Metadata-Version: 2.4
Name: darwin-rag
Version: 0.2.7
Summary: DARWIN — Local-first RAG engine with API + ONNX embedding support
Author-email: Brightdotdev <mail.bright.dev@gmail.com>
License-Expression: MIT
Project-URL: Homepage, https://github.com/Brightdotdev/DARWIN
Project-URL: Repository, https://github.com/Brightdotdev/DARWIN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Operating System :: OS Independent
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: litellm==1.83.14
Requires-Dist: onnxruntime>=1.17.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: polars>=1.41.0
Requires-Dist: pyarrow>=24.0.0
Requires-Dist: scikit-learn>=1.8.0
Requires-Dist: usearch>=2.25.1
Requires-Dist: markitdown>=0.1.5
Requires-Dist: pymupdf==1.27.2.2
Requires-Dist: pymupdf4llm==1.27.2.2
Requires-Dist: trafilatura>=2.0.0
Requires-Dist: openpyxl>=3.1.5
Requires-Dist: pyexcel-ods>=0.6.0
Requires-Dist: rich>=14.3.3
Requires-Dist: psutil>=7.2.2
Requires-Dist: jinja2>=3.1.6
Requires-Dist: tiktoken>=0.12.0
Requires-Dist: beautifulsoup4>=4.12.0
Requires-Dist: websockets>=16.0
Requires-Dist: filelock>=3.13.0
Requires-Dist: huggingface-hub>=0.20.0
Requires-Dist: gputil>=1.4.0
Requires-Dist: keyring>=25.7.0
Requires-Dist: httpx>=0.28.1
Requires-Dist: rapidocr-onnxruntime>=1.4.4
Requires-Dist: tokenizers>=0.22.2
Requires-Dist: pillow>=12.2.0
Requires-Dist: sentencepiece>=0.2.1
Requires-Dist: rapidocr>=3.8.4
Requires-Dist: pyvis>=0.3.2
Requires-Dist: nvidia-ml-py>=13.610.43
Requires-Dist: sse-starlette>=2.2.0
Requires-Dist: starlette>=1.3.0
Requires-Dist: uvicorn>=0.50.0
Requires-Dist: fastmcp>=3.4.2
Requires-Dist: click>=8.4.0
Provides-Extra: nlp
Requires-Dist: spacy>=3.8.14; extra == "nlp"
Requires-Dist: pytextrank>=3.3.0; extra == "nlp"
Requires-Dist: networkx>=3.4; extra == "nlp"
Dynamic: license-file

# Darwin RAG

Local-first RAG engine. Ingest documents, index them with BM25 and embeddings, and search via hybrid/semantic/keyword retrieval. Runs as an MCP server for AI agent integration or via CLI. All local, all offline-capable.

Built by [BrightDotDev](https://github.com/brightdotdev).

[![License: MIT with Attribution](https://img.shields.io/badge/License-MIT%20with%20Attribution-blue.svg)](LICENSE)

---

## Setup

Internet is required for first-time setup to download and validate models. After that, everything runs offline.

### Interactive (guided)

Detects your hardware, shows available models, lets you pick. Takes about 2 minutes.

```bash
pip install darwin-rag
darwin-admin setup interactive
```

### One-shot: required (embedding only)

Downloads and configures only the embedding model. No prompts, no choices. Fastest path to a working install.

```bash
darwin-admin setup --preset required
```

### One-shot: recommended (embedding + reranker + OCR)

Also downloads a reranker and OCR model. Better search quality out of the box.

```bash
darwin-admin setup --preset recommended
```

After setup, start the MCP server:

```bash
darwin mcp --http --port 8765
```

For a full setup walkthrough including Docker, from source, and API key configuration, see [docs/setup.md](docs/setup.md).

---

## Connecting your agent

```bash
# Generate config for Claude Desktop, Cursor, etc.
darwin config claude

# Generate config for all clients
darwin config all --copy
```

Or point any MCP client directly:
- **SSE:** `http://localhost:8765/sse`
- **HTTP:** `http://localhost:8765/mcp`

---

## Commands

**`darwin`** — user CLI (mcp, config)

**`darwin-admin`** — power-user CLI (setup, models, store, pipeline, search, logs, system, uninstall, status)

See [docs/admin.md](docs/admin.md) for the full command reference.

---

## Documentation

| Doc | What |
|---|---|
| [setup.md](docs/setup.md) | Full setup walkthrough |
| [architecture.md](docs/architecture.md) | For developers and contributors |
| [mcp.md](docs/mcp.md) | MCP server, tools, resources |
| [admin.md](docs/admin.md) | Admin CLI reference |
| [storage.md](docs/storage.md) | DarwinStore |
| [pipeline.md](docs/pipeline.md) | Ingestion & indexing |
| [retrieval.md](docs/retrieval.md) | Search engine |
| [models.md](docs/models.md) | Model registry & inference |
| [logger.md](docs/logger.md) | Structured logging |
| [orchestrators.md](docs/orchestrators.md) | High-level business logic |

---

## License

MIT with Attribution — see [LICENSE](LICENSE).

Core architecture and implementation by [BrightDotDev](https://github.com/brightdotdev).
