From 7764d37e8db27f06c2ad234d6cffccc861bee9cc Mon Sep 17 00:00:00 2001
From: zTgx <747674262@qq.com>
Date: Thu, 16 Apr 2026 00:31:53 +0800
Subject: [PATCH] docs(README): update image dimensions and spacing
- Increase image width from 720px to 900px for better visibility
- Add blank line after the main description section
---
README.md | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
index dae45c0e..96d73505 100644
--- a/README.md
+++ b/README.md
@@ -15,7 +15,7 @@
**Vectorless** is a reasoning-native document engine designed to be the foundational layer for AI applications that need structured access to documents, with the core written in Rust. It does not use vector databases, embeddings, or similarity search. Instead, it transforms documents into hierarchical semantic trees and uses the LLM itself to navigate and retrieve — purely LLM-guided, from indexing to querying.
----
+
## Why Vectorless
@@ -24,11 +24,11 @@ Most document retrieval solutions rely on vector similarity — splitting docume
Vectorless takes a different approach. No vectors at all. It builds a **semantic tree index** of each document — preserving the original hierarchy — and uses the LLM itself to navigate that structure. The LLM generates the tree during indexing and reasons through it during retrieval. Pure LLM guidance, end to end.
-
+
-
+