Metadata-Version: 2.4
Name: atlas-ragkit
Version: 1.1.14
Summary: Atlas RAGKit — Local-First RAG Engineering Platform
Author: Rishi Bhanushali
License: MIT
Keywords: rag,llm,ai,local,retrieval,augmented,generation,nlp
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastapi>=0.100.0
Requires-Dist: uvicorn>=0.22.0
Requires-Dist: python-multipart>=0.0.6
Requires-Dist: typer>=0.9.0
Requires-Dist: rich>=13.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: pymupdf>=1.23.0
Requires-Dist: python-docx>=1.1.0
Requires-Dist: beautifulsoup4>=4.12.0
Requires-Dist: gitpython>=3.1.0
Requires-Dist: sentence-transformers>=2.2.2
Requires-Dist: faiss-cpu>=1.7.4
Requires-Dist: chromadb>=0.4.0
Requires-Dist: rank-bm25>=0.2.2
Requires-Dist: groq>=0.9.0
Requires-Dist: tiktoken>=0.7.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: scikit-learn>=1.2.0
Requires-Dist: umap-learn>=0.5.3
Requires-Dist: markdown-it-py>=3.0.0
Dynamic: license-file

# ⚡ Atlas — Local-First RAG Engineering Platform

[![PyPI version](https://img.shields.io/pypi/v/atlas-ragkit)](https://pypi.org/project/atlas-ragkit/)
[![Python](https://img.shields.io/pypi/pyversions/atlas-ragkit)](https://pypi.org/project/atlas-ragkit/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)


Atlas is a **local-first, zero-cost** Retrieval-Augmented Generation (RAG) engineering platform with a full-featured visual web dashboard. Ingest documents, benchmark chunking strategies, visualize embeddings in 3D, run RAG queries, and evaluate pipeline quality — all from your browser with no cloud dependency.

---

## 🚀 Installation

```bash
pip install -U atlas-ragkit
```

## ▶️ Quick Start

1. Open a terminal and navigate to any directory.
2. Start the Atlas server:
   ```bash
   atlas server
   ```
3. Your browser will open automatically at **http://localhost:8000**.
4. In the **System Config** tab, click **"Provision Workspace"** to initialize your workspace with demo files and pipelines.

## 🏗️ Architecture

Atlas is structured as a clean monorepo with four modules:

| Module | Role |
|--------|------|
|  tlas_sdk | Plugin interfaces and reference implementations (chunkers, embedders, retrievers, LLMs) |
|  tlas_core | Domain models, execution engine, ingestion, and studio services |
|  tlas_server | FastAPI REST API + full-featured visual web dashboard (SPA) |
|  tlas_cli | Minimal CLI — boots the server, manages workspace scaffold |

## 🔑 Supported LLM Providers

Atlas supports **Groq, OpenAI, Anthropic, Google Gemini, Mistral, Together AI, HuggingFace, Ollama, LM Studio**, and local GGUF models. Configure your API keys through the Atlas web UI — no terminal required.

## 🗑️ Uninstall

**Mac / Linux:**
```bash
pip uninstall -y atlas-ragkit
rm -rf .atlas atlas.db
```

**Windows (PowerShell):**
```powershell
pip uninstall -y atlas-ragkit
Remove-Item -Recurse -Force .atlas, atlas.db -ErrorAction SilentlyContinue
```

**Windows (Command Prompt):**
```cmd
pip uninstall -y atlas-ragkit
rmdir /s /q .atlas & del /f /q atlas.db
```

---

> Built with ❤️ by Rishi Bhanushali
