Ivan Pleshkov
ec4d42e7f6
add gpu indexing flag add gpu vector storage time measurement add chmod flag build hnsw using gpu scoring speedup move gl_GlobalInvocationID to mains glslc with o flag fix tests use gpu atomics instead of multiple runs enable atomics add timers profile search let shader work while points collection use generations for visited flags add gpu init timer avoid entries download remove gpu call timers for a while rename to combined graph builder move gpu graph builder restore levels in link access restore links_map add gpu start condition use graph builder links memory remove mut's list point ids before processing download-upload links using methods only cpu graph builder as separate struct add cpu threads count parallel cpu build single threaded cpu preprocess try to fix glove accuracy unsafe Send and Sync for gpu builder copy graph layers builder instead of moving remove obsolete mut fix build move builders to arc fix bfb deadlock move uneccessary clear run cpu and gpu in separate threads many vectors storage buffers debug gpu vector storage fix vector storage upload bug add cpu ful graph build don't use non-ready links for point try to resolve conflicts while upsert add indexing unit test for measurements add test utilize cpu more efficient dont clear bhaep debug gpu runs try to use vec4 instead of mat4 dump scores count estimate gpu usage print usage per run start using working groups build shaders for vulkan v1.3 start shaders subgroup vk instance version 1.3 subgroup vector storage fix test nearest heap nearest heap test are you happy fmt add assert to nearest heap test are you happy fmt gpu visited flags start candidates heap candidates heap push debug nearest heap remove subgroupExclusiveMin fix build are you happy clippy remove links dependency from nearest heap provide input count to nearest test are you happy fmt provide ef to shader are you happy fmt get subgroup size move compiled shaders are you happy fmt fix workgroups count for vector storage compute test return true subgroup size do nearest heap on gpu with partial sorting remove tmp shader unite scores and indices are you happy fmt gpu nearest sorting are you happy fmt fix nearest heap test links test with subgroups gpu candidates start fix candidates sorting are you happy fmt fix candidates test on m1 chip move obsolete and test shaders start new gpu search context search context test fix links uploading debug hnsw searh on level test fix gpu hnsw search on level test move test initialization to separate function gpu greedy search shader test test heuristic shader gpu greedy search test gpu test heuristic move greedy search into searcher start insertion shader find hnsw patch on gpu fix gpu patches test start gpu graph builder equivalency test fix layers check add timers are you happy fmt quality test and fix multithreaded bug debug tests are you happy fmt fix levels count and clear links fix equivalency test remove obsolete solution trivial gpu indexing integration gpu config and skip conflicts for large hnsw glsl generic vector storage element type gpu generic vector storage enable vulkan features for f16 and u8 force_half_precision option add force f16 test fix u8 and f16 unit tests apply generic shaders in hnsw construction remove conflicts check; start cpu utilization cpu prebuild upload first point links to gpu mark all points in cpu graph as ready multithreaded cpu and gpu fix equivalency test remove cpu links copy parallel patches clearing fix multithreaded env external layers source more logs to debug cpu+gpu syncronization clear gpu processed points count remove some temp logs fix cpu stop condition bug new insert vector shader greedy search returns only ids download whole layer links apply new links on gpu directly update win shader script parallel links loading provide memory amount as setting and estimate groups count start bq gpu bq test fix tests shaders invocations refactor revert max groups settings gix build after rebase fix bug after rebase upload links to gpu in cpu thread fix greedy search iteration atomic checker for conflicts dump graph changes for debugging move iterator to separate file start combined builder refactor start cpu builder as separate struct separate gpu and cpu construction fix tests fix atomics count bug upload links to gpu as separate fn glue cpu and gpu gpu thread link points on cpu while gpu is busy fix gpu bq scoring test use xor instead of calc it reallocate with less groups if not enough gpu memory update compiled shaders don't use llvm gpu emulator debug panic if no gpu remove tmp debug dumping dockerfile for gpu customize candidates count fix gpu storage size runtime shader compilation dim as define nearest heap params as macro candidates and links capacities as macro parallel bitonic sort use bubble sort too nearest heap as shared limited shared candidates heap combine buble and bitonic sorts one-argumented similarity cache vector for scoring dont check candidates overflow do greedy before search visited hashtable Revert "visited hashtable" This reverts commit 7540d04d3859d02f17908c874927d18076f3eb8e. use less flushes bulk sum calculation Revert "bulk sum calculation" This reverts commit 6ef78ceb8d6ba7d9bf2077804548df162052c749. load vector in one read Revert "load vector in one read" This reverts commit ea980d0399b90f44638590d40fdbfb1d6ffa9504. fix build after rebase fix build after rebase sq support simplify bq uploading using constructed quantization metrics alignment depends on subgroup size are you happy fmt exact flag use lazy static for device access remove prints test reallocation factor visited flags capacity as a compile time constant build gpu hnsw for payload blocks add dynamically sized subgroup size support fix build update rust version for nvidia docker dynamically sized subgroups start device filter test device filter are you happy clippy devices manager provide device instead of flag, better locking partial cpu permit release free cpus when gpu enabled use cpu is waiting is disabled create device only when gpu is enabled cpu permit release all cases parallel indices count provide queue index small refactor of shader builder are you happy fmt quantization params as separate struct pq refactor fmt remove upload_mapped_ptr from gpu buffer refactor gpu buffer check buffer range buffer refactor refactor pipeline move shader compiler to instance refactor context more refactor no unwraps in gpu crate clippy apply pr changes are you happy fmt dont use shaderc in segment more gpu tests pq bq tests provide bq option fix bq for small dim bind pq buffers pq more complex test cover all storage types by tests test multi and vectors as iterator multivectors upload data multivectors shader fix multivector tests refactor shader builder move storage tests into separate file move quantization to separate file refactor gpu vector storage creation refactor gpu quantization api dont convert to float when unnecessary more comments small upload vectors refactor fix build after rebase fix tests after rebase different vk queue priorities capacity vectors upload stopper amd dockerfile fix build after rebase
Vector Search Engine for the next generation of AI applications
Qdrant (read: quadrant) is a vector similarity search engine and vector database. It provides a production-ready service with a convenient API to store, search, and manage points—vectors with an additional payload Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural-network or semantic-based matching, faceted search, and other applications.
