Merge pull request #46 from vectorlessflow/dev

Dev

Author: zTgx

.gitignore

@@ -35,8 +35,10 @@ workspace/
 test_output/
 temp/
 
-# Documentation
-docs/_build/
+# Documentation (Docusaurus)
+docs/node_modules/
+docs/build/
+docs/.docusaurus/
 
 # Benchmarks
 .criterion/

Cargo.toml

@@ -84,7 +84,8 @@ rand = "0.8"
 bm25 = { version = "2.3.2", features = ["parallelism"] }
 
 # Python bindings
-pyo3 = { version = "0.22", features = ["extension-module"] }
+pyo3 = { version = "0.28", features = ["extension-module"] }
+pyo3-async-runtimes = { version = "0.28", features = ["tokio-runtime"] }
 
 # Dev dependencies
 tempfile = "3.10"

README.md

@@ -1,6 +1,6 @@
 <div align="center">
 
-<img src="https://raw.githubusercontent.com/vectorlessflow/vectorless/main/docs/design/with-title.png" alt="Vectorless" width="400" style="vertical-align:middle;">
+<img src="https://vectorless.dev/img/with-title.png" alt="Vectorless" width="400" style="vertical-align:middle;">
 
 <h1>Reasoning-native Document Intelligence Engine</h1>
 
@@ -27,23 +27,26 @@ pip install vectorless
 ### Index and Query
 
 ```python
+import asyncio
 from vectorless import Engine, IndexContext
 
-# Create engine — api_key and model are required
-engine = Engine(
-    workspace="./data",
-    api_key="sk-...",
-    model="gpt-4o",
-)
-
-# Index a document (PDF or Markdown)
-result = engine.index(IndexContext.from_file("./report.pdf"))
-doc_id = result.doc_id
-
-# Query
-result = engine.query(doc_id, "What is the total revenue?")
-print(result.content)
-print(f"Score: {result.score}")
+async def main():
+    # Create engine — api_key and model are required
+    engine = Engine(
+        workspace="./data",
+        api_key="sk-...",
+        model="gpt-4o",
+    )
+
+    # Index a document (PDF or Markdown)
+    result = await engine.index(IndexContext.from_file("./report.pdf"))
+    doc_id = result.doc_id
+
+    # Query
+    result = await engine.query(doc_id, "What is the total revenue?")
+    print(result.single().content)
+
+asyncio.run(main())
 ```
 
 <details>

docs/.gitignore

@@ -0,0 +1,20 @@
+# Dependencies
+/node_modules
+
+# Production
+/build
+
+# Generated files
+.docusaurus
+.cache-loader
+
+# Misc
+.DS_Store
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*

docs/README.md

@@ -0,0 +1,41 @@
+# Website
+
+This website is built using [Docusaurus](https://docusaurus.io/), a modern static website generator.
+
+## Installation
+
+```bash
+yarn
+```
+
+## Local Development
+
+```bash
+yarn start
+```
+
+This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
+
+## Build
+
+```bash
+yarn build
+```
+
+This command generates static content into the `build` directory and can be served using any static contents hosting service.
+
+## Deployment
+
+Using SSH:
+
+```bash
+USE_SSH=true yarn deploy
+```
+
+Not using SSH:
+
+```bash
+GIT_USER=<Your GitHub username> yarn deploy
+```
+
+If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.

