freshcrate
Skin:/
Home > Databases > knowhere

knowhere

Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.

Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.

README

Knowhere Logo

This document will help you to build the Knowhere repository from source code and to run unit tests. Please file an issue if there's a problem.

Introduction

Knowhere is written in C++. It is an independent project that act as Milvus's internal core.

Building Knowhere Within Milvus

If you wish to only use Knowhere within Milvus without changing any of the Knowhere source code, we suggest that you move to the Milvus main project and build Milvus directly, where Knowhere is then built implicitly during Milvus build.

System Requirements

All Linux distributions are available for Knowhere development. However, a majority of our contributor worked with Ubuntu or CentOS systems, with a small portion of Mac (both x86_64 and Apple Silicon) contributors. If you would like Knowhere to build and run on other distributions, you are more than welcome to file an issue and contribute!

Here's a list of verified OS types where Knowhere can successfully build and run:

  • Ubuntu 22.04 x86_64
  • Ubuntu 22.04 Aarch64
  • Ubuntu 20.04 x86_64 / Aarch64 (EOL by April 2025 and kept for legacy reasons; see scripts/install_deps.sh for details)
  • MacOS (x86_64)
  • MacOS (Apple Silicon)

Building Knowhere From Source Code

Install Dependencies

scripts/install_deps.sh install all dependencies for building, testing, and shipping the knowhere library. If you don't need the full pipeline, please refer to the file and modify it for a more fine-grained dependency control.

$ bash scripts/install_deps.sh

Build From Source Code

A top-level Makefile provides a unified build interface. Run make help to see all targets and flags.

# CPU release (default)
$ make

# GPU release (cuVS)
$ make WITH_GPU=True

# CPU with unit tests
$ make WITH_UT=True

# CPU UT + AddressSanitizer
$ make WITH_UT=True WITH_ASAN=True

# GPU with unit tests
$ make WITH_GPU=True WITH_UT=True

# Debug build
$ make WITH_DEBUG=True

# Custom compiler via Conan profile (e.g. clang, gcc-15)
$ make CONAN_PROFILE=clang14

Running Unit Tests

# requires a prior build with WITH_UT=True
$ make test

Clean up

$ make clean

Python Wheel

Building the Python wheel requires swig and Python development headers (python3-dev on Ubuntu). These are installed automatically by scripts/install_deps.sh.

After building Knowhere with a Release configuration:

# Build portable manylinux wheel
$ make wheel

# Install
$ pip3 install python/dist/pyknowhere-*-manylinux*.whl

For more options (clean build, verbose, custom Python binary), see python/build_portable_wheel.sh -h.

Contributing

Pre-Commit

Before submitting a pull request, run pre-commit checks locally:

pip3 install pre-commit
pre-commit install --hook-type pre-commit --hook-type pre-push

# Run all pre-commit hooks
$ make pre-commit

# Or run individually:
$ make format   # clang-format
$ make lint     # clang-tidy (requires a prior build)

If clang-format and clang-tidy are not already installed:

# linux
apt install clang-format clang-tidy
# mac
brew install llvm
ln -s "$(brew --prefix llvm)/bin/clang-format" "/usr/local/bin/clang-format"
ln -s "$(brew --prefix llvm)/bin/clang-tidy" "/usr/local/bin/clang-tidy"

