←新闻详情

Testing Catalog更新于 10月27日 00:03

Nace AI 推出 Drex for Search 检索工具

Nace AI launched Drex for Search, a tool that lets agents retrieve answers from files stored in the cloud by giving them the exact pages they need.

AI 导读

Nace AI 推出 Drex for Search,让智能体从云端文件中按文件夹、文件、页面逐层定位,返回答案、引文和页码。该工具可连接 AWS S3、Azure 和 DigitalOcean,读取扫描版 PDF、表格、邮件和音频,并可作为 Claude Code、Codex、Hermes Agent 等编码智能体的工具调用。Nace 称每个问题步骤减少 62%、输入 token 减少 56%;在包括 Databricks OfficeQA 在内的六个专业工作基准共 529 条查询上,使用该工具的智能体正确率为 67.1%,高于此前的 63.1%。

推荐理由

AI 评分 56

原文给出了检索步骤、token 节省和基准提升的具体数字,可据此判断这类检索工具对智能体工作流的影响。

主题

标签

引用

Nace AI

@NaceAI

推出用于搜索的 Drex 🔍 用 Decision 驱动的检索为你的智能体搜索强力加速 标准文件搜索会拖累 AI 智能体。Drex 改变了这一点: • 找到答案所需步骤减少 62% • 节省 56% 的 token • 在 Claude Code、Codex、OpenCode、Hermes 和 PI 上性能提升 +4% 已在 OfficeQA(529 条真实世界查询)等 6 个专业工作基准上验证 用 File Search API 升级你的智能体工作流 免费试用:https://t.co/vdEavE1dsd 更快的智能体。更低的运行成本。更精准的准确率。

查看原文

Introducing Drex for Search 🔍 Supercharge your agentic search with Decision-powered retrieval Standard file search holds AI agents back. Drex changes that: • 62% fewer steps to find answers • 56% tokens saved • +4% performance boost across Claude Code, Codex, OpenCode, Hermes, and PI Validated across 6 professional work benchmarks like OfficeQA (529 real-world queries) Upgrade your agentic workflows with the File Search API Try for free: https://t.co/vdEavE1dsd Faster agents. Cheaper runs. Sharper accuracy.

查看原帖

正文

Nace AI launched Drex for Search, a tool that lets agents retrieve answers from files stored in the cloud by giving them the exact pages they need.

When given a question, Drex for Search first finds the likely folder, then the file, then the page, and returns the answer, the quote, and the page number where it found the info.

> Drex Search is able to connect to a user’s AWS S3, Azure, and DigitalOcean, with the ability to read scanned PDFs, spreadsheets, email, and audio.

> Coding agents such as Claude Code, Codex, and Hermes Agent can use it as a tool, with Nace reporting 62% fewer steps and 56% fewer input tokens per question.

> Across 529 queries from six professional work benchmarks, including Databricks’ OfficeQA, agents using it answered 67.1% correctly, up from 63.1%.

来源

Testing Catalog