From 871a4cfa7715cc6b93b802e1d5fe6c07c95ba1b4 Mon Sep 17 00:00:00 2001 From: daniel-azoulai Date: Thu, 20 Nov 2025 10:38:05 -0800 Subject: [PATCH] bento-box-addition --- qdrant-landing/content/blog/case-study-cosmos.md | 12 +++++------- ...cosmos:bento-box-dark.jpg => bento-box-dark.jpg} | Bin 2 files changed, 5 insertions(+), 7 deletions(-) rename qdrant-landing/static/blog/case-study-cosmos/{case-study-cosmos:bento-box-dark.jpg => bento-box-dark.jpg} (100%) diff --git a/qdrant-landing/content/blog/case-study-cosmos.md b/qdrant-landing/content/blog/case-study-cosmos.md index 1d4034c7e..e1e0eea8f 100644 --- a/qdrant-landing/content/blog/case-study-cosmos.md +++ b/qdrant-landing/content/blog/case-study-cosmos.md @@ -5,9 +5,9 @@ short_description: "Cosmos built fast, multimodal visual search with exact color description: "Discover how Cosmos powered text, color, and hybrid search with sub-second latency and 79% faster processing by adopting Qdrant Cloud as its retrieval layer." preview_image: /blog/case-study-cosmos/social_preview_partnership-cosmos.jpg social_preview_image: /blog/case-study-cosmos/social_preview_partnership-cosmos.jpg -date: 2025-11-19 +date: 2025-11-21 author: "Daniel Azoulai" -featured: true +featured: false tags: - Cosmos @@ -19,11 +19,9 @@ tags: - case study --- -How Cosmos delivered editorial-grade visual search with Qdrant - ![How Cosmos powered text, color, and hybrid search with Qdrant](/blog/case-study-cosmos/bento-box-dark.jpg) -Cosmos is redefining how people find inspiration online. It’s a visual search app built for creative professionals and everyday users who want a clean, meditative, ad-free place to collect and curate ideas. In contrast to feeds dominated by doomscrolling, ads, and generative “AI slop,” Cosmos focuses on high-quality, human-made content. AI-powered search and captions connect each image to its creator, making visual discovery richer, more accurate, and easier to navigate. +Cosmos is redefining how people find inspiration online. It’s a visual search app built for creative professionals and everyday users who want a clean, meditative, ad-free place to collect and curate ideas. In contrast to feeds dominated by doomscrolling, ads, and generative “AI slop,” Cosmos focuses on high-quality, human-made content. AI-powered search and captions connect each image to its creator, making visual discovery richer, more accurate, and easier to navigate. Behind this front end sits a complex technical problem: powering text, color, and hybrid visual search for millions of users in real time. For Cosmos, the solution came from Qdrant Cloud. @@ -48,7 +46,7 @@ Early prototypes relied on Postgres with pgvector, but scalability and performan *“We wanted a vector search engine that could handle our color and text embeddings together while letting us filter by dozens of metadata dimensions.”* -- *Griffin Miller, AI/ML & Product* +-*Griffin Miller, AI/ML & Product* Cosmos also needed a managed deployment to avoid maintaining reindexing, scaling, or balancing logic manually. The engineering team wanted to focus on product innovation, not infrastructure tuning. @@ -106,5 +104,5 @@ Miller highlighted the partnership: “Qdrant’s customer engineering team has As Cosmos moves toward its next release, its search stack now reflects its design philosophy: fast, thoughtful, and exact. *“Our users are artists. They can tell the difference between ‘almost right’ and perfect. Qdrant helps us achieve this level of precision.”* - — Griffin Miller, AI/ML & Product, Cosmos + -*Griffin Miller, AI/ML & Product, Cosmos* diff --git a/qdrant-landing/static/blog/case-study-cosmos/case-study-cosmos:bento-box-dark.jpg b/qdrant-landing/static/blog/case-study-cosmos/bento-box-dark.jpg similarity index 100% rename from qdrant-landing/static/blog/case-study-cosmos/case-study-cosmos:bento-box-dark.jpg rename to qdrant-landing/static/blog/case-study-cosmos/bento-box-dark.jpg