Release History

VersionChangesUrgencyDate
v3.0.3## What's Changed * Update build scripts by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1619 * Reset cardinal SHA by @yhmo in https://github.com/zilliztech/knowhere/pull/1626 * Optimize BM25 scoring in DAAT MaxScore by @lyang24 in https://github.com/zilliztech/knowhere/pull/1629 * upgrade faiss 1.14.1+, commit cb69d7c5665241d1e84f476105ffb6fd6c7c192c by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1635 * fix: reject invalid HNSW binary metrics in static conHigh5/30/2026
v2.6.14## What's Changed * chore: [2.6] update v2 dependency version by @foxspy in https://github.com/zilliztech/knowhere/pull/1625 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.6.13...v2.6.14High5/12/2026
v2.6.11## What's Changed * [2.6] fix: wheel build fails silently when setup.py crashes by @jamesgao-jpg in https://github.com/zilliztech/knowhere/pull/1541 * [2.6] update cardinal version by @chasingegg in https://github.com/zilliztech/knowhere/pull/1539 * fix: [2.6 cherry-pick] check brute-force threshold before iterator path in HNSW RangeSearch by @foxspy in https://github.com/zilliztech/knowhere/pull/1536 * [2.6] make 2.6 branch compile with cardinal by @chasingegg in https://github.com/zillizteHigh4/3/2026
v2.6.10## What's Changed * Add AVX512 to sparse inverted index (IP) by @lyang24 in https://github.com/zilliztech/knowhere/pull/1414 * Fix a problem in test_emb_list.cc, related to C++ compiler optimizations by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1436 * fix missing boost include by @chasingegg in https://github.com/zilliztech/knowhere/pull/1438 * update cardinal version by @chasingegg in https://github.com/zilliztech/knowhere/pull/1437 * enhance: add claude md for knowheLow1/26/2026
v2.5.8## What's Changed * Fix scann filter search performance and cleanup ensure_topk_full config by @chasingegg in https://github.com/zilliztech/knowhere/pull/1179 * fix: optimize boolean config parsing in json by @foxspy in https://github.com/zilliztech/knowhere/pull/1186 * fix a problem of incorrect VPOPCNTDQ instruction set detection by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1190 * fix: share the pool externally to ensure that other tasks can be scheduled by @foxspy inLow1/20/2026
v2.6.9## What's Changed * fix:Adjustment of the data view index parameters' scope by @cqy123456 in https://github.com/zilliztech/knowhere/pull/1423 * fix: minhash functions support avx512 by @cqy123456 in https://github.com/zilliztech/knowhere/pull/1424 * Fix a bug of fvec_L2sqr_*() not matching a reference implementation by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1426 * fix: Fix for incorrect mask handling and treating u64 as u32 in minhash functions by @cqy123456 in httpsLow1/14/2026
v2.6.6## What's Changed * [Test] Add refine type for IVF_PQ/IVF_SQ by @CLiqing in https://github.com/zilliztech/knowhere/pull/1371 * fix pyknowhere Dump/Load by @chasingegg in https://github.com/zilliztech/knowhere/pull/1387 * enhance: update cardinal v1 version by @foxspy in https://github.com/zilliztech/knowhere/pull/1388 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.6.5...v2.6.6Low12/30/2025
v2.6.7## What's Changed * add log for re-search in hnsw by @chasingegg in https://github.com/zilliztech/knowhere/pull/1390 * FEAT: Support RVV-optimized Scalar Quantizer by @hansu2022 in https://github.com/zilliztech/knowhere/pull/1396 * fix: bruteforce_emblist support empty_list (length==0) by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1394 * feat: emb list support ivfflat / ivfflatcc by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1397 * fix: build portableLow12/30/2025
v2.6.8## What's Changed * Add validation to prevent building illegal IVF indexnode for emb_list by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1411 * feat: support brute_force search and iterator with chunked dataset by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1409 * add feature emb_list for ivf_flat int8 by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1415 * Add sq4 for HNSW by @CLiqing in https://github.com/zilliztech/knowhere/pull/1406 Low12/30/2025
