diff --git a/Cargo.toml b/Cargo.toml
index 9da12c6c..cfa82590 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -3,7 +3,7 @@ members = ["rust", "python"]
 resolver = "2"
 
 [workspace.package]
-version = "0.1.19"
+version = "0.1.20"
 edition = "2024"
 authors = ["zTgx <beautifularea@gmail.com>"]
 license = "Apache-2.0"
diff --git a/README.md b/README.md
index e96095ad..3365eb7d 100644
--- a/README.md
+++ b/README.md
@@ -17,11 +17,7 @@
 
 **Vectorless** is a library for querying structured documents using natural language — without vector databases or embedding models. Core engine written in Rust, with Python bindings.
 
-Instead of chunking documents into vectors, Vectorless preserves the document's tree structure and uses a **hybrid algorithm + LLM approach** to navigate it — like how a human reads a table of contents:
-
-- **Pilot (LLM)** handles "where to go"
-- **Algorithm** handles "how to walk"
-
+Instead of chunking documents into vectors, Vectorless preserves the document's tree structure and uses LLM to navigate it — like how a human reads a table of contents.
 
 ## How It Works
 
@@ -45,9 +41,9 @@ Each node gets an AI-generated summary, enabling fast navigation.
 When you ask "How do I reset the device?":
 
 1. **Analyze** — Understand query intent and complexity
-2. **Navigate** — LLM guides tree traversal (like reading a TOC)
+2. **Navigate** — LLM guides tree traversal
 3. **Retrieve** — Return the exact section with context
-4. **Verify** — Check if more information is needed (backtracking)
+4. **Verify** — Check if more information is needed
 
 ## Traditional RAG vs Vectorless
 
diff --git a/pyproject.toml b/pyproject.toml
index 3a77c43c..bee82a1f 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "vectorless"
-version = "0.1.0"
+version = "0.1.1"
 description = "Hierarchical document intelligence without vectors"
 readme = "README.md"
 requires-python = ">=3.9"