1. "Code only" vs. "Code with explanation"—similar questions don't always mean identical requirements. ... "Code only" vs. "Code with explanation"—similar questions don't always mean identical requirements. That's why traditional semantic caching often breaks. To solve this, Zil 10/16 23:15 ♡
2. I In product search, the closest semantic match isn’t always the best result once price, freshness, po... In product search, the closest semantic match isn’t always the best result once price, freshness, popularity, and ratings enter the picture. In this demo, we show how 𝗠 10/15 23:46 ♡
3. One self-driving car can record terabytes of video in a day. But engineers don’t need all that foot... One self-driving car can record terabytes of video in a day. But engineers don’t need all that footage. They need a few seconds when something important happened. A pedestrian cros 10/14 23:40 ♡
4. We tested whether Jev could replace some of the LLM calls inside three agentic search workloads. 1... We tested whether Jev could replace some of the LLM calls inside three agentic search workloads. 1️⃣ In 𝗗𝗲𝗲𝗽𝗦𝗲𝗮𝗿 10/13 23:50 ♡
5. 🎤 Our Solutions Architect, Yulan Yan, will speak at Tokyo AI’s 𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗮𝗴𝗲𝗻𝘁𝘀: ... 🎤 Our Solutions Architect, Yulan Yan, will speak at Tokyo AI’s 𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗮𝗴𝗲𝗻 10/12 08:36 ♡
6. S Single-vector retrieval is a useful default. But on visually dense PDFs, it can become lossy: diagra... Single-vector retrieval is a useful default. But on visually dense PDFs, it can become lossy: diagrams, labels, arrows, and spatial relationships get compressed into one representa 10/09 23:31 ♡
7. 𝗪𝗲’𝗿𝗲 𝗯𝗿𝗶𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗠𝗶𝗹𝘃𝘂𝘀 𝟯.𝟬 𝗠𝗲𝗲𝘁𝘂𝗽 𝘁𝗼 𝗦𝗮𝗻 𝗙𝗿𝗮𝗻𝗰𝗶𝘀𝗰𝗼 ... 𝗪𝗲’𝗿𝗲 𝗯𝗿𝗶𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗠𝗶𝗹𝘃 10/09 11:56 ♡
8. Millions of questions. How does Milvus help find the right one? Traditional full-text retrieval fin... Millions of questions. How does Milvus help find the right one? Traditional full-text retrieval finds questions through the words they contain. In a growing question bank, students 10/07 23:45 ♡
9. SQ, PQ, or PRQ: how do they compress vectors in Milvus HNSW? HNSW can deliver high recall, but its ... SQ, PQ, or PRQ: how do they compress vectors in Milvus HNSW? HNSW can deliver high recall, but its full precision vectors and layered graph consume substantial memory. Milvus offer 10/05 23:30 ♡
10. Real-world data is rarely flat. A driving video, for example, has an overall scene—an intersection,... Real-world data is rarely flat. A driving video, for example, has an overall scene—an intersection, a highway ramp, a residential street—but it also contains dozens of individual o 10/02 23:15 ♡