v2.6.4## What's Changed * [skip e2e]: update cardinal version by @foxspy in https://github.com/zilliztech/knowhere/pull/1356 * feat: emb list support within index_node by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1352 * feat: cardinal support emb_list by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1357 * fix ut: emb list hnsw / diskann by @alwayslove2013 in https://github.com/zilliztech/knowhere/pull/1360 * fix ut: add check function for emblist by @marceloLow10/20/2025
v2.6.0## What's Changed * enhance: sparse: Add support for persistency of sparse indexes by @sparknack in https://github.com/zilliztech/knowhere/pull/1238 * feat(simd/rvv): add RVV SIMD optimization for int8_vec_inner_product, int8_vec_L2sqr, int8_vec_norm_L2sqr by @lyd1992 in https://github.com/zilliztech/knowhere/pull/1240 * feat(simd/rvv): add RVV SIMD optimization for int8_vec batch_4 functions by @lyd1992 in https://github.com/zilliztech/knowhere/pull/1242 * sparse: change index file header sLow7/23/2025
v2.5.5## What's Changed * [bug] fix IVFPQFastScan::RangeSearch() on ARM by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1116 * fix ARM bf16 patch functions by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/1120 * enhance: reduce the queuing problem caused by the mixed task of growing index and sealed index by @foxspy in https://github.com/zilliztech/knowhere/pull/1126 * fix: add use_knowhere_build_pool param for BuildAsync by @foxspy in https://github.com/zillizLow4/11/2025
v2.5.4## What's Changed * [skip e2e] Change CI timeout to 120min by @cydrain in https://github.com/zilliztech/knowhere/pull/1099 * Add Int8Vector SIMD APIs for avx512/avx2/sse/ref by @cydrain in https://github.com/zilliztech/knowhere/pull/1098 * Add benchmark_simd_qps by @cydrain in https://github.com/zilliztech/knowhere/pull/1101 * enhance: SCANN_DVR support different refine type in train and search process by @cqy123456 in https://github.com/zilliztech/knowhere/pull/1106 * Add neon implementatiLow4/10/2025
v2.5.3## Features * support diskann mv(cloud only) by @chasingegg in https://github.com/zilliztech/knowhere/pull/1045 * knowhere support data view index node by @cqy123456 in https://github.com/zilliztech/knowhere/pull/1016 ## Enhance * scann support search parameter 'ensure_topk_full' by @cqy123456 in https://github.com/zilliztech/knowhere/pull/1072 ## Bugfix * fix : for all empty sparse index, PrepareMmap will early return to avoid mmapping empty file by @sparknack in #1050 **Full CLow2/7/2025
v2.5.2## Features * add max score ratio downscaling for approximate searching on sparse vector @sparknack in #1018 * add DAAT MaxScore support for sparse vector by @sparknack in #1015 * support MV only for HNSW by @chasingegg in #1020 ## Improvements * Iterator thread control optimization by @alwayslove2013 in #1008 * memory usage optimization for sparse vector by @sparknack in #1011 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.5.1...v2.5.2Low1/14/2025
v2.5.1## What's Changed * enhance: scann support iterator by @cqy123456 in https://github.com/zilliztech/knowhere/pull/992 * make FileReader to close fd using RAII by @zhengbuqian in https://github.com/zilliztech/knowhere/pull/1005 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.5.0...v2.5.1Low12/26/2024
v2.3.14## What's Changed * enhance: optimize sparse index and get ~10% performance improvement @zhengbuqian in https://github.com/zilliztech/knowhere/pull/968 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.3.13...v2.3.14Low12/6/2024
v2.3.13## Features * update raft to 24.10 by @Presburger in #914 * raft index supports cosine similarity by @Presburger in #924 * add optimized distiance functions for PowerPC by @carll99 in #894 ## Improvements * accelerate the distance computation for ARM NEON by @Presburger in #922 * mmap almost everything for sparse vector index by @zhengbuqian in #928 * accelerate the brute-force performance with cosine metric by adding avx simd support and pre-compute the norms by @cqy123456 in #950 Low11/18/2024