docs/blog/2026-04-12-welcome/index.mdx

@@ -0,0 +1,84 @@
+---
+slug: welcome
+title: Welcome to Vectorless
+authors: [zTgx]
+tags: [vectorless, rag, llm, announcement]
+---
+
+Vectorless is a reasoning-native document intelligence engine written in Rust — **no vector database, no embeddings, no similarity search**.
+
+{/* truncate */}
+
+## Why Vectorless?
+
+Traditional RAG systems rely on vector embeddings and similarity search. This approach loses document structure, requires a vector database, and often returns chunks that lack context.
+
+Vectorless takes a different path:
+
+- **Hierarchical Semantic Trees** — Documents are parsed into a tree of sections, preserving structure and relationships.
+- **LLM Navigation** — Queries are resolved by intelligently traversing the tree, not by comparing vectors.
+- **Zero Infrastructure** — No vector DB, no embedding models, no similarity search. Just an LLM API key.
+
+## Quick Start
+
+### Python
+
+```python
+import asyncio
+from vectorless import Engine, IndexContext
+
+async def main():
+    engine = Engine(
+        workspace="./data",
+        api_key="sk-...",
+        model="gpt-4o",
+    )
+
+    # Index a document
+    result = await engine.index(IndexContext.from_file("./report.pdf"))
+    doc_id = result.doc_id
+
+    # Query
+    answer = await engine.query(doc_id, "What is the total revenue?")
+    print(answer.single().content)
+
+asyncio.run(main())
+```
+
+### Rust
+
+```rust
+use vectorless::{EngineBuilder, IndexContext, QueryContext};
+
+#[tokio::main]
+async fn main() -> vectorless::Result<()> {
+    let engine = EngineBuilder::new()
+        .with_workspace("./data")
+        .with_key("sk-...")
+        .with_model("gpt-4o")
+        .build()
+        .await?;
+
+    let result = engine.index(IndexContext::from_path("./report.pdf")).await?;
+    let doc_id = result.doc_id().unwrap();
+
+    let result = engine.query(
+        QueryContext::new("What is the total revenue?").with_doc_id(doc_id)
+    ).await?;
+    println!("{}", result.content);
+
+    Ok(())
+}
+```
+
+## What's Next?
+
+- Cross-document relationship graph
+- Incremental indexing with content fingerprinting
+- Multi-format support (Markdown, PDF, DOCX)
+
+The project is open source under Apache-2.0. Contributions welcome!
+
+- [GitHub](https://github.com/vectorlessflow/vectorless)
+- [PyPI](https://pypi.org/project/vectorless/)
+- [crates.io](https://crates.io/crates/vectorless)

docs/blog/authors.yml

@@ -0,0 +1,8 @@
+zTgx:
+  name: zTgx
+  title: Rust Developer
+  url: https://beautifularea.com
+  page: true
+  socials:
+    x: pendingcode
+    github: zTgx

docs/blog/tags.yml

@@ -0,0 +1,4 @@
+hello:
+  label: Hello
+  permalink: /hello
+  description: Hello tag description

docs/docs/intro.mdx

@@ -0,0 +1,84 @@
+---
+sidebar_position: 1
+---
+
+# Introduction
+
+**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.
+
+## How It Works
+
+1. **Parse** — Documents (Markdown, PDF) are parsed into hierarchical semantic trees, preserving structure and relationships between sections.
+2. **Index** — Trees are stored with metadata, keywords, and optional summaries. Incremental indexing skips unchanged files via content fingerprinting.
+3. **Query** — An LLM navigates the tree to find the most relevant sections. No embeddings, no similarity search — just structural reasoning.
+
+## Quick Start
+
+### Python
+
+```bash
+pip install vectorless
+```
+
+```python
+import asyncio
+from vectorless import Engine, IndexContext
+
+async def main():
+    engine = Engine(
+        workspace="./data",
+        api_key="sk-...",
+        model="gpt-4o",
+    )
+
+    result = await engine.index(IndexContext.from_file("./report.pdf"))
+    doc_id = result.doc_id
+
+    answer = await engine.query(doc_id, "What is the total revenue?")
+    print(answer.single().content)
+
+asyncio.run(main())
+```
+
+### Rust
+
+```toml
+[dependencies]
+vectorless = "0.1"
+tokio = { version = "1", features = ["full"] }
+```
+
+```rust
+use vectorless::{EngineBuilder, IndexContext, QueryContext};
+
+#[tokio::main]
+async fn main() -> vectorless::Result<()> {
+    let engine = EngineBuilder::new()
+        .with_workspace("./data")
+        .with_key("sk-...")
+        .with_model("gpt-4o")
+        .build()
+        .await?;
+
+    let result = engine.index(IndexContext::from_path("./report.pdf")).await?;
+    let doc_id = result.doc_id().unwrap();
+
+    let result = engine.query(
+        QueryContext::new("What is the total revenue?").with_doc_id(doc_id)
+    ).await?;
+    println!("{}", result.content);
+
+    Ok(())
+}
+```
+
+## Features
+
+- **Hierarchical Semantic Trees** — Preserves document structure, not flat chunks
+- **LLM-Powered Retrieval** — Structural reasoning over the tree, not vector similarity
+- **Incremental Indexing** — Content fingerprinting skips unchanged files
+- **Cross-Document Graph** — Automatic relationship discovery between documents
+- **Multi-Format** — Markdown and PDF support
+- **Zero Infrastructure** — No vector DB, no embedding models, just an LLM API key