生物医药研发团队终于有了能搜遍全部 PubMed 的 AI 工具——Sapu 用 Qdrant 解决了文献检索的碎片化痛点，做药物发现的团队可以直接参考这个架构。
纳米药物初创公司 Sapu 将全部 2800 万篇 PubMed 摘要索引到单个 Qdrant 向量数据库中，使研究人员能进行全语料库的文献搜索。其 AI 平台支持论文撰写、SOP 感知聊天机器人以及生物医学摘要的全文向量搜索。研究人员可通过元数据过滤子集或直接对 2800 万条记录进行向量搜索。该工具已帮助团队发表 7 篇同行评审论文，并获得从 CEO 到实验室的日常使用。Sapu 从自托管 Docker 迁移到 Qdrant Cloud Premium，获得了 SOC 2 合规性，从而将工程资源重新聚焦于癌症研究。
A nanomedicine startup developing treatments for hard-to-treat cancers needed its researchers to sea...
A nanomedicine startup developing treatments for hard-to-treat cancers needed its researchers to search the entire PubMed corpus, not filtered subsets. Sapu indexed all 28 million PubMed abstracts into a single Qdrant collection. Their AI platform now supports research paper authorship, SOP-aware chatbots, and full-corpus literature search across biomedical abstracts. Researchers query a small filtered slice using metadata or run vector search across the full 28 million records at once. Using this tool, they created seven peer-reviewed papers published using the AI tooling, seen daily adoption from the CEO to the lab floor, and inked a new robotics partnership extending the platform into physical lab workflows. Sapu moved from self-hosted Docker to Qdrant Cloud Premium, gaining SOC 2 compliance (critical for licensing the platform to other biotech companies) and the stability to stop pulling engineering attention away from cancer research. Read the full story: qdrant.tech/blog/case-stud… 💬 0 🔄 1 ❤️ 11 👀 409 📊 3 ⚡