v2.5.0draft ## What's Changed * update raft to 24.10 by @Presburger in https://github.com/zilliztech/knowhere/pull/914 * Fix group search by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/913 * fix : add config check for open and closed range settings by @foxspy in https://github.com/zilliztech/knowhere/pull/915 * fix: knowhere ut bugfix by @foxspy in https://github.com/zilliztech/knowhere/pull/918 * raft index supports cosine similarity by normalizing the input data. by @PresbuLow11/15/2024
v2.3.12## Features * async build support for cardinal by @Presburger in https://github.com/zilliztech/knowhere/pull/873 * provide a static checking method for index config by @foxspy in https://github.com/zilliztech/knowhere/pull/888 ## Improvements * add a bit-based structure to mark index-specific features by @foxspy in https://github.com/zilliztech/knowhere/pull/887 ## Bug Fixes * fix: copy the query vector to resolve the use-after-free issue for ivf-iterator by @alwayslove2013 in https://Low10/25/2024
v2.3.11## What's Changed * FAISS HNSW range search support by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/853 * Update knowhere default thread priority by @congqixia in https://github.com/zilliztech/knowhere/pull/868 * Remove cache for graph search by @liliu-z in https://github.com/zilliztech/knowhere/pull/872 * fix raft compile error by @Presburger in https://github.com/zilliztech/knowhere/pull/876 * Iterator support for diskann by @alwayslove2013 in https://github.com/zilliztLow10/11/2024
v2.3.10# What's Changed ## Features * Iterator support for faiss hnsw indices by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/823 * Add knowhere static interface for milvus to estimate loading resource by @foxspy in https://github.com/zilliztech/knowhere/pull/836 ## Improvements * Skip coverage check for trace code by @cydrain in https://github.com/zilliztech/knowhere/pull/858 * Enhance BM25 performance issue by @zhengbuqian in https://github.com/zilliztech/knowhere/pull/851 *Low9/20/2024
v2.3.9# What's Changed ## Features * faiss hnsw supports `GetVectorByIds` by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/801 ## Improvements * Use SIMD to accelerate the float vector normalization procedure by @cydrain in https://github.com/zilliztech/knowhere/pull/797 https://github.com/zilliztech/knowhere/pull/802 * Add API description for index_node by @liliu-z in https://github.com/zilliztech/knowhere/pull/800 * Optimize error messages when encountering unsupported data Low9/6/2024
v2.3.8## Features * Add support for Iterator on IVFSQ8 #772 ## Improvements * Provide a static API to check if any index type contains raw vector data #751 * Iterator now supports returning results in order of distance through parameters #755 #766 * Expose Knowhere's config validation API through C interface #760 ## Bug Fixes * Fix the issue where sparse INVERTED_INDEX couldn't handle empty vectors #775Low8/28/2024
v2.3.7## Features * Support using CAGRA for indexing and HNSW for searching ## Improvements * Provide an API to check if any index type supports mmap #698 * When HNSW search results are fewer than k, use brute force search to ensure the number of results #711 * Add more monitor metrics #717 #732 * Support SIMD acceleration of FP16/BF16 computations #723 ## Changes * RangeSearch terminates early based on `topk`, and won't return more than topk results #700 * Sparse Index now supportsLow7/19/2024
v2.2.7## What's Changed * fix: [cherry-pick]Replace gettid() with syscall(SYS_gettid) by @xige-16 in https://github.com/zilliztech/knowhere/pull/697 ## New Contributors * @xige-16 made their first contribution in https://github.com/zilliztech/knowhere/pull/697 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.2.6...v2.2.7Low7/19/2024
v2.3.6## What's Changed * Add data type conversion test by @cydrain in https://github.com/zilliztech/knowhere/pull/653 * Update BruteForce ut for multi data type by @cydrain in https://github.com/zilliztech/knowhere/pull/656 * Clean build warnings by @cydrain in https://github.com/zilliztech/knowhere/pull/657 * Support numpy array to sparse dataset in pyknowhere api by @chasingegg in https://github.com/zilliztech/knowhere/pull/654 * cagra support train on gpu, search on cpu, use hnswlib by @PresbLow7/4/2024
