Hybrid Search Engine
Sub-second semantic search across a multilingual product catalogue. Keyword (BM25), dense vector and image embeddings are blended into a single hybrid ranking — customers find products they didn't even know to look for.
Stack
QdrantPythonFastAPIHybrid SearchDense VectorsBM25Image EmbeddingsGemini RerankRedis Cache
The store exposes its full catalogue through one search bar — suggestions surface before a single key is pressed.
1 / 4
Up next
- Agent assuranceAgentTwinCatches the agent regressions a 200 OK hides — down to the step where they begin.
- Topic intelligenceContextLensFollows what a conversation is about — and can answer “uncertain” instead of guessing.
- Relational MLRealPathAnswers predictive questions straight from related tables — leakage-tested and explained.


