chore(workspace): migrate to workspace-managed dependencies and configuration

- Move common package metadata to workspace level in Cargo.toml
- Replace individual dependency versions with workspace references
- Add comprehensive workspace dependencies section for shared crates
- Configure workspace lints for rust and clippy
- Set up release and development profiles at workspace level
- Update python and rust Cargo.toml files to use workspace inheritance
- Consolidate all dependency management to central workspace configuration

Author: zTgx

Cargo.toml

@@ -1,3 +1,126 @@
 [workspace]
 members = ["rust", "python"]
 resolver = "2"
+
+[workspace.package]
+version = "0.1.19"
+edition = "2024"
+authors = ["zTgx <beautifularea@gmail.com>"]
+license = "Apache-2.0"
+repository = "https://github.com/vectorlessflow/vectorless"
+homepage = "https://vectorless.dev"
+documentation = "https://docs.rs/vectorless"
+
+[workspace.dependencies]
+# Async runtime
+tokio = { version = "1", features = ["full"] }
+async-trait = "0.1"
+futures = "0.3"
+
+# Serialization
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1.0"
+toml = "0.8"
+
+# Error handling
+thiserror = "2"
+anyhow = "1"
+
+# OpenAI-compatible API client
+async-openai = { version = "0.34", features = ["chat-completion"] }
+
+# UUID
+uuid = { version = "1.10", features = ["v4", "serde"] }
+
+# Time
+chrono = { version = "0.4", default-features = false, features = ["serde", "clock"] }
+
+# Logging
+tracing = "0.1"
+
+# Rate limiting
+governor = "0.6"
+nonzero_ext = "0.3"
+
+# Token counting
+tiktoken-rs = "0.9"
+
+# Text processing
+regex = "1.10"
+
+# Markdown parsing
+pulldown-cmark = { version = "0.12", default-features = false, features = ["simd"] }
+
+# Tree data structure
+indextree = { version = "4.8.0", features = ["deser"] }
+
+# LRU cache
+lru = "0.12"
+
+# Checksum
+sha2 = "0.10"
+
+# BLAKE2b hashing
+blake2 = "0.10"
+base64 = "0.22"
+
+# Synchronization primitives
+parking_lot = "0.12"
+
+# Compression
+flate2 = "1.0"
+
+# File locking (Unix)
+libc = "0.2"
+
+# PDF processing
+pdf-extract = "0.10.0"
+lopdf = "0.34"
+
+# DOCX processing
+zip = "2.2"
+roxmltree = "0.20"
+
+# Random number generation
+rand = "0.8"
+
+# BM25 scoring
+bm25 = { version = "2.3.2", features = ["parallelism"] }
+
+# HTML parsing
+scraper = "0.22"
+
+# Python bindings
+pyo3 = { version = "0.22", features = ["extension-module"] }
+
+# Dev dependencies
+tempfile = "3.10"
+tokio-test = "0.4"
+tracing-subscriber = { version = "0.3", features = ["env-filter"] }
+
+[workspace.lints.rust]
+missing_docs = "warn"
+unsafe_code = "warn"
+
+[workspace.lints.clippy]
+all = "warn"
+pedantic = "warn"
+
+# Profile settings (must be at root level, not under workspace)
+[profile.release]
+opt-level = 3
+lto = "thin"
+codegen-units = 1
+strip = true
+panic = "abort"
+
+[profile.dev]
+opt-level = 0
+debug = true
+
+[profile.bench]
+inherits = "release"
+debug = true
+
+[profile.release.package."*"]
+opt-level = 3

README.md

@@ -1,11 +1,11 @@
 <div align="center">
 
-![Vectorless](docs/design/logo-horizontal.svg)
+<img src="https://raw.githubusercontent.com/vectorlessflow/vectorless/main/docs/design/logo-horizontal.svg" alt="Vectorless" width="400">
 
