From ed3f04cb981d3f3c48137e03ed9d5d8baf149477 Mon Sep 17 00:00:00 2001
From: zTgx <747674262@qq.com>
Date: Sat, 11 Apr 2026 19:33:38 +0800
Subject: [PATCH 1/3] docs(README): update description and refine supported
formats
Update the main description to better highlight Vectorless's unique
approach without vector databases, embeddings, or similarity search.
Also refine the list of supported document formats to be more accurate
and add missing blank line in examples section.
---
README.md | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/README.md b/README.md
index 579b0a62..75683824 100644
--- a/README.md
+++ b/README.md
@@ -13,10 +13,7 @@
-**Vectorless** is an ultra-performant reasoning-native document intelligence engine for AI, with the core written in Rust. It transforms documents into rich semantic trees and uses LLMs to intelligently traverse the hierarchy — retrieving the most relevant content through structural reasoning and deep contextual understanding.
-
-
-
+**Vectorless** is a reasoning-native document intelligence engine written in Rust — **no vector database, no embeddings, no similarity search**. It transforms documents into hierarchical semantic trees and uses LLMs to navigate the structure, retrieving the most relevant content through reasoning instead of vector math.
## Quick Start
@@ -40,7 +37,7 @@ from vectorless import Engine, IndexContext
# Create engine with a workspace directory
engine = Engine(workspace="./data")
-# Index a document (PDF, Markdown, DOCX, HTML)
+# Index a document (PDF or Markdown)
result = engine.index(IndexContext.from_file("./report.pdf"))
doc_id = result.doc_id
@@ -84,6 +81,7 @@ async fn main() -> vectorless::Result<()> {
## Examples
+
See [examples](examples/) for more and stay tuned.
## Contributing
From 2e4cfe182d192d56db64949876f8e6c7ebdd5060 Mon Sep 17 00:00:00 2001
From: zTgx <747674262@qq.com>
Date: Sat, 11 Apr 2026 21:04:16 +0800
Subject: [PATCH 2/3] docs(README): update description with improved
terminology
Replace "reasoning" with "deep contextual understanding" to better
describe how Vectorless retrieves content through semantic analysis
rather than vector-based approaches.
---
README.md | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/README.md b/README.md
index 75683824..0bfc7e60 100644
--- a/README.md
+++ b/README.md
@@ -13,7 +13,8 @@
-**Vectorless** is a reasoning-native document intelligence engine written in Rust — **no vector database, no embeddings, no similarity search**. It transforms documents into hierarchical semantic trees and uses LLMs to navigate the structure, retrieving the most relevant content through reasoning instead of vector math.
+**Vectorless** is a reasoning-native document intelligence engine written in Rust — **no vector database, no embeddings, no similarity search**. It transforms documents into hierarchical semantic trees and uses LLMs to navigate the structure, retrieving the most relevant content through deep contextual understanding instead of vector math.
+
## Quick Start
From 51e3ff299668c47f3325867b0837353c10115233 Mon Sep 17 00:00:00 2001
From: zTgx <747674262@qq.com>
Date: Sat, 11 Apr 2026 21:05:45 +0800
Subject: [PATCH 3/3] refact: remove images
---
docs/design/logo-title.svg | 4 ---
docs/design/positioning.svg | 71 -------------------------------------
2 files changed, 75 deletions(-)
delete mode 100644 docs/design/logo-title.svg
delete mode 100644 docs/design/positioning.svg
diff --git a/docs/design/logo-title.svg b/docs/design/logo-title.svg
deleted file mode 100644
index aaf3fbd1..00000000
--- a/docs/design/logo-title.svg
+++ /dev/null
@@ -1,4 +0,0 @@
-
diff --git a/docs/design/positioning.svg b/docs/design/positioning.svg
deleted file mode 100644
index 8087fb27..00000000
--- a/docs/design/positioning.svg
+++ /dev/null
@@ -1,71 +0,0 @@
-
