vectorlessflow · zTgx · Apr 16, 2026 · Apr 16, 2026 · Apr 16, 2026 · Apr 16, 2026
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1,21 @@
+## Summary
+
+<!-- Brief description of what this PR does -->
+
+## Changes
+
+<!-- List the key changes -->
+
+-
+
+## Checklist
+
+- [ ] Code compiles (`cargo build`)
+- [ ] Tests pass (`cargo test --lib --all-features`)
+- [ ] No new clippy warnings (`cargo clippy --all-features`)
+- [ ] Public APIs have documentation comments
+- [ ] Python bindings updated (if Rust API changed)
+
+## Notes
+
+<!-- Anything reviewers should know? Breaking changes, migration notes, etc. -->
diff --git a/Cargo.toml b/Cargo.toml
@@ -3,7 +3,7 @@ members = ["rust", "python"]
 resolver = "2"
 
 [workspace.package]
-version = "0.1.28"
+version = "0.1.29"
 edition = "2024"
 authors = ["zTgx <beautifularea@gmail.com>"]
 license = "Apache-2.0"

diff --git a/README.md b/README.md
@@ -13,15 +13,11 @@
 
 </div>
 
-**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.
+**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 will reason through any of your structured documents — **PDFs, Markdown, reports, contracts** — and retrieve only what's relevant. Nothing more, nothing less.
 
 
 
-## Why Vectorless
-
-Most document retrieval solutions rely on vector similarity — splitting documents into chunks, embedding them, and searching by cosine distance. This works for rough topic matching, but breaks down when you need **precision**: specific numbers, cross-section references, or multi-step reasoning across a document.
-
-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.
+## How It Works
 
 <div align="center">
   <img src="https://vectorless.dev/img/workflow.svg" alt="Vectorless Workflow" width="900">
@@ -48,6 +44,7 @@ async fn main() -> vectorless::Result<()> {
     let engine = EngineBuilder::new()
         .with_key("sk-...")
         .with_model("gpt-4o")
+        .with_endpoint("https://api.openai.com/v1")
         .build()
         .await?;
 
@@ -77,7 +74,7 @@ import asyncio
 from vectorless import Engine, IndexContext, QueryContext
 
 async def main():
-    engine = Engine(api_key="sk-...", model="gpt-4o")
+    engine = Engine(api_key="sk-...", model="gpt-4o", endpoint="https://api.openai.com/v1")
 
