QDL123/Periplus
A remote cache for vector databases which allows for a dynamically updated subset of a large dataset to be held entirely in memory.
This project helps operations engineers and data architects who manage large datasets of vector embeddings for AI applications. It acts as an in-memory cache, allowing frequently accessed subsets of vector data to be stored for fast retrieval, bypassing slower disk-based databases. Input consists of vector search queries, and the output is a fast, relevant set of results if the data is cached, or an indication to fetch from the main database otherwise.
No commits in the last 6 months.
Use this if you need to accelerate vector similarity search queries by keeping a dynamically updated, frequently accessed subset of a very large vector dataset in fast memory.
Not ideal if your vector database is small enough to fit entirely in memory, or if you need a standalone vector database solution rather than a caching layer.
Stars
8
Forks
1
Language
C++
License
MIT
Category
Last pushed
Aug 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/QDL123/Periplus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MariaDB/server
MariaDB server is a community developed fork of MySQL server. Started by core members of the...
AlayaDB-AI/AlayaLite
AlayaLite – A Fast, Flexible Vector Database for Everyone.
infiniflow/infinity
The AI-native database built for LLM applications, providing incredibly fast hybrid search of...
nnethercott/hannoy
Production-ready KV-backed HNSW implementation in Rust using LMDB
dingodb/dingo
A multi-modal vector database that supports upserts and vector queries using unified SQL...