-[![Crates.io](https://img.shields.io/crates/v/vectorless.svg)](https://crates.io/crates/vectorless)
 [![PyPI](https://img.shields.io/pypi/v/vectorless.svg)](https://pypi.org/project/vectorless/)
-[![Downloads](https://img.shields.io/crates/d/vectorless.svg)](https://crates.io/crates/vectorless)
-[![Documentation](https://docs.rs/vectorless/badge.svg)](https://docs.rs/vectorless)
+[![Python](https://img.shields.io/pypi/pyversions/vectorless.svg)](https://pypi.org/project/vectorless/)
+[![Crates.io](https://img.shields.io/crates/v/vectorless.svg)](https://crates.io/crates/vectorless)
+[![Docs](https://docs.rs/vectorless/badge.svg)](https://docs.rs/vectorless)
 [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
 [![Rust](https://img.shields.io/badge/rust-1.85%2B-orange.svg)](https://www.rust-lang.org/)
 
@@ -23,7 +23,7 @@ Instead of chunking documents into vectors, Vectorless preserves the document's
 
 ## How It Works
 
-![How it works](docs/design/how-it-works.svg)
+<img src="https://raw.githubusercontent.com/vectorlessflow/vectorless/main/docs/design/how-it-works.svg" alt="How it works" width="600">
 
 ### 1. Index: Build a Navigable Tree
 
@@ -49,7 +49,7 @@ When you ask "How do I reset the device?":
 
 ## Traditional RAG vs Vectorless
 
-![Traditional RAG vs Vectorless](docs/design/comparison.svg)
+<img src="https://raw.githubusercontent.com/vectorlessflow/vectorless/main/docs/design/comparison.svg" alt="Traditional RAG vs Vectorless" width="600">
 
 | Aspect | Traditional RAG | Vectorless |
 |--------|----------------|------------|
@@ -164,7 +164,7 @@ async fn main() -> vectorless::Result<()> {
 
 ## Architecture
 
-![Architecture](docs/design/architecture.svg)
+<img src="https://raw.githubusercontent.com/vectorlessflow/vectorless/main/docs/design/architecture.svg" alt="Architecture" width="600">
 
 ### Core Components
 

python/Cargo.toml

@@ -1,16 +1,17 @@
 [package]
 name = "vectorless-py"
 version = "0.1.0"
-edition = "2024"
-authors = ["zTgx <beautifularea@gmail.com>"]
+edition.workspace = true
+authors.workspace = true
 description = "Python bindings for vectorless"
-license = "Apache-2.0"
+license.workspace = true
+repository.workspace = true
 
 [lib]
 name = "vectorless"
 crate-type = ["cdylib"]
 
 [dependencies]
-pyo3 = { version = "0.22", features = ["extension-module"] }
+pyo3 = { workspace = true }
 tokio = { version = "1", features = ["rt-multi-thread"] }
 vectorless = { path = "../rust" }

rust/Cargo.toml

@@ -1,12 +1,12 @@
 [package]
 name = "vectorless"
-version = "0.1.19"
-edition = "2024"
-authors = ["zTgx <beautifularea@gmail.com>"]
+version.workspace = true
+edition.workspace = true
+authors.workspace = true
 description = "Hierarchical, reasoning-native document intelligence engine"
-license = "Apache-2.0"
-repository = "https://github.com/vectorlessflow/vectorless"
-homepage = "https://vectorless.dev"
+license.workspace = true
+repository.workspace = true
+homepage.workspace = true
 documentation = "https://docs.rs/vectorless"
 keywords = ["rag", "document", "retrieval", "indexing", "llm"]
 categories = ["text-processing", "data-structures", "algorithms"]
@@ -15,111 +15,88 @@ exclude = ["samples/", "docs/", ".*"]
 
 [dependencies]
 # Async runtime
-tokio = { version = "1", features = ["full"] }
-async-trait = "0.1"
-futures = "0.3"
+tokio = { workspace = true }
+async-trait = { workspace = true }
+futures = { workspace = true }
 
