From e0067dd956697f8d57ee9eb8f8c3cc7ad7e19a3b Mon Sep 17 00:00:00 2001 From: Mingtian Zhang Date: Wed, 11 Jun 2025 00:04:15 +0100 Subject: [PATCH] Update README.md --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index 4d7f198..e1cefb1 100644 --- a/README.md +++ b/README.md @@ -4,8 +4,13 @@ +### We will have a major update to our PageIndex cloud service on June 23, 2025. Stay in touch! + + # 📄 PageIndex + + Are you frustrated with vector database retrieval accuracy for long professional documents? Traditional vector-based RAG relies on semantic *similarity* rather than true *relevance*. But **similarity ≠ relevance** — what we truly need in retrieval is **relevance**, and that requires **reasoning**. When working with professional documents that demand domain expertise and multi-step reasoning, similarity search often falls short. 🧠 **Reasoning-based RAG** offers a better alternative: enabling LLMs to *think* and *reason* their way to the most relevant document sections. Inspired by AlphaGo, we use *tree search* to perform structured document retrieval. @@ -22,6 +27,7 @@ Self-host it with this open-source repo, or try our ☁️ [Cloud service](https Built by Vectify AI. + --- # **⭐ What is PageIndex** @@ -205,6 +211,7 @@ Reply in the following JSON format: - [x] [Detailed examples of document selection, node selection, and RAG pipelines](https://pageindex.vectify.ai/examples/rag) - [x] [Integration of reasoning-based retrieval and semantic-based retrieval](https://pageindex.vectify.ai/examples/hybrid-rag) +- [ ] Release of PageIndex Platform with Retrieval (23rd June 2025) - [ ] Efficient tree search methods introduction - [ ] Technical report on the design of PageIndex