kagisearch/vectordb
A minimal Python package for storing and retrieving text using chunking, embeddings, and vector search.
This tool helps you quickly find relevant information within a large collection of text documents, like articles or reports. You provide it with your text content and any associated details (like URLs or titles), and it allows you to search through it using natural language queries. It's designed for anyone who needs to quickly pinpoint specific concepts or facts across many documents without having to manually read through everything.
783 stars. No commits in the last 6 months.
Use this if you need to build a system that can understand and retrieve specific pieces of information from a large pool of text based on the meaning of a query, rather than just keywords.
Not ideal if you primarily need to perform complex data analysis, numerical computations, or highly structured database queries rather than semantic text search.
Stars
783
Forks
42
Language
Python
License
MIT
Category
Last pushed
Oct 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/kagisearch/vectordb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apconw/Aix-DB
Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
FalkorDB/code-graph
A code-graph demo using GraphRAG-SDK and FalkorDB
symfony/ai-store
Low-level abstraction for storing and retrieving documents in a vector store.
awa-ai/awadb
AI Native database for embedding vectors
niclasko/Cypher.js
Cypher graph database for Javascript