     # Index a document
     result = await engine.index(IndexContext.from_path("./report.pdf"))
@@ -130,7 +127,7 @@ result = await engine.query(
 Indexed documents are stored in a workspace — there's no need to reprocess files between sessions:
 
 ```python
-engine = Engine(api_key="sk-...", model="gpt-4o")
+engine = Engine(api_key="sk-...", model="gpt-4o", endpoint="https://api.openai.com/v1")
 
 # List all indexed documents
 docs = await engine.list()

diff --git a/docs/docs/api-reference.mdx b/docs/docs/api-reference.mdx
@@ -0,0 +1,17 @@
+---
+sidebar_position: 9
+title: API Reference
+description: Complete API reference for Vectorless Rust crate and Python SDK.
+---
+
+# API Reference
+
+> This page is a work in progress. The full API reference will be published in a future update.
+
+In the meantime, you can refer to the following resources:
+
+- **Rust crate docs**: [docs.rs/vectorless](https://docs.rs/vectorless) — auto-generated documentation from source code
+- **Python SDK docs**: Available via `help(vectorless)` in an interactive Python session
+- **Source code**: [github.com/vectorlessflow/vectorless](https://github.com/vectorlessflow/vectorless)
+
+For usage examples, see [Quick Query](/docs/examples/quick-query), [Multi-Document](/docs/examples/multi-document), and [Batch Indexing](/docs/examples/batch-indexing).
diff --git a/docs/docusaurus.config.ts b/docs/docusaurus.config.ts
@@ -111,7 +111,7 @@ const config: Config = {
             },
             {
               label: 'API Reference',
-              href: 'https://docs.rs/vectorless',
+              to: '/docs/api-reference',
             },
           ],
         },
@@ -133,7 +133,7 @@ const config: Config = {
           ],
         },
       ],
-      copyright: `Copyright © ${new Date().getFullYear()} Vectorless`,
+      copyright: `Copyright \u00A9 ${new Date().getFullYear()} Vectorless`,
     },
     prism: {
       theme: prismThemes.github,

diff --git a/docs/sidebars.ts b/docs/sidebars.ts
@@ -42,6 +42,7 @@ const sidebars: SidebarsConfig = {
         'sdk/rust',
       ],
     },
+    'api-reference',
     {
       type: 'category',
       label: 'Examples',

diff --git a/docs/src/components/GitHubStar/index.tsx b/docs/src/components/GitHubStar/index.tsx
@@ -1,5 +1,5 @@
 import React, { useState, useEffect } from 'react';
-import { FaGithub, FaStar } from 'react-icons/fa';
+import { FaGithub } from 'react-icons/fa';
 import styles from './styles.module.css';
 
 function formatStars(count: number | null): string {
@@ -40,16 +40,16 @@ export default function GitHubStar(): React.ReactElement {
         rel="noopener noreferrer"
         className={styles.githubStarButton}
       >
-        <FaGithub size={14} />
+        <FaGithub size={16} />
         <span className={styles.githubStarText}>Star</span>
       </a>
       {loading ? (
         <div className={styles.githubStarCount}>
-          <span className={styles.spinner}>...</span>
+          <span className={styles.spinner}>&hellip;</span>
         </div>
       ) : (
         <a
-          href="https://github.com/vectorlessflow/vectorless/stargazers"
+          href="https://github.com/vectorlessflow/vectorless"
           target="_blank"
           rel="noopener noreferrer"
           className={styles.githubStarCount}

diff --git a/docs/src/components/GitHubStar/styles.module.css b/docs/src/components/GitHubStar/styles.module.css
@@ -15,7 +15,7 @@
   border-radius: 3px;
   text-decoration: none;
   font-size: 12px;
-  font-weight: 700;
+  font-weight: 600;
   line-height: 24px;
   transition: background-color 0.2s;
 }
@@ -46,7 +46,7 @@
   margin-left: 5px;
   padding: 0 5px;
   font-size: 12px;
-  font-weight: 700;
+  font-weight: 600;
   line-height: 24px;
   border: 1px solid #d5d5d5;
   border-radius: 3px;

diff --git a/docs/src/css/custom.css b/docs/src/css/custom.css
@@ -6,18 +6,26 @@
 
 :root {
   --primary: #AF788B;
