sede-open/Fleming
Fleming repo to run semantic search models on databricks on CPU.
Provides end-to-end semantic search pipelines combining GitHub repository ingestion, corpus creation, and BERT model training/serving on Databricks MLflow with CPU-based inference. Integrates with GitHub APIs for code extraction, Azure OpenAI for documentation generation, and Databricks serving endpoints for querying embeddings. Includes utilities for tokenization, model registration, and cost-optimized CPU deployment with optional scale-to-zero capabilities.
Stars
14
Forks
5
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sede-open/Fleming"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
databricks-industry-solutions/product-search
Semantic product search on Databricks
Shakeel77-creator/ClassiCore-Public
AI-powered UNSPSC classification tool leveraging semantic search, vector embeddings, and large...
sametcodes/product-taxonomy
Classify your e-commerce products into categories of well-known e-commerce platforms. It uses...
Mule-Mart/Mule-Mart
A dedicated online marketplace for the Colby College community to buy, sell, and donate items,...
Miessa/smartsearch-ecommerce
Semantic e-commerce search engine using Word2Vec built from scratch