Trieve logo

Trieve

by devflowinc

Trieve is an all-in-one solution for search, recommendations, and RAG. It offers features like semantic vector search, typo-tolerant full-text search, and convenient RAG API routes.

View on GitHub

Last updated: N/A

What is Trieve?

Trieve is a comprehensive platform that combines search, recommendation, and Retrieval-Augmented Generation (RAG) capabilities. It provides tools for semantic vector search, full-text search, and integration with various LLMs.

How to use Trieve?

Trieve can be used through its API, SDKs (Typescript and Python), or by self-hosting the platform. The documentation provides detailed instructions on setting up and using the various features, including API references and guides for local development.

Key features of Trieve

  • Self-Hosting in your VPC or on-prem

  • Semantic Dense Vector Search

  • Typo Tolerant Full-Text/Neural Search

  • Sub-Sentence Highlighting

  • Recommendations

  • Convenient RAG API Routes

  • Bring Your Own Models

  • Hybrid Search with cross-encoder re-ranking

  • Recency Biasing

  • Tunable Merchandizing

  • Filtering

  • Grouping

Use cases of Trieve

  • Building search functionality for websites and applications

  • Creating recommendation systems based on content similarity

  • Implementing RAG pipelines for question answering and content generation

  • Developing internal knowledge bases with advanced search capabilities

FAQ from Trieve

Are we missing a feature that your use case would need?

Call us at 628-222-4090, make a Github issue, or join the Matrix community and tell us! We are a small company who is still very hands-on and eager to build what you need; professional services are available.

How do I get started with local development?

Follow the instructions in the README for installing the necessary packages, setting up environment variables, and starting the services.

Where can I find the API documentation?

The API reference and documentation are available at https://docs.trieve.ai/api-reference.

How can I test cross encoder reranking models?

Follow the additional instructions for testing cross encoder reranking models in the README.

How can I get help with debugging issues?

Reach out to us on discord for assistance. We are available and more than happy to assist.