The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
-
Updated
Nov 12, 2026 - C++
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
multi-vectorHere are 11 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
search-engine vector nearest-neighbor-search full-text-search approximate-nearest-neighbor-search embedding bm25 information-retrival cpp20 rag hnsw vector-search vector-database hybrid-search cpp20-modules ai-native tensor-database vectordatabase multi-vector
NextPlaid, ColGREP: Multi-vector search, from database to coding agents.
Coltt is a vector database that supports Multi-Vector Search, high-performance HNSW, FLAT and quantization, and enables fast searches through sophisticated internal data shard design.
distributed-systems database key-value bitmap distributed-database cosine-similarity kv semantic-search hnsw vector-search vector-database hybrid-search multi-vector
High-quality search for AI-native applications.
search retrieval embedding-models keyword-search rag vector-search vector-database hybrid-search multi-vector late-interaction
[ICML'26] LEMUR reduces multi-vector retrieval for late interaction models such as ColBERT into regular single-vector retrieval.
embeddings nearest-neighbor-search approximate-nearest-neighbor-search colbert multi-vector late-interaction multi-vector-embeddings
A Java implementation of HNSW with multi-vector search support
java maven java-library semantic-search similarity-search hnsw vector-embedding vector-search java-17 nearest-neighbors-search multi-vector
HeatPro Python Package: Generate Heat Demand Load Profile for District Heating
CryptGuardian is a research-level concept, created from the perspective of a developer concerned about long-term security for distributed systems. It is not a final product, but an exploration of defense strategies against modern and future threats, including AI-assisted attacks and quantum cryptanalysis.
security crypto math regex guardian blockchain seed cybersecurity blockchain-technology ddos-tool security-tools insane reputation-system blockchain-tool risk-scoring forensics-tools cybersecurity-tools block-validation multi-vector quarantine-system
ColBERT-style late-interaction MaxSim scoring for multi-vector retrieval — tiny, zero-dependency Rust crate
Climate Monitoring Search Engine built on MultiVectors using Qdrant
vector geospatial structured climate-change structured-output climate-analysis vector-search huggingface streamlit vector-database vector-embeddings qdrant inference-client multi-vector
🎮 Engage in neon-drenched arena combat for 1-8 players locally or join up to 99 in Battle Royale mode. Experience fast-paced, thrilling gameplay!
javascript search-engine arena neovim asset-manager p2p nearest-neighbor-search full-text-search surge canvas2d itam asset-management hnsw vector-search bert-embeddings multi-vector
Add this topic to your repoTo associate your repository with the multi-vector topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |