feat: add Python bindings and convert to multi-language workspace

- Add Python bindings using PyO3 for the vectorless Rust library
- Convert monorepo structure from single Rust crate to multi-language workspace
- Add pyproject.toml, setup configuration for Python package distribution
- Include comprehensive Python documentation and examples in README
- Add basic integration tests for Python bindings covering core functionality
- Update .gitignore to include Python-specific files and directories
- Maintain existing Rust functionality while enabling cross-language usage

Author: zTgx

.gitignore

@@ -53,4 +53,32 @@ config.toml
 .vectorless.toml
 
 # Test fixtures
-test_workspace/
+test_workspace/
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.venv/
+venv/
+ENV/

Cargo.toml

@@ -1,125 +1,3 @@
-[package]
-name = "vectorless"
-version = "0.1.19"
-edition = "2024"
-authors = ["zTgx <beautifularea@gmail.com>"]
-description = "Hierarchical, reasoning-native document intelligence engine"
-license = "Apache-2.0"
-repository = "https://github.com/vectorlessflow/vectorless"
-homepage = "https://vectorless.dev"
-documentation = "https://docs.rs/vectorless"
-keywords = ["rag", "document", "retrieval", "indexing", "llm"]
-categories = ["text-processing", "data-structures", "algorithms"]
-readme = "README.md"
-exclude = ["samples/", "docs/", ".*"]
-
-[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 = { version = "1", optional = true }
-
-# 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 for fingerprints
-blake2 = "0.10"
-base64 = "0.22"
-
-# Synchronization primitives (for memo store)
-parking_lot = "0.12"
-
-# Compression
-flate2 = "1.0"
-
-# File locking (Unix)
-[target.'cfg(unix)'.dependencies]
-libc = "0.2"
-
-# PDF processing
-pdf-extract = "0.10.0"
-lopdf = "0.34"
-
-# DOCX processing
-zip = "2.2"
-roxmltree = "0.20"
-
-# Random number generation (for sampling)
-rand = "0.8"
-
-# BM25 scoring
-bm25 = { version = "2.3.2", features = ["parallelism"] }
-
-# HTML parsing
-scraper = "0.22"
-
-[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"
+[workspace]
+members = ["rust", "python"]
+resolver = "2"

README.md

@@ -3,6 +3,7 @@
 ![Vectorless](docs/design/logo-horizontal.svg)
 
 [![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)
 [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
@@ -90,7 +91,30 @@ Source: Chapter 4 > Section 4.2 > Reset Procedure
 
 ## Quick Start
 
-### Installation
+### Python
+
+```bash
+pip install vectorless
+```
+
+```python
+from vectorless import Engine, IndexContext
+
+# Create engine (uses OPENAI_API_KEY env var)
+engine = Engine(workspace="./data")
+
+# Index a document
+ctx = IndexContext.from_file("./report.pdf")
+doc_id = engine.index(ctx)
+
+# Query
+result = engine.query(doc_id, "What is the total revenue?")
+print(f"Answer: {result.content}")
+```
+
+See [python/README.md](python/README.md) for full Python documentation.
+
+### Rust
 
 ```toml
 [dependencies]