Qdrant CTO分享了未来架构怎么省掉云端来回；Panel聊了Agent不跑检索的坑，还有用同个模型判自己作业的槽点，做AI的都该看看。
Qdrant CTO Andrey Vasnetsov介绍了未来架构：存储和计算彻底分离，用户仅需查询本地设备上的索引片段，无需云端往返。Panel嘉宾来自cognee、Haystack_AI、llama_index、n8n_io，讨论了实际生产中Agent使用检索的问题——Agent有时不会主动调用检索，这比预期更严重。还指出若用同一模型生成评估数据集和作为评判者，相当于自己判自己作业。更多详情和完整录像在Qdrant YouTube频道。
Last week, we hosted Vector Space Meetup: Retrieval in the Age of Agents. Our CTO Andrey Vasnetsov ...
Last week, we hosted Vector Space Meetup: Retrieval in the Age of Agents. Our CTO Andrey Vasnetsov kicked things off with a look at where Qdrant is heading: storage and compute separation taken to its logical limit - querying only the index fragments you need, on your own device, without a cloud round-trip. The panel with @cognee_ , @Haystack_AI by @deepset_ai , @llama_index , and @n8n_io covered agents in production, evaluation, and the decisions that are hardest to undo. A few honest takes from the room: Agents won't always choose to run retrieval when you need them to. That's a bigger problem than most people expect. If you generate your eval dataset and run your LLM-as-a-judge with the same model, you're asking it to grade its own homework. Thanks to everyone who came and pushed back. More details and takes in the full recording on our YouTube: youtube.com/watch?v=EEXUuI… 💬 1 🔄 0 ❤️ 2 👀 224 📊 2 ⚡