🧭 Qdrant Flashcards
📦 What is Qdrant?
Qdrant is an open-source vector database optimized for fast and scalable similarity search using embeddings.
🧠 What is Qdrant used for?
Qdrant is used in AI search, recommendation systems, RAG pipelines, and semantic search applications.
📐 How are vectors stored in Qdrant?
Vectors are stored in collections with optional metadata (payload) for filtering and advanced querying.
⚡ What similarity metric does Qdrant support?
Qdrant supports cosine similarity, dot product, and Euclidean distance as similarity metrics.
🧪 Does Qdrant support filtering?
Yes, you can use payload filtering to combine vector similarity with structured search.
🔌 What are Qdrant clients available in?
Qdrant offers official clients in Python, TypeScript, and REST API access for integration with any language.
🔄 What is a payload in Qdrant?
A payload is additional metadata associated with a vector, enabling advanced filtering and hybrid search.
🚀 Can Qdrant be self-hosted?
Yes, Qdrant can be self-hosted using Docker or installed directly. A cloud-hosted version is also available.
📈 Is Qdrant production-ready?
Yes, it’s optimized for scale and performance, with high availability and monitoring capabilities.
🔗 Is Qdrant integrated with LangChain?
Yes, LangChain provides a Qdrant vector store wrapper for easy integration into RAG pipelines.