v2.3.5## What's Changed * fix: make GetIsSparse const by @zhengbuqian in https://github.com/zilliztech/knowhere/pull/627 * check the combination of index type and data type by @cqy123456 in https://github.com/zilliztech/knowhere/pull/634 * add sparse support type in knowherecheck by @cqy123456 in https://github.com/zilliztech/knowhere/pull/635 * [skip ci] Add diskann benchmark test by @cydrain in https://github.com/zilliztech/knowhere/pull/637 * register index(binary_hnsw) in knowhere by @cqy1234Low6/14/2024
v2.3.4## What's Changed * Dockerfile optimizations * Add Size interface for binaryset * Replace binary hnsw when cardinal is enabled * Removed `seed_ef` for iterator and use `ef` directly for HNSW * Fix iterator based range search for similarity metric when range filter is not provided ## New Contributors * @chyezh made their first contribution in https://github.com/zilliztech/knowhere/pull/586 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.3.3...v2.3.4Low5/30/2024
v2.3.2## What's Changed * [cherry-pick] AIX-related patches from the Faiss baseline by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/526 * [cherrypick] Unroll loop in lookup_2_lanes for PQFasfScan for PPC64 by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/524 * fix compiler warnings by @alexanderguzhva in https://github.com/zilliztech/knowhere/pull/527 * sparse float vector index to support mmap when loading from index file by @zhengbuqian in https://github.com/Low5/14/2024
v2.3.1## What's Changed * remove two unused variables by @zhjwpku in https://github.com/zilliztech/knowhere/pull/495 * [improvement] Make MAP_POPULATE configurable by @foxspy in https://github.com/zilliztech/knowhere/pull/499 * Fix create index log by @chasingegg in https://github.com/zilliztech/knowhere/pull/504 * knowhere light for milvus local by @Presburger in https://github.com/zilliztech/knowhere/pull/502 * Fix SQ4 AVX-512 implementation by @alexanderguzhva in https://github.com/zilliztech/Low4/29/2024
v2.2.6## What's Changed * Add bf16 distance calculator patch for zilliz-cloud (#519 ) by @foxspy in https://github.com/zilliztech/knowhere/pull/525 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.2.5...v2.2.6Low4/24/2024
v2.3.0# Release Notes ### What's new? - **Sparse Index:** - Introduced sparse vectors. Indexes `SPARSE_WAND` and `SPARSE_INVERTED_INDEX` are supported. - **GPU-based indexes:** - Supported `CAGRA`, a GPU-based graph index from Nvidia. - Supported `BRUTE_FORCE` for GPU. - **Iterator:** - Iterating approximately nearest vector is supported. A new API `Interator` is introduced for `HNSW` and `IVF`-series indexes. - `SPARSE_WAND` and `SPARSE_INVERTED_INDEX` also supports iterators. -Low4/7/2024
v2.3.0-beta# Release Notes ### What's new? - **Sparse Index:** - Introduced sparse vectors. Indexes `SPARSE_WAND` and `SPARSE_INVERTED_INDEX` are supported. - **GPU-based indexes:** - Supported `CAGRA`, a GPU-based graph index from Nvidia. - Supported `BRUTE_FORCE` for GPU. - **Iterator:** - Iterating approximately nearest vector is supported. A new API `Interator` is introduced for `HNSW` and `IVF`-series indexes. - **Multiple Data Types:** - Knowhere now supports `BF16` and `FP16` aLow3/15/2024
v2.2.5## What's Changed * Bugfix for diskann index building (#385) by @foxspy in https://github.com/zilliztech/knowhere/pull/386 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v2.2.4...v2.2.5Low2/19/2024
v2.2.4## What's Changed * Upgrade conan to 1.61.0 (#182) by @chasingegg in https://github.com/zilliztech/knowhere/pull/347 * switch knowhere-test branch to 2.2 by @cqy123456 in https://github.com/zilliztech/knowhere/pull/384 * [2.2] Ensure topk results for IVF_FLAT_CC (#353) by @chasingegg in https://github.com/zilliztech/knowhere/pull/383 * [fix 2.2]: make sure we rethrow exceptions in async tasks by @zhengbuqian in https://github.com/zilliztech/knowhere/pull/382 * [2.2 fix] wrap IVF index trainLow2/4/2024
v2.2.3# Release Notes ### Enhancements and Fixes - Remove the by default 6400 results limit for DiskANN range search.(https://github.com/zilliztech/knowhere/pull/237) - Remove `search_list_and_k_ratio` from the parameter list for range search.(https://github.com/zilliztech/knowhere/pull/258) - Add more logs to indicate the index building process for HNSW and DiskANN.(https://github.com/zilliztech/knowhere/pull/260, https://github.com/zilliztech/knowhere/pull/261) - Correct Cosine distance underLow12/26/2023
