CoolFace
15 results

vector-search

labofsahil /hackernews-vector-search-datasetThe Hacker News dataset contains 28.74 million postings and their vector embeddings. The embeddings were generated using SentenceTransformers model all-MiniLM-L6-v2. The dimension of each embedding vector is 384. Created by clickhouse more info: https://clickhouse.com/docs/getting-started/example-datasets/hackernews-vector-search-dataset tabular10M<n<100M2 likes248 downloads10mo agoHugging Faceroshbeed /ai-residency-vector-search-retrieval-datatextn<1K0 likes105 downloads1mo agoHugging Facehabedi /multi-vector-search-datasets Multi-Vector Search Datasets The datasets listed below are used in the Multi-Vector HNSW project for testing and benchmarking multi-vector approximate nearest neighbor search algorithms and their implementations. Stack Exchange Datasets Source: habedi/stack-exchange-dataset Each row contains: id: unique post ID title: the post title body: the main body content (with HTML tags removed) tags: associated tags embedding: a list of three 768-dimensional vectors for [title… See the full description on the dataset page: https://huggingface.co/datasets/habedi/multi-vector-search-datasets.1M<n<10M0 likes96 downloads1y agoHugging Facemzx /car-search-vector-db0 likes66 downloads11mo agoHugging Faceberkcangumusisik /turkish-medical-vector-search 🩺 Türkçe Tıbbi Vektör Arama Projesi Bu projede Türkçe tıbbi makaleler üzerinde çalışan basit bir semantik arama sistemi geliştirdim. Temel amaç, kullanıcı bir soru sorduğunda bu soruyla en alakalı makale parçalarını bulabilmek. Burada özellikle dikkat ettiğim noktalardan biri, sistemin elinde yeterli bilgi yokken cevap üretmeye çalışmamasıydı. Bu nedenle benzerlik skoru belirli bir seviyenin altında kaldığında sistem cevap vermek yerine: Bu sorunun cevabı dokümanlarımda yer… See the full description on the dataset page: https://huggingface.co/datasets/berkcangumusisik/turkish-medical-vector-search.tabular1K<n<10K0 likes54 downloads2mo agoHugging Facebeatsprom /autonomous-db-internals-vector-search-suite ⚡ Autonomous Database Internals, Vector Search Engines & Distributed Storage Suite (2026) A Production-Grade, Verifiable Synthetic Corpus for Training Autonomous Database Kernel & Vector Retrieval LLMs 💼 Get Full 12,500-Row Enterprise Suite on Gumroad → Full 10,000 SFT + 2,500 DPO Rows • 254.6 MB Pre-Indexed SQLite DB • RLVR/GRPO Sandboxed Testbed • Commercial License ⚡ Overview & Industry Problem Deploying autonomous AI… See the full description on the dataset page: https://huggingface.co/datasets/beatsprom/autonomous-db-internals-vector-search-suite.tabulartext-generation1K<n<10K0 likes37 downloads6d agoHugging Face