GPT Researcher 用 Jev 替换 embeddings，相关上下文比例从 46% 升至 73%
有人把 GPT Researcher 里的 embeddings 换成 Jev，28 个任务测试下来相关内容多了 59%，盲测 15 比 3 获胜，成本没变，仓库开源可以自己试。
Assaf Elovic 在 GPT Researcher 的 RAG 管线中把传统 embeddings 替换为 Jev，并在 SimpleQA 与开放式研究任务的 28 个测试上对比。结果显示相关上下文占比从 46% 提升到 73%，即多出 59%。盲测中 Jev 生成的报告以 15 比 3 获得更多偏好，每次报告成本保持不变。GPT Researcher 现已默认使用 Jev，不再依赖 embeddings，技术栈为 LangChain、Tavily 和 Jev。
retrieval is a decision problem, not just a similarity problem cool experiment from @assaf_elovic swapping embeddings for Jev in GPT Researcher - 73% vs 46% relevant context decision models will show up all over the harness x.com/assaf_elovic/s… Assaf Elovic @assaf_elovic Didn't expect this 🤯 We replaced embeddings with Jev in GPT Researcher's RAG pipeline and tested both on 28 research tasks from SimpleQA and open ended research. Jev beat embeddings on every quality measure we ran: - 59% more relevant context (73% vs 46%) - Reports preferred 15 to 3 in blind comparisons - Same cost per report GPT Researcher now runs on Jev by default, and no longer needs embeddings at all. All you need is @LangChain + @tavilyai +Jev for the perfect RAG system. Check out the repo here: github.com/assafelovic/gp… q Research: docs.gptr.dev/docs/gpt-resea… q 🔗 View Quoted Tweet 💬 12 🔄 2 ❤️ 13 👀 1806 📊 10 ⚡