Qdrant is written in Rust 🦀, which makes it fast and reliable even under high load. See benchmarks.
With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!
Qdrant is also available as a fully managed Qdrant Cloud ⛅ including a free tier.
Quick Start • Client Libraries • Demo Projects • Integrations • Contact
Getting Started
Python
pip install qdrant-client
The python client offers a convenient way to start with Qdrant locally:
from qdrant_client import QdrantClient
qdrant = QdrantClient(":memory:") # Create in-memory Qdrant instance, for testing, CI/CD
# OR
client = QdrantClient(path="path/to/db") # Persists changes to disk, fast prototyping
Client-Server
To experience the full power of Qdrant locally, run the container with this command:
docker run -p 6333:6333 qdrant/qdrant
Now you can connect to this with any client, including Python:
qdrant = QdrantClient("http://localhost:6333") # Connect to existing Qdrant instance
Before deploying Qdrant to production, be sure to read our installation and security guides.
Clients
Qdrant offers the following client libraries to help you integrate it into your application stack with ease:
- Official:
- Community:
Where do I go from here?
- Quick Start Guide
- End to End Colab Notebook demo with SentenceBERT and Qdrant
- Detailed Documentation are great starting points
- Step-by-Step Tutorial to create your first neural network project with Qdrant
Demo Projects 
Discover Semantic Text Search 🔍
Unlock the power of semantic embeddings with Qdrant, transcending keyword-based search to find meaningful connections in short texts. Deploy a neural search in minutes using a pre-trained neural network, and experience the future of text search. Try it online!
Explore Similar Image Search - Food Discovery 🍕
There's more to discovery than text search, especially when it comes to food. People often choose meals based on appearance rather than descriptions and ingredients. Let Qdrant help your users find their next delicious meal using visual search, even if they don't know the dish's name. Check it out!
Master Extreme Classification - E-commerce Product Categorization 📺
Enter the cutting-edge realm of extreme classification, an emerging machine learning field tackling multi-class and multi-label problems with millions of labels. Harness the potential of similarity learning models, and see how a pre-trained transformer model and Qdrant can revolutionize e-commerce product categorization. Play with it online!
More solutions
|
|
|
| Semantic Text Search | Similar Image Search | Recommendations |
|
|
|
| Chat Bots | Matching Engines | Anomaly Detection |
API
REST
Online OpenAPI 3.0 documentation is available here. OpenAPI makes it easy to generate a client for virtually any framework or programming language.
You can also download raw OpenAPI definitions.
gRPC
For faster production-tier searches, Qdrant also provides a gRPC interface. You can find gRPC documentation here.
Features
Filtering and Payload
Qdrant can attach any JSON payloads to vectors, allowing for both the storage and filtering of data based on the values in these payloads. Payload supports a wide range of data types and query conditions, including keyword matching, full-text filtering, numerical ranges, geo-locations, and more.
Filtering conditions can be combined in various ways, including should, must, and must_not clauses,
ensuring that you can implement any desired business logic on top of similarity matching.
Hybrid Search with Sparse Vectors
To address the limitations of vector embeddings when searching for specific keywords, Qdrant introduces support for sparse vectors in addition to the regular dense ones.
Sparse vectors can be viewed as an generalization of BM25 or TF-IDF ranking. They enable you to harness the capabilities of transformer-based neural networks to weigh individual tokens effectively.
Vector Quantization and On-Disk Storage
Qdrant provides multiple options to make vector search cheaper and more resource-efficient. Built-in vector quantization reduces RAM usage by up to 97% and dynamically manages the trade-off between search speed and precision.
Distributed Deployment
Qdrant offers comprehensive horizontal scaling support through two key mechanisms:
- Size expansion via sharding and throughput enhancement via replication
- Zero-downtime rolling updates and seamless dynamic scaling of the collections
Highlighted Features
- Query Planning and Payload Indexes - leverages stored payload information to optimize query execution strategy.
- SIMD Hardware Acceleration - utilizes modern CPU x86-x64 and Neon architectures to deliver better performance.
- Async I/O - uses
io_uringto maximize disk throughput utilization even on a network-attached storage. - Write-Ahead Logging - ensures data persistence with update confirmation, even during power outages.
Integrations
Examples and/or documentation of Qdrant integrations:
- Cohere (blogpost on building a QA app with Cohere and Qdrant) - Use Cohere embeddings with Qdrant
- DocArray - Use Qdrant as a document store in DocArray
- Haystack - Use Qdrant as a document store with Haystack (blogpost).
- LangChain (blogpost) - Use Qdrant as a memory backend for LangChain.
- LlamaIndex - Use Qdrant as a Vector Store with LlamaIndex.
- OpenAI - ChatGPT retrieval plugin - Use Qdrant as a memory backend for ChatGPT
- Microsoft Semantic Kernel - Use Qdrant as persistent memory with Semantic Kernel
Contacts
- Have questions? Join our Discord channel or mention @qdrant_engine on Twitter
- Want to stay in touch with latest releases? Subscribe to our Newsletters
- Looking for a managed cloud? Check pricing, need something personalised? We're at info@qdrant.tech
License
Qdrant is licensed under the Apache License, Version 2.0. View a copy of the License file.