAG approaches.

## GrapheDeConnaissance

- Philippe Ensarguet —affirme_que→ le RAG est en déclin structurel (AFFIRMATION, 0.98)
- Nicolas Bustamante —publie→ The RAG Obituary (DOCUMENT, 0.97)
- Nicolas Bustamante —dirige→ Fintool (ORGANISATION, 0.95)
- RAG —résout→ fenêtres de contexte (CONCEPT, 0.95)
- cascade d'échecs en cinq étapes —observé_dans→ RAG (TECHNOLOGIE, 0.93)
- Claude Code —remplace→ RAG (TECHNOLOGIE, 0.88)
- Claude Code —utilise→ grep et glob (TECHNOLOGIE, 0.96)
- Anthropic —publie→ Claude Code (TECHNOLOGIE, 0.97)
- fenêtres de contexte —mesure→ passage de 8K à 2M tokens (MESURE, 0.97)
- IA agentique —remplace→ RAG (TECHNOLOGIE, 0.9)
- IA agentique —utilise→ nouvelles compétences techniques (CONCEPT, 0.92)
- Philippe Ensarguet —prédit→ l'expansion des contextes LLM rendra le RAG obsolète (AFFIRMATION, 0.85)
- Gemini 2.5 —mesure→ 1M tokens de contexte (MESURE, 0.95)

---
Canonical: https://www.thekb.eu/en/fiches/rag-decline-context-windows-2025-10-08/