gottingen/kumo-search
docs for search system and ai infra
Implements a full-stack search engine framework supporting inverted/forward indexing, ranking, caching, and hierarchical indexes, with dynamic business logic updates via an AOT Python-to-C++ compiler that generates binaries without service restarts. Built on the EA (Elastic Atomic) infrastructure platform using RPC (melon), vector engines (phekda), and RocksDB-based storage (mizar), with integrated service discovery, metadata management, and multi-cluster orchestration across data centers.
222 stars. No commits in the last 6 months.
Stars
222
Forks
22
Language
—
License
Apache-2.0
Category
Last pushed
Jul 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gottingen/kumo-search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GustyCube/Codect
A detector for AI-written code
isaacus-dev/isaacus-typescript
A server-side JavaScript/TypeScript library for interacting with the Isaacus API.
AtomicSearch/AI-search-engine
Instant AI Search Engine, using React with ViteJS 🚀 A modern and personalized AI engine
davidemiceli/natural-language-flows
A very simple prototype of Natural Language Flow builder and Natural Language Generator for...
neuml/mlflow-txtai
MLflow automatic tracing for txtai