github-featured/vectifyai--pageindex
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity

Feat/newreadme (#419)

Browse Source 
* improve readme
This commit is contained in:
Mingtian Zhang
2026-08-20 16:59:20 +08:00
committed by GitHub
parent 18ea86a643
commit 5f44d691f3
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -4
View File
@@ -41,7 +41,7 @@
## What is PageIndex?
Are you frustrated with vector database retrieval accuracy for long professional documents? Vector-based RAG retrieves by semantic **similarity**. But **similarity ≠ relevance** — what retrieval actually needs is relevance, and relevance requires **reasoning**. On professional documents that demand contextual understanding, domain expertise, and multi-step reasoning, similarity search misses what is relevant but not similar, and returns what is similar but not relevant.
Are you frustrated with vector database retrieval accuracy for long and complex documents? Vector-based RAG retrieves by semantic **similarity**. But **similarity ≠ relevance** — what retrieval actually needs is relevance, and relevance requires **reasoning**. On professional documents that demand contextual understanding, domain expertise, and multi-step reasoning, similarity search misses what is relevant but not similar, and returns what is similar but not relevant.
Inspired by AlphaGo, **[PageIndex](https://vectify.ai/pageindex)** replaces the vector index with a **hierarchical tree index** and lets an LLM **reason** its way through it — the way a human expert flips to the right section of a long report. Retrieval happens in two steps:
@@ -59,10 +59,10 @@ Inspired by AlphaGo, **[PageIndex](https://vectify.ai/pageindex)** replaces the
| | Vector RAG | **PageIndex** |
|---|---|---|
| **Index** | embeddings in a vector DB | tree structure of the document itself |
| **Index** | vector index | tree index |
| **Unit** | fixed-size chunks | natural sections |
| **Retrieval** | approximate similarity search | LLM reasoning over the tree |
| **Result** | opaque, “vibe retrieval” | traceable to explicit sections and page numbers |
| **Retrieval** | semantic similarity search | LLM-based relevance search |
| **Result** | opaque, “vibe retrieval” | traceable to explicit references |
| **Context** | query embedding only | full context: conversation history, domain knowledge |
It is ideal for financial reports, legal documents, regulatory filings, technical manuals, medical literature, academic textbooks — any long, complex professional document.