Learn how we use massively parallel LLM inference to cheat at search. Don't leave results to chance. See what's new

Blog

Category: Tutorials

Cover image

Accurate Hallucination Detection With NER

Jan 7, 2025 · Dens Sumesh

Using a LLM-as-a-judge for hallucinations is slow and imprecise relative to simple NER. We share how we solved hallucination detection at Trieve.

Cover image

Build a Hotel Voice Agent with Trieve + Vapi

Mar 4, 2025

Step by step guide on how to create a knowledge base from a hotel website and connect it to a Vapi voice agent.

Cover image

How we Built 300μs Typo Detection for 1.3M Words in Rust

Sep 9, 2024 · Dens Sumesh

We explain how we built blazingly fast spellcheck in Rust using BKTrees, Redis queues, and Clickhouse in this blog.

Cover image

Building Search For the YC Company Directory With Trieve, Bun, and SolidJS

Feb 19, 2024 · Nick Khami

Trieve tutorial covering how to use Trieve in order to build an updated search UX for the YC company directory using Bun and SolidJS.

Cover image

Streaming LLM assistant completions with the OpenAI API and Rust Actix-Web

Aug 8, 2024 · Denzell Ford

Guide on how we were able to stream LLM assistant completions in real time using Actix-Web.

Cover image

PGVector's Missing Features

Sep 13, 2024

PGVector offers infrastructure simplicity at the cost of missing some key features desireable in search solutions. We explain what those are in this blog.

Cover image

Guide for Self-Hosting Trieve on a VPS

Sep 12, 2024 · Marcin Stankiewicz

Instructions for self-hosting Trieve on a VPS using docker-compose. You'll be able to set up Trieve on a Hetzner server which comes with semantic and hybrid search, SPLADE fulltext search, re-ranker models, RAG AI Chat, recommendations, and analytics.