v1.3.21## What's Changed * Add async thread pool for generating diskann cache and catch unexpected return. by @cqy123456 in https://github.com/zilliztech/knowhere/pull/226 * Change async thread pool size to 1 by @cqy123456 in https://github.com/zilliztech/knowhere/pull/234 * Add some log for diskann prepare by @cqy123456 in https://github.com/zilliztech/knowhere/pull/235 * Fix diskann async cache by @liliu-z in https://github.com/zilliztech/knowhere/pull/250 **Full Changelog**: https://github.Low12/5/2023
v1.3.20## What's Changed * Generate diskann cache asynchronously. by @cqy123456 in https://github.com/zilliztech/knowhere/pull/191 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v1.3.19...v1.3.20Low11/22/2023
v1.3.19## What's Changed * Reverted changes to modify knowhere threads scheduling priority **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v1.3.18-hotfix...v1.3.19Low11/2/2023
v2.2.2# Release Notes ### What's New - **`SCANN` without refine:** (#77) - `SCANN` now supports a `with_raw_data` config option to determine whether the refine process is needed. Omitting the refine step can dramatically reduce memory usage (to approximately 1/17 of the original). - **Multi devices for GPU:** (#83 #146) - GPU indexes can now be distributed in different cards to accelerate and the performance and enlarge the capacity. - **Remove `IVF_FLAT_NM`:** (https://github.com/zillLow10/19/2023
v1.3.18-hotfix## What's Changed * Fix DiskANN LRU Set Invalid Medoid by @PwzXxm in https://github.com/zilliztech/knowhere/pull/97 **Full Changelog**: https://github.com/zilliztech/knowhere/compare/v1.3.18...v1.3.18-hotfixLow9/19/2023
v2.2.1## What's Changed * Temporary solution to fix ivf_flat search result wrong when cosine by @cydrain in https://github.com/zilliztech/knowhere/pull/36 * Fix scann add_with_ids logic by @chasingegg in https://github.com/zilliztech/knowhere/pull/45 * Fix brute force search wrong when COSINE by @cydrain in https://github.com/zilliztech/knowhere/pull/48 * Fix segment fault when use config load a list by @Presburger in https://github.com/zilliztech/knowhere/pull/49 ## New Contributors * @weiliuLow9/6/2023
v2.2.0# Release Notes ### New Features - **FastScan Integration with FAISS**: (https://github.com/zilliztech/knowhere/pull/1) - Introducing support for `FastScan` from `FAISS`. Functionally analogous to `SCANN`, FastScan utilizes a 4-bit PQ with IVF to enhance the search speed, making it ideal for high-dimensional vector searches. - **New index type IVF_FLAT_CC**: (https://github.com/milvus-io/knowhere/pull/824) - Introducing new index type IVF_FLAT_CC for growing segment searching. - Low8/22/2023
v1.3.18## What changes - Deprioritize the thread pool to ensure the main thread's healthy.Low8/22/2023

Dependencies & License Audit

Loading dependencies...

Similar Packages

endeeEndee.io – A high-performance vector database, designed to handle up to 1B vectors on a single node, delivering significant performance gains through optimized indexing and execution. Also available i1.3.5
lancedbDeveloper-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.python-v0.33.1-beta.2
topkTopK is a search engine for the AI era.cli-v0.11.0
vespaAI + Data, online. https://vespa.aiv8.699.8
awesome-vector-databaseA curated list of awesome works related to high dimensional structure/vector search & databasemain@2026-06-02

More from zilliztech

memsearchA Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
VectorDBBenchBenchmark for vector databases.
vector-graph-ragGraph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

More in Databases

WeKnoraLLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
ai-real-estate-assistantAdvanced AI Real Estate Assistant using RAG, LLMs, and Python. Features market analysis, property valuation, and intelligent search.
alibabacloud-adb20211201Alibaba Cloud adb (20211201) SDK Library for Python
milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search