RediSearch and redis-product-search
The "redis-developer/redis-product-search" tool is an example application that demonstrates how to utilize "RediSearch/RediSearch" for visual and semantic vector similarity search within a Redis Stack environment.
About RediSearch
RediSearch/RediSearch
A query and indexing engine for Redis, providing secondary indexing, full-text search, vector similarity search and aggregations.
Implements compressed inverted indexes for memory-efficient indexing and supports distributed clustering across Redis Enterprise for billion-scale datasets. Built as a Redis module providing a dedicated query language with BM25 ranking, phonetic matching, multi-language stemming, and geospatial/vector KNN search capabilities beyond basic secondary indexes.
About redis-product-search
redis-developer/redis-product-search
Visual and semantic vector similarity with Redis Stack, FastAPI, PyTorch and Huggingface.
Supports both image and text-based vector search through separate embedding models (Img2Vec for images, Sentence Transformers for text), with hybrid filtering capabilities that apply metadata tags as pre-filters before vector similarity operations. Uses Redis's HNSW and flat indexing strategies for approximate and exact nearest-neighbor matching, backed by RedisVL as the Python vector database client. Built as a full-stack SPA with FastAPI backend, React frontend, and Docker Compose orchestration for seamless local development and deployment.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work