Trieve logo

TrieveInfrastructure for search teams building retrieval and RAG

Infrastructure for search teams building retrieval and RAG. Trieve combines search language models with tools for tuning ranking and relevance. Building excellent search is difficult and can take months to implement then even more time to maintain. Trieve offers production-ready infrastructure that works out of the box to help search teams build adjustable AI search and RAG into their products. With tools for custom models, relevancy weighting, date-recency biasing, semantic full-text hybrid search, recommendations, and more Trieve covers the full spectrum of what a team wants from their discovery infrastructure.

2024-02-29
Active
Early
W24
3
B2B
United States of AmericaAmerica / Canada
Trieve screenshot
More About Trieve

Trieve: AI Search Infrastructure

Introduction

Trieve offers all-in-one infrastructure for building search, recommendations, and RAG (Retrieval-Augmented Generation). Combining search language models with tools for tuning ranking and relevance, Trieve ensures users find exactly what they're looking for every time.

Key Features

  • Private Managed Embedding Models: Use your own embedding model or choose from our open-source hosted defaults.
  • SPLADE Full-Text Neural Search: State-of-the-art retrieval model for full-text search.
  • Semantic Vector Search: Supports semantic vector search out of the box.
  • Hybrid Search: Combines full-text search and semantic vector search with cross-encoder re-ranker models.
  • Merchandising Relevance Tuning: Boost search results based on sales or popularity.
  • Date Recency Biasing: Ensures the most recent results are shown first.
  • Private Open Source Models: Use open-source embedding models and LLMs on our servers to ensure data privacy.
  • Host Yourself: Host on your own servers with terraform templates and no external dependencies.
  • Batteries Included: Comprehensive API surface, numerous features, and thorough documentation.

Use Cases

  • Search: Full-text search with SPLADE and semantic vector search.
  • RAG: Build RAG experiences with generated outputs and citation management.
  • Recommendations: Engage users with recommendations based on history and content similarity.
  • Term Frequency Boosting: Highlight flagship products by boosting certain terms in your search index.
  • Sub-Sentence Highlighting: Show users exactly what they are looking for within long paragraphs.

Pricing

Trieve offers flexible pricing plans to suit different needs. Contact us for detailed pricing information and to find the plan that best fits your requirements.

Teams

Trieve is built by a dedicated team focused on providing industry-leading AI search infrastructure. Our team ensures that you can focus on building unique features while we handle the complexities of search and RAG.

Get started with Trieve today and transform your application's search capabilities.