 # Serialization
-serde = { version = "1.0", features = ["derive"] }
-serde_json = "1.0"
-toml = "0.8"
+serde = { workspace = true }
+serde_json = { workspace = true }
+toml = { workspace = true }
 
 # Error handling
-thiserror = "2"
-anyhow = { version = "1", optional = true }
+thiserror = { workspace = true }
+anyhow = { workspace = true, optional = true }
 
 # OpenAI-compatible API client
-async-openai = { version = "0.34", features = ["chat-completion"] }
+async-openai = { workspace = true }
 
 # UUID
-uuid = { version = "1.10", features = ["v4", "serde"] }
+uuid = { workspace = true }
 
 # Time
-chrono = { version = "0.4", default-features = false, features = ["serde", "clock"] }
+chrono = { workspace = true }
 
 # Logging
-tracing = "0.1"
+tracing = { workspace = true }
 
 # Rate limiting
-governor = "0.6"
-nonzero_ext = "0.3"
+governor = { workspace = true }
+nonzero_ext = { workspace = true }
 
 # Token counting
-tiktoken-rs = "0.9"
+tiktoken-rs = { workspace = true }
 
 # Text processing
-regex = "1.10"
+regex = { workspace = true }
 
 # Markdown parsing
-pulldown-cmark = { version = "0.12", default-features = false, features = ["simd"] }
+pulldown-cmark = { workspace = true }
 
 # Tree data structure
-indextree = { version = "4.8.0", features = ["deser"] }
+indextree = { workspace = true }
 
 # LRU cache
-lru = "0.12"
+lru = { workspace = true }
 
 # Checksum
-sha2 = "0.10"
+sha2 = { workspace = true }
 
-# BLAKE2b hashing for fingerprints
-blake2 = "0.10"
-base64 = "0.22"
+# BLAKE2b hashing
+blake2 = { workspace = true }
+base64 = { workspace = true }
 
-# Synchronization primitives (for memo store)
-parking_lot = "0.12"
+# Synchronization primitives
+parking_lot = { workspace = true }
 
 # Compression
-flate2 = "1.0"
+flate2 = { workspace = true }
 
 # File locking (Unix)
 [target.'cfg(unix)'.dependencies]
-libc = "0.2"
+libc = { workspace = true }
 
 # PDF processing
-pdf-extract = "0.10.0"
-lopdf = "0.34"
+pdf-extract = { workspace = true }
+lopdf = { workspace = true }
 
 # DOCX processing
-zip = "2.2"
-roxmltree = "0.20"
+zip = { workspace = true }
+roxmltree = { workspace = true }
 
-# Random number generation (for sampling)
-rand = "0.8"
+# Random number generation
+rand = { workspace = true }
 
 # BM25 scoring
-bm25 = { version = "2.3.2", features = ["parallelism"] }
+bm25 = { workspace = true }
 
 # HTML parsing
-scraper = "0.22"
+scraper = { workspace = true }
 
 [dev-dependencies]
-tempfile = "3.10"
-tokio-test = "0.4"
-tracing-subscriber = { version = "0.3", features = ["env-filter"] }
-
-[profile.release]
-opt-level = 3
-lto = "thin"
-codegen-units = 1
-strip = true
-panic = "abort"
-
-[profile.dev]
-opt-level = 0
-debug = true
-
-[profile.bench]
-inherits = "release"
-debug = true
-
-[profile.release.package."*"]
-opt-level = 3
-
-[lints.rust]
-missing_docs = "warn"
-unsafe_code = "warn"
-
-[lints.clippy]
-all = "warn"
-pedantic = "warn"
+tempfile = { workspace = true }
+tokio-test = { workspace = true }
+tracing-subscriber = { workspace = true }
+
+[lints]
+workspace = true