Qdrant
Qdrant is an open-source vector database and similarity-search engine for storing, indexing, and querying vectors, including searches filtered by associated metadata.
Build an Advanced RAG Application (From Scratch)
Qdrant is an open-source vector search engine and database that supports similarity search, metadata filtering, and scalable vector indexing.
- How it is used
- Provides the vector retrieval layer for hotel and research-paper RAG applications, including metadata-filtered semantic search.
- How deep it goes
- Walks through collection setup, point upload, filtered querying, and generation integration without detailing Qdrant internals.
- Examples
- Uses city-filtered hotel reviews and 657 embedded research-paper chunks queried for dynamic synapses.
- What you can do after
- Build it from scratch as an in-memory Qdrant retrieval component that supplies cited context to a RAG generator.
Read how Build an Advanced RAG Application (From Scratch) explains Qdrant →
Spring AI in Action
Qdrant is a vector database for storing, filtering, and similarity-searching vector data and its associated payloads.
- How it is used
- Supports document ingestion and retrieval in Spring AI applications that implement question-answering with RAG.
- How deep it goes
- Covers Docker setup, collection verification, point counting, and RAG integration, while deferring similarity mathematics to the vector store.
- Examples
- Uses game-rule documents, the board-game-buddy collection, Burger Battle, HTTPie requests, and a two-point count.
- What you can do after
- Operate/configure Qdrant with Docker Compose, verify stored points through its HTTP API, and connect it to Spring AI RAG.
Build a Multi-Agent System (from Scratch)
Qdrant is an open-source vector database and similarity-search engine.
- How it is used
- Retrieves past agent episodes by similarity to the current task.
- How deep it goes
- Implements collection-backed writes and top-result retrieval, and flags embedding-model choice for benchmarking and dataset evaluation.
- Examples
- Stores Hailstone episodes for starting values 6 and 8, then retrieves the episode for 6.
- What you can do after
- Apply Qdrant through QdrantMemoryStore to persist episodes and recall similar ones.
Read how Build a Multi-Agent System (from Scratch) explains Qdrant →
Also covered in
What to know first
- embeddingAn embedding is a numerical vector representation of an item in a feature space, encoding selected properties or relationships for computational tasks such as comparison or retrieval.
- HNSWHNSW is a graph-based approximate nearest-neighbor indexing and search method that organizes data points in a hierarchy of navigable proximity graphs.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
Related concepts
- information retrievalused by · Information retrieval is the process of finding and selecting information relevant to a query or information need from a collection.
- Rustuses · Rust is a statically typed systems programming language designed for performance, concurrency, and memory safety without requiring garbage collection.
- vector databasekind of · A vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
- Docker Composeconfigured by · Docker Compose is a tool for defining and running applications composed of multiple containers through declarative configuration.
Questions about Qdrant
What is Qdrant?
Qdrant is an open-source vector database and similarity-search engine for storing, indexing, and querying vectors, including searches filtered by associated metadata.
Which Manning books explain Qdrant?
Build an Advanced RAG Application (From Scratch), Spring AI in Action and Build a Multi-Agent System (from Scratch).
What should I know before learning Qdrant?
Manning books that teach Qdrant usually introduce embedding, HNSW and retrieval-augmented generation first.
What is Qdrant a kind of?
Qdrant is a kind of vector database. A vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


