Metadata-Version: 2.4
Name: AutoRAG-Research
Version: 0.0.1
Summary: Automate your RAG research.
Project-URL: Homepage, https://vkehfdl1.github.io/AutoRAG-Research/
Project-URL: Repository, https://github.com/vkehfdl1/AutoRAG-Research
Project-URL: Documentation, https://vkehfdl1.github.io/AutoRAG-Research/
Author-email: NomaDamas <vkehfdl1@gmail.com>
License: Apache-2.0
License-File: LICENSE
Keywords: python
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: <4.0,>=3.10
Requires-Dist: beir>=2.2.0
Requires-Dist: bert-score>=0.3.13
Requires-Dist: datasets<3.0.0
Requires-Dist: evaluate>=0.4.6
Requires-Dist: httpx>=0.28.0
Requires-Dist: huggingface-hub>=0.36.0
Requires-Dist: hydra-core>=1.3.0
Requires-Dist: langchain-core>=0.3.0
Requires-Dist: langchain-openai>=0.3.0
Requires-Dist: mteb>=1.34.0
Requires-Dist: nltk>=3.9.2
Requires-Dist: numpy>=2.2.6
Requires-Dist: omegaconf>=2.3.0
Requires-Dist: pandas>=2.3.3
Requires-Dist: pgvector>=0.4.1
Requires-Dist: pillow>=12.0.0
Requires-Dist: platformdirs>=4.5.0
Requires-Dist: psycopg[binary]>=3.2.12
Requires-Dist: pydantic>=2.12.4
Requires-Dist: pyyaml>=6.0.0
Requires-Dist: rich>=14.0.0
Requires-Dist: rouge-score>=0.1.2
Requires-Dist: sacrebleu>=2.5.1
Requires-Dist: sqlalchemy>=2.0.44
Requires-Dist: tenacity>=9.1.2
Requires-Dist: tiktoken>=0.12.0
Requires-Dist: tqdm>=4.60.0
Requires-Dist: typer>=0.15.0
Requires-Dist: typing-extensions>=4.15.0
Provides-Extra: all
Requires-Dist: cohere>=5.0.