Metadata-Version: 2.4
Name: dataenginex
Version: 1.1.2
Summary: DataEngineX - Core framework for AI/ML/Data engineering projects
Author-email: Jay <jayapal.myaka99@gmail.com>
License: MIT License
        
        Copyright (c) 2026 Jay
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE.
License-File: LICENSE
Requires-Python: >=3.13
Requires-Dist: arq>=0.28.0
Requires-Dist: asyncpg>=0.31.0
Requires-Dist: click>=8.3.3
Requires-Dist: croniter>=6.2.2
Requires-Dist: duckdb>=1.5.2
Requires-Dist: httpx>=0.28.1
Requires-Dist: prometheus-client>=0.25.0
Requires-Dist: pyarrow>=23.0.1
Requires-Dist: pydantic>=2.13.4
Requires-Dist: python-dotenv>=1.2.2
Requires-Dist: pyyaml>=6.0.3
Requires-Dist: qdrant-client>=1.18.0
Requires-Dist: redis>=5.3.1
Requires-Dist: structlog>=25.5.0
Provides-Extra: cloud
Requires-Dist: boto3>=1.43.7; extra == 'cloud'
Requires-Dist: google-cloud-bigquery>=3.41.0; extra == 'cloud'
Requires-Dist: google-cloud-storage>=3.10.1; extra == 'cloud'
Provides-Extra: observability
Requires-Dist: langfuse>=4.5.1; extra == 'observability'
Description-Content-Type: text/markdown

# dataenginex

Unified Data + ML + AI **library**. Config-driven, self-hosted, production-ready.

`dataenginex` is a pure Python library — no HTTP server. Your application owns the server layer.

## Install

```bash
# Core (DuckDB, structlog, Pydantic, Click, arq, asyncpg, qdrant-client)
pip install dataenginex

# Optional extras
pip install "dataenginex[cloud]"          # S3 + GCS + BigQuery storage backends
pip install "dataenginex[observability]"  # Langfuse LLM call tracing
```

> **LiteLLM:** Install separately — it pins `python-dotenv==1.0.1` which conflicts
> with dataenginex's `python-dotenv>=1.2.2`.
> ```bash
> pip install 'litellm>=1.83.3' --no-deps
> ```

## Submodules

| Module | Description |
|--------|-------------|
| `dataenginex.engine` | `DexEngine` — single entry point; loads config, inits store, wires all backends |
| `dataenginex.store` | `DexStore` — DuckDB-backed persistence (`.dex/store.duckdb`) |
| `dataenginex.config` | `dex.yaml` schema, loader, env var resolution, layering |
| `dataenginex.core` | Exceptions, `Base*` ABCs, `BackendRegistry` |
| `dataenginex.cli` | `dex` CLI (`validate`, `version`, `init`) |
| `dataenginex.api` | HTTP helpers: error types, response models (no server bundled) |
| `dataenginex.data` | Connectors, pipeline runner, schema registry, profiler |
| `dataenginex.ml` | Classical ML: training, model registry, serving, drift detection |
| `dataenginex.ai` | LLM providers, agents, RAG, vectorstore, memory, observability |
| `dataenginex.orchestration` | `DriftScheduler`, background scheduling |
| `dataenginex.middleware` | structlog config, Prometheus metrics |
| `dataenginex.lakehouse` | Storage backends (local, S3, GCS), catalog, partitioning |
| `dataenginex.warehouse` | SQL transforms, lineage tracking |
| `dataenginex.plugins` | Entry-point plugin discovery |

## Quick Usage

```python
from pathlib import Path
from dataenginex.engine import DexEngine

# Load config and initialize all backends
engine = DexEngine(Path("dex.yaml"))

# Data
engine.run_pipeline("clean_users")
sources = list(engine.config.data.sources.keys())

# ML
models = engine.model_registry.list_models()
result = engine.model_registry.predict("churn_model", features)

# AI
response = engine.agents["assistant"].chat("summarize the latest run")

# Persistence (DuckDB)
runs = engine.store.list_pipeline_runs(limit=10)
```

```python
# Config system only
from dataenginex.config import load_config
cfg = load_config(Path("dex.yaml"))

# Core interfaces + registry
from dataenginex.core.interfaces import BaseConnector
from dataenginex.core.registry import BackendRegistry

# ML
from dataenginex.ml import ModelRegistry, SklearnTrainer

# AI
from dataenginex.ai.llm import get_llm_provider
from dataenginex.ai.vectorstore import VectorStoreBackend
```

## Source and Docs

- Repository: https://github.com/TheDataEngineX/DEX
- Documentation: https://docs.thedataenginex.org
- Release notes: `CHANGELOG.md`
