Qdrant
Qdrant is an open-source vector database and vector similarity search engine designed for storing, managing, and retrieving high-dimensional vector data. It supports efficient approximate nearest neighbor (ANN) search and is applicable to AI scenarios such as semantic search, recommendation systems, and image retrieval. Qdrant provides RESTful API and gRPC interfaces, supports hybrid queries with multiple filter conditions, and offers horizontal scalability for deployment in cloud-native environments.
Core Facts
Timeline (last 90 days)
Vector databases (such as Pinecone, Weaviate, and Qdrant) specialize in storing and retrieving vectors; in AI scenarios they convert data such as text and images into vectors, so that content with similar semantics is also close in distance in vector space.
For a personal memory system, it is recommended to use PostgreSQL as the single source of truth, pgvector or Qdrant for semantic search, Neo4j or Kuzu for the personal knowledge graph, and encrypted object storage for raw files.
Common choices for vector databases include PostgreSQL with pgvector, MongoDB Vector Search, Pinecone, Weaviate, Qdrant, and others.
自托管Qdrant相比Pinecone可节省约80%的成本
混合检索的四阶段流程为：第一阶段并行稠密检索和稀疏检索；第二阶段用RRF融合，k_constant默认60，稠密权重0.7，稀疏权重0.3；第三阶段用Cross-Encoder重排序（推荐ms-marco-MiniLM-L-6-v2）；第四阶段截取Top-K，默认k=5，fetch_k=20。
Storage locations can be summarized into three routes: dedicated vector databases (such as Milvus, Qdrant, Pinecone), PostgreSQL + pgvector, and local libraries.
Dedicated vector databases have built-in production-oriented features, including distributed sharding and horizontal scaling, quantization compression (PQ, SQ), joint execution of metadata filtering and vector retrieval, multi-tenant isolation, batch writes and consistency control.
Milvus, Qdrant, and Pinecone are specialized vector databases, designed from the ground up to store and index massive embeddings and efficiently perform nearest-neighbor queries.
The recommended hybrid architecture is to use Durable Objects for short-term context and homelab/Qdrant for long-term knowledge, establishing a memory hierarchy and using TTL policies to clean up expired session data.
A self-hosted Home Lab (VPS + Qdrant + PostgreSQL) typically has latency of 50–200 ms, but provides full SQL and vector retrieval capabilities, with capacity limited only by hardware.
34 more timeline events
All Facts (20)
Agent的记忆系统通常分为三个层次：工作记忆（当前对话上下文窗口）、短期记忆（近期交互历史）和长期记忆（通过向量数据库持久化存储）
80%Verified常见的向量数据库包括ChromaDB、Milvus、Pinecone、Weaviate，它们针对高维向量的近似最近邻（ANN）搜索进行了专门优化
80%Verified长期记忆Agent通常基于RAG（检索增强生成）技术构建，通过向量数据库将信息转化为高维向量并持久化存储
80%Verified向量数据库的核心操作是近似最近邻搜索（ANN），通过HNSW、IVF等索引算法将相似度计算加速到毫秒级响应
80%VerifiedDify's core architecture adopts a microservices design, using Docker Compose to decouple and deploy components such as the API service, Worker, Web frontend, PostgreSQL, Redis, and vector database.
80%VerifiedMainstream vector databases include Faiss, Milvus, Qdrant, and Weaviate, which can complete Approximate Nearest Neighbor (ANN) searches over millions of vectors in milliseconds.
75%VerifiedMainstream vector databases such as Pinecone, Weaviate, and Qdrant are implemented based on ANN algorithms such as HNSW or IVF-PQ.
70%VerifiedChroma and Pinecone are vector databases used to store vectorized data.
65%Verified向量存储常用专用向量数据库如Pinecone、Chroma、Weaviate，支持近似最近邻检索
65%VerifiedFlowise supports mainstream vector databases including Pinecone, Weaviate, Chroma, and Qdrant.
65%UnverifiedFastEmbed与Qdrant出自同一团队，两者有天然的集成关系
95%UnverifiedFastEmbed是由Qdrant团队开发的Python库，专门用于在本地环境中快速生成文本和图像的向量嵌入
95%UnverifiedQdrant向量数据库在使用add方法添加文档时，如果没有手动提供嵌入向量，会自动调用FastEmbed在后台完成嵌入计算
90%Partially VerifiedAnythingLLM has built-in support for multiple vector databases including ChromaDB, Pinecone, LanceDB, and Weaviate.
80%Partially Verified常见的向量数据库包括Milvus、Qdrant、Weaviate等开源方案以及Pinecone等云服务
65%UnverifiedThe project's vector storage uses the Qdrant vector database.
60%UnverifiedIn production environments, when the data scale exceeds millions of vectors, it is generally necessary to consider vector database solutions such as Milvus and Qdrant that support distributed deployment and HNSW index optimization.
60%UnverifiedVector databases (such as Pinecone, Weaviate, and Qdrant) specialize in storing and retrieving vectors; in AI scenarios they convert data such as text and images into vectors, so that content with similar semantics is also close in distance in vector space.
50%UnverifiedFor a personal memory system, it is recommended to use PostgreSQL as the single source of truth, pgvector or Qdrant for semantic search, Neo4j or Kuzu for the personal knowledge graph, and encrypted object storage for raw files.
50%UnverifiedCommon choices for vector databases include PostgreSQL with pgvector, MongoDB Vector Search, Pinecone, Weaviate, Qdrant, and others.
50%