playwithllm/store
A RAG-driven image product search that showcases MERN, Milvus for vector indexing, Transformers, and a local Ollama Gemma LLM. Explore integrated embeddings, store vectors in Milvus, and manipulate queries with advanced language understanding.
Implements a complete RAG pipeline combining visual and semantic search through Transformers-based multimodal embeddings stored in Milvus, with Node.js/Express REST APIs bridging the frontend React interface to Ollama's Gemma for query augmentation. The architecture uses semantic similarity matching for product retrieval while leveraging the LLM to interpret natural language queries and refine results. Designed for extensibility with pluggable embedding models and data sources, enabling rapid experimentation with different vector indexing strategies and language models without external API dependencies.
No commits in the last 6 months.
Stars
22
Forks
7
Language
TypeScript
License
—
Category
Last pushed
Apr 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/playwithllm/store"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.