All 82 Dependencies

Every package Qdrant depends on, ranked by repo health score.

Qdrant is an open-source, high-performance vector database and similarity search engine written in Rust. It is designed to store, index, and search vector embeddings produced by neural networks at production scale — powering use cases such as semantic search, retrieval-augmented generation (RAG), recommendation engines, image similarity, and anomaly detection. Its core innovation is a custom storage engine called Gridstore and a highly optimized HNSW (Hierarchical Navigable Small World) graph implementation accelerated by SIMD instructions and, optionally, NVIDIA and AMD GPUs via Vulkan.

Qdrant supports three vector modes: dense vectors for semantic similarity, sparse vectors (BM25, SPLADE++) for keyword-based retrieval, and multivectors (e.g. ColBERT-style late interaction). These can be combined in a single hybrid query with configurable fusion strategies like Reciprocal Rank Fusion (RRF) or Distribution-Based Score Fusion (DBSF). Rich JSON payload filtering — keyword matching, full-text, numeric ranges, geo-location, boolean conditions — is applied natively during HNSW graph traversal, not as a post-processing step.

For scale-out workloads, Qdrant offers horizontal sharding and replication with zero-downtime rolling upgrades, a Raft-based consensus layer for distributed consistency, and granular resource budgets for CPU and I/O. Built-in quantization (scalar, binary, product) cuts memory usage by up to 97% while preserving search accuracy. The platform also ships Qdrant Edge, a lightweight in-process version for edge devices and offline-capable applications.

Qdrant integrates with major AI frameworks and providers including LangChain, LlamaIndex, Haystack, OpenAI, Cohere, and Microsoft Semantic Kernel. Its API surface covers REST (OpenAPI 3.0) and gRPC for high-throughput production use, supplemented by a built-in Web UI for collection management, data exploration, and optimization monitoring.

15 actix-web-extras 0.1.0 21 num-cmp 0.1.0 23 aligned-vec 0.6.4 23 serde-value 0.7 24 permutation-iterator-rs 0.1.2 29 slog-stdlog 4.1.1 33 serde-untagged 0.1.9 34 retry >=0.9.2,<0.10 34 rust-stemmers 1.2.2 outdated 36 rust-typed-arena 2.0.2 36 rustls-pemfile 2.2.0 36 serde_urlencoded 0.7 37 sys-info-rs 0.9.1 38 crc-rs 3.4.0 39 grpc-interceptor >=0.15,<0.16 39 shaderc 0.10.1 42 jsons >=1.6.3,<2 42 nom 8.0.0 42 num-derive 0.4.2 outdated 42 num_cpus 1.17 42 ringbuffer 0.16.0 43 colored 3 43 macro_rules_attribute-rs 0.2.2 43 prometheus 0.14.0 44 siphasher 1.0.3 45 arrayvec 0.7.6 45 csv 1.4.0 45 quick-cache 0.6.22 outdated 46 constant_time_eq 0.4.2 outdated 46 slog 2.8.2 47 pytest-cases >=3.9.1,<4 48 approx 0.5.1 outdated 48 crc32c 0.6.8 49 geohash 0.13.2 49 prettyplease 0.2 outdated 50 Tower 0.5.3 50 Tower 0.3.3 outdated 51 derive_more 2.1 52 HdrHistogram (Rust) 7.5.4 52 hashring-rs 0.3.6 53 ArcSwap 1.9.1 53 fs-err 3 55 console-subscriber 0.5.0 57 rustls-pki-types 1.14.0 58 jsonwebtoken 10.0 outdated 59 gpu-allocator 0.28.0 59 proc-macro2 1.0 61 vaporetto 0.6.5 63 ash 0.38.0 64 charabia 0.9.9 outdated 64 lz4_flex 0.13.1 outdated 64 quote 1.0 64 tempfile 3 65 tracing-tracy 0.11.4 outdated 66 pytest-timeout >=2.4,<3 68 serial_test 3.5.0 outdated 69 anyhow 1.0.98 70 regex 1.12.3 72 ndarray 0.17.2 74 geo 0.33.1 74 tqdm >=4.67.1,<5 75 ureq 3 77 Requests >=2.32.5,<3 77 config 0.15.22 79 foyer 0.22 79 rustix 1 79 sysinfo 0.38 outdated 80 tracing 0.2 outdated 80 tracing 0.2 outdated 80 tracing 0.3 outdated 82 flate2 1.1.9 84 pytest-xdist >=3.8.0,<4 85 docker-py >=7.1.0,<8 86 more-itertools >=10.8,<11 outdated 87 PyJWT >=2.10,<3 90 PyO3 0.28.3 outdated 90 syn 2.0 outdated 91 Actix Web 0.7.2 outdated 91 qdrant-client >=1.16.1,<2 94 rustls 0.23.37 96 actix-cors 0.7.1 96 pytest >=8.4,<9 outdated

Join founders buildingwith open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on Substack
Join 750+ subscribers