Semantic Vector Search
For when you need more than just full-text search. Trieve supports semantic vector search out of the box.
BM25 & SPLADE Full-Text Search
Choose between the leading state-of-the-art retrieval models for full-text search.
Stock and Custom Embedding models
Our modular infrastructure offers several models and bring your own embedding model.
Hybrid Search
Get the best of both worlds. Trieve supports hybrid search, combining full-text search and semantic vector search with cross-encoder re-ranker models.
Merchandising & Relevance tuning
Tune and boost search results to hit your KPIs via the API or no-code dashboard.
Sub-sentence Highlighting
Search results can get long. Sub-sentence highlights show users exactly what they are looking for, quick.
Private Open-Source Models
We use open source embedding models and LLMs running in our own servers. Data is never leaked.
Batteries Included
Our API surface covers chunking, ingestion, search, recommendations, RAG, and even a little front-end.
Self-Hostable
Sensitive data? Need maximum performance? Host Trieve yourself with terraform templates and no external dependencies.
