Qdrant は月間 72,992 訪問、前月比成長率 -38.4%、料金体系フリーミアム、料金は要問い合わせを記録しています。Shaped は月間 11,871 訪問、成長率 -39.2%、料金体系料金は要問い合わせを記録しています。
Qdrant is an open-source vector search engine and database, written in Rust, for high-performance similarity search in AI applications.
Built entirely in Rust with SIMD and a custom Gridstore storage engine for fast, scalable vector search.
Combine dense and sparse vectors in one query, supporting BM25, SPLADE++ and miniCOIL for keyword-plus-vector retrieval.
Store metadata as JSON and apply advanced filters such as nested, text, geo and has_vector, with filters applied during HNSW traversal.
Asymmetric, scalar and binary quantization reduce memory usage by up to 64x while preserving search quality.

フィードバックループを備えたレレバンスエンジン
SQL ライクな単一クエリで、セマンティック検索、キーワード検索、行動モデルを横断した検索・フィルタ・スコアリング・再ランキングを実行します。
セマンティック検索とキーワード検索を組み合わせ、各ユーザーの予測クリック率とエンゲージメントで結果を再ランキングします。
ML モデルがライブのインタラクション信号で再学習し、トラフィックの増加に伴ってランキング品質が自動的に向上します。
Snowflake、Kafka、BigQuery、Shopify などのデータウェアハウス、分析ツール、イベントパイプラインから ETL なしでデータを取り込みます。
特化型Pinecone is a managed vector database and AI knowledge platform for building retrieval-augmented generation (RAG), semantic search, and agent memory. It stores vector embeddings at scale, makes writes searchable within seconds with no index tuning, and keeps p99 latency steady as data grows. Pinecone powers products for more than 10,000 customers and over a million developers worldwide.
特化型Pinecone is a managed vector database and AI knowledge platform for building retrieval-augmented generation (RAG), semantic search, and agent memory. It stores vector embeddings at scale, makes writes searchable within seconds with no index tuning, and keeps p99 latency steady as data grows. Pinecone powers products for more than 10,000 customers and over a million developers worldwide.

無料・オープンソースセルフホストもクラウドも選べる超高速検索エンジン

Zilliz is the company behind Milvus, the open-source vector database, and offers Zilliz Cloud — a fully managed vector database service built for large-scale AI retrieval, RAG, and similarity search workloads.

無料・オープンソースオブジェクトストレージ上に構築された、AI エージェント記憶のためのグラフデータベース

SvectorDB is a natively serverless vector database designed around AWS. It offers pay-per-request pricing, hybrid key-value filtering, built-in text and image vectorizers, and CloudFormation support, making it cheap and simple to add semantic search or recommendations to an existing cloud stack.
SvectorDB is a natively serverless vector database designed around AWS. It offers pay-per-request pricing, hybrid key-value filtering, built-in text and image vectorizers, and CloudFormation support, making it cheap and simple to add semantic search or recommendations to an existing cloud stack.

無料・オープンソースTrieve is an AI search and discovery platform and open API for building RAG applications. It combines hybrid search, chunk management, conversational AI and relevance analytics in one system, and can be used as a managed service or self-hosted.
無料・オープンソースTrieve is an AI search and discovery platform and open API for building RAG applications. It combines hybrid search, chunk management, conversational AI and relevance analytics in one system, and can be used as a managed service or self-hosted.