한국어EN
RAG, Fine-Tuning & ContextOpenAI

OpenAI announces GPT-4 Turbo 128K and Assistants API Retrieval

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

GPT-4 Turbo 128K and Assistants API Retrieval announced

Why it matters

The turning point at which homemade RAG pipelines began to be absorbed into built-in platform features

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

Officialopenai.comhttps://openai.com/index/new-models-and-developer-products-announced-at-devday/

Added in Week 35, 2026 · See that week

On the map — ② RAG, Fine-Tuning line

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

In the model family tree — GPT family · 23 versions

  1. Earlier versionGPT-4V(ision)
  2. This recordGPT-4 Turbo
  3. Later versionGPT-4o
See the whole GPT family

Same week

Rethinking Benchmark and ContaminationPaperDevDayOfficial

Nearby on the same axis

Anthropic releases Claude 2.1 with a 200K-token contextOfficialGreg Kamradt publishes the needle-in-a-haystack long-context recall stress testPressSelf-RAG publishedPaperMemGPT publishedPaper