BeMoreHumanOrg/bemorehuman
The recommendation engine with particular focus on uniqueness of the person receiving the rec.
Builds statistical valence models from implicit/explicit rating data (purchases, clicks) via correlation and regression, then serves real-time recommendations through a REST API by matching user history to highest-correlated items. The two-stage architecture—offline valence generation (`valgen`) and in-memory runtime recommendation (`recgen`)—enables sub-25ms latency without external dependencies or telemetry, supporting configurable popularity filters and flexible rating scales across multi-platform deployments.
No commits in the last 6 months.
Stars
50
Forks
—
Language
C
License
MIT
Category
Last pushed
Apr 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/BeMoreHumanOrg/bemorehuman"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Praful932/Kitabe
Book Recommendation System built for Book Lovers📖. Simply Rate ⭐ some books and get immediate...
passadis/ai-assistant
Books recommendation AI engine
sujee/mongodb-atlas-vector-search
Using MongDB Atlas with embedding models and LLMs to do vector search and RAG applications
dvsander/mdb-search
Example application querying data in different ways
Arfazrll/OllamaLLM-RecomendationSystem
An AI book recommendation system built with Streamlit and Ollama. It uses 'nomic-embed-text' for...