Release

Phasing Out N-to-1: Upgrading Multi-path Knowledge Retrieval

We're phasing out the N-to-1 retrieval strategy on September 1, 2024, and introducing a more flexible Multi-path retrieval strategy. We recommend switching to this new approach to boost your application's retrieval efficiency.

Pan

Product Operation

Joshua

Content Marketing

Written on

Aug 1, 2024

Share

Share to Twitter
Share to LinkedIn
Share to Hacker News

Release

·

Aug 1, 2024

Phasing Out N-to-1: Upgrading Multi-path Knowledge Retrieval

We're phasing out the N-to-1 retrieval strategy on September 1, 2024, and introducing a more flexible Multi-path retrieval strategy. We recommend switching to this new approach to boost your application's retrieval efficiency.

Pan

Product Operation

Joshua

Content Marketing

Share to Twitter
Share to LinkedIn
Share to Hacker News

Release

Phasing Out N-to-1: Upgrading Multi-path Knowledge Retrieval

We're phasing out the N-to-1 retrieval strategy on September 1, 2024, and introducing a more flexible Multi-path retrieval strategy. We recommend switching to this new approach to boost your application's retrieval efficiency.

Pan

Product Operation

Joshua

Content Marketing

Written on

Aug 1, 2024

Share

Share to Twitter
Share to LinkedIn
Share to Hacker News

Release

·

Aug 1, 2024

Phasing Out N-to-1: Upgrading Multi-path Knowledge Retrieval

Share to Twitter
Share to LinkedIn
Share to Hacker News

Release

·

Aug 1, 2024

Phasing Out N-to-1: Upgrading Multi-path Knowledge Retrieval

Share to Twitter
Share to LinkedIn
Share to Hacker News

Dify is taking a step forward in knowledge base retrieval. Come September 1, 2024, we're moving away from the N-to-1 retrieval strategy and embracing a more versatile Multi-path retrieval approach. This update is designed to significantly enhance your application's retrieval efficiency. We urge you to act now: Switch to Multi-path retrieval for an improved strategy that adapts to your unique needs and delivers results with high accuracy.

Why retire "N-to-1 retrieval"?

Our analysis has uncovered key limitations in the N-to-1 retrieval strategy. This approach restricts searches to a single knowledge base and relies heavily on LLM interpretation of knowledge base descriptions. As a result, it often produces incomplete or inaccurate results, compromising retrieval quality. Feedback from our community supports these findings, driving our decision to move towards a more effective solution.

A Better Solution: Configurable "Multi-path Retrieval"

Our enhanced Multi-path retrieval strategy offers:

  • Optional reranking strategies

  • Semantic and keyword weighting for optimized retrieval

  • Integration with reranking models (e.g., Cohere, Jina) for peak performance

We recommend using this new setup for more accurate retrieval.

What you need to do

Dify Cloud Users: Switch from "N-to-1 retrieval" to "Multi-path retrieval" in Context > Retrieval Setting. We encourage you to make this change before September 1, 2024, to ensure optimal performance and take full advantage of the new features. If you haven't made the switch by then, we'll automatically update your settings to Multi-path retrieval on that date.

Community and Enterprise Users: If you're running v0.6.16, we also encourage you to transition to Multi-path retrieval before September 1. Our User Guide provides detailed configuration steps to help you maximize performance. Our September 1 release will automatically transition all users to Multi-path retrieval. After the update, if you experience any performance shifts, you'll have the flexibility to manually fine-tune your retrieval settings as needed.

Optimizing "Multi-path Retrieval" with Rerank

Multi-path retrieval in Dify offers two primary configuration options: Keyword & Semantic Weighted Score and Rerank Model selection.

Keyword & Semantic Weighted Score Configuration

Keyword-only (weight: 1): Best for exact matches. It's fast and efficient, especially for large knowledge bases. Use this when your users know precisely what they're looking for.

Semantic-only (weight: 1): Understands the meaning behind queries. It can find relevant info even without exact keyword matches. Great for multilingual content and complex searches.

Custom weight balance: Blend keyword and semantic approaches to fit your needs. Adjust the mix to match your unique business requirements or complex information structure.

Rerank Model

For unparalleled retrieval precision, implementing a rerank model is key. This refines initial results, dramatically enhancing overall accuracy.

For detailed configuration steps and best practices, please refer to our documentation.

Looking ahead

This upgrade marks the beginning of our journey to enhance Dify's RAG capabilities. We're committed to refining our RAG system, prioritizing flexibility and openness to serve our diverse community and customer needs.

Your insights are crucial as we grow. Join our community and help us shape the future of Dify.

On this page

    The Innovation Engine for Generative AI Applications

    The Innovation Engine for Generative AI Applications

    The Innovation Engine for Generative AI Applications