The vector search uses semantic embeddings instead of keywords and works best with short texts. With Qdrant, you can build and deploy semantic neural search on your data in minutes. Check out our demo!
Recommendations
User behavior can be represented as a semantic vector is similar way as text or images. Vector database allows you to create a real-time recommendation engine. No MapReduce cluster required.
Semantic search for intent detection is the key chatbot technology. In combination with conversation scripts, modern NLP models and Qdrant, it is possible to build an automated FAQ answering system.
Matching Engines
Matching semantically complex objects is a special case of search. Usually a large number of additional conditions are used in matching, which makes Qdrant an ideal tool for building such systems.
Anomaly detection is one of the non-obvious applications of Similarity Learning. However, it has a number of properties that make it an excellent way to approach anomaly detection.