-  --primary-dark: #96637A;
+  --primary-dark: #8B5E6F;
+  --primary-deeper: #6E4556;
   --primary-light: #C9A0AE;
+  --primary-soft: rgba(175, 120, 139, 0.12);
   --text: #1e293b;
-  --text-light: #64748b;
+  --text-light: #5a4a52;
   --bg: #ffffff;
-  --bg-secondary: #fdf8f9;
-  --border: #e8dde1;
+  --bg-secondary: #F5EBEE;
+  --bg-offset: #F6F8FA;
+  --card-bg: #FAF5F7;
+  --border: #E2E8F0;
+  --code-bg: #0F172A;
+  --code-text: #E2E8F0;
+  --code-comment: #6272A4;
+  --code-keyword: #FF79C6;
 
   --ifm-color-primary: #AF788B;
-  --ifm-color-primary-dark: #96637A;
-  --ifm-color-primary-darker: #8d5a6f;
-  --ifm-color-primary-darkest: #6e4556;
+  --ifm-color-primary-dark: #8B5E6F;
+  --ifm-color-primary-darker: #7a5062;
+  --ifm-color-primary-darkest: #6E4556;
   --ifm-color-primary-light: #C9A0AE;
   --ifm-color-primary-lighter: #d3b0bb;
   --ifm-color-primary-lightest: #e8d0d8;
@@ -26,6 +34,19 @@
 }
 
 [data-theme='dark'] {
+  --text: #EEF2FF;
+  --text-light: #8B9AB0;
+  --bg: #0A0C10;
+  --bg-secondary: #11151A;
+  --bg-offset: #11151A;
+  --card-bg: #11151A;
+  --border: #1E293B;
+  --primary-soft: rgba(201, 160, 174, 0.15);
+  --code-bg: #010409;
+  --code-text: #E2E8F0;
+  --code-comment: #6272A4;
+  --code-keyword: #FF79C6;
+
   --ifm-color-primary: #C9A0AE;
   --ifm-color-primary-dark: #b88d9d;
   --ifm-color-primary-darker: #af7f91;
@@ -36,57 +57,104 @@
   --docusaurus-highlighted-code-line-bg: rgba(175, 120, 139, 0.2);
 }
 
-/* Navbar: no border, no shadow, match homepage bg */
+/* ===== Navbar ===== */
 .navbar {
-  background-color: #fdf8f9 !important;
+  background-color: var(--bg) !important;
   border-bottom: none !important;
   box-shadow: none !important;
+  height: 68px !important;
+  padding: 0 1.5rem !important;
+}
+
+.navbar__inner {
+  height: 68px !important;
+  max-width: 1200px;
+  margin: 0 auto;
+}
+
+.navbar__brand {
+  height: 68px !important;
+}
+
+.navbar__title {
+  font-size: 1.4rem !important;
+  font-weight: 700 !important;
+  color: var(--text) !important;
+  letter-spacing: -0.01em;
+}
+
+.navbar__logo {
+  height: 36px;
+  margin-right: 0.6rem;
+}
+
+.navbar__link {
+  font-size: 0.95rem !important;
+  font-weight: 500 !important;
+  color: var(--text-light) !important;
+  transition: color 0.15s !important;
+}
+
+.navbar__link:hover {
+  color: var(--primary-dark) !important;
+}
+
+.navbar__link--active {
+  color: var(--primary-dark) !important;
 }
 
 [data-theme='dark'] .navbar {
-  background-color: var(--ifm-background-color) !important;
+  background-color: var(--bg) !important;
+  border-bottom: none !important;
+}
+
+[data-theme='dark'] .navbar__title {
+  color: var(--text) !important;
+}
+
+[data-theme='dark'] .navbar__link {
+  color: var(--text-light) !important;
+}
+
+[data-theme='dark'] .navbar__link:hover {
+  color: var(--primary-light) !important;
+}
+
+[data-theme='dark'] .navbar__link--active {
+  color: var(--primary-light) !important;
 }
 
 /* ===== Footer ===== */
 .footer {
   background-color: transparent !important;
-  padding: 3rem 1.5rem 2rem;
+  padding: 5rem 1.5rem 1.5rem;
 }
 
-/* Column titles */
 .footer__title {
-  font-size: 0.8rem;
+  font-size: 0.85rem;
   font-weight: 700;
   text-transform: uppercase;
   letter-spacing: 0.08em;
   color: var(--text);
-  margin-bottom: 0.75rem;
+  margin-bottom: 1rem;
 }
 
-/* Link items */
 .footer__link-item {
-  font-size: 0.88rem;
+  font-size: 0.92rem;
   color: var(--text-light);
-  line-height: 1.8;
+  line-height: 2;
   transition: color 0.15s;
 }
 
 .footer__link-item:hover {
   color: var(--primary);
 }
 
-/* Hide external-link icons */
 .footer__link-item svg {
   display: none;
 }
 
-/* Copyright */
 .footer__copyright {
-  text-align: center;
-  font-size: 0.8rem;
+  font-size: 0.88rem;
   color: var(--text-light);
-  letter-spacing: 0.03em;
-  margin-top: 2rem;
-  padding-top: 1.5rem;
-  border-top: 1px solid var(--border);
 }