Qdrant
Qdrant is a cutting-edge, large-scale Vector Database and Vector Search Engine designed for the next generation of AI applications, with cloud availability. It offers a robust vector similarity search engine and database solution, featuring a user-friendly API for storing, searching, and managing vectors with additional payloads. Qdrant excels in providing extensive filtering capabilities, making it ideal for neural network and semantic-based matching, faceted search, and various other applications.
Filtering and Payload Management: Qdrant allows attaching JSON payloads to vectors, enabling data storage and filtering based on payload values. It supports a diverse range of data types and query conditions, including keyword matching, full-text filtering, numerical ranges, geo-locations, and more.
Hybrid Search with Sparse Vectors: Supports hybrid search techniques that combine vector similarity search with traditional sparse vector searches.
Vector Quantization and On-Disk Storage: Optimizes storage efficiency through vector quantization and on-disk storage solutions.
Distributed Deployment and Scaling: Offers distributed deployment options with horizontal scaling via sharding and replication, ensuring zero-downtime rolling updates and seamless dynamic scaling of collections.
Query Planning and Payload Indexes: Utilizes stored payload information to optimize query execution strategies, enhancing search performance.
SIMD Hardware Acceleration: Leverages modern CPU architectures (x86-x64 and Neon) for hardware acceleration, delivering improved performance.
Async I/O: Employs io_uring to maximize disk throughput utilization, even on network-attached storage.
Write-Ahead Logging: Ensures data persistence with update confirmations, safeguarding against data loss during power outages.
- Get an SSH key pair to connect to a virtual machine (VM).
- Create a VM from a public image. Under Image/boot disk selection, go to the Cloud Marketplace tab and select Qdrant. Under Access:
- Enter the username in the Login field.
- Paste the contents of the public key file in the SSH key field.
- Connect to the VM via SSH. To do this, use the username you set when creating the VM and the private SSH key you created earlier.
- High-performance vector database and search solutions.
- Implementation of hybrid search functionalities.
- Seamless integration with AI workflow tools, such as langflow.
- Serving as a vector database for RAG applications.
Yandex Cloud technical support is available 24/7 to respond to requests. The types of requests available and their response time depend on your pricing plan. You can enable paid support in the management console. Learn more about requesting technical support.
Yandex Cloud does not provide technical support for this product. If you have any issues, please refer to the developer’s information resources.
