한국어EN
RAG, Fine-Tuning & ContextGoogle DeepMind

Gemini 1.5 Pro

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Gemini 1.5 Pro — 128K standard, 1 million tokens in preview

Why it matters

Context length jumped by an order of magnitude, sparking the RAG-is-dead debate

Source — Primary sources first; secondary reports are labelled “Press”

Officialblog.googlehttps://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/

Added in Week 35, 2026 · See that week

On the map — ② RAG, Fine-Tuning line

  1. Previous stopGPT-4 Turbo
  2. This record · stopGemini 1.5 Pro
  3. Next stopPrompt caching
See it on the map

In the model family tree — Gemini family · 21 versions

  1. Earlier versionGemini 1.0
  2. This recordGemini 1.5 Pro
  3. Later versionGemini 2.0 Flash
See the whole Gemini family

Same week

Chain-of-Thought Reasoning Without Prompting publishedPaperOpenAI announces Sora with a technical reportOfficialMicrosoft Research publishes GraphRAG blog postOfficial

Nearby on the same axis

RAPTOR publishedPaperCorrective RAG publishedPaperRULER publishedPaperAnthropic releases Claude 2.1 with a 200K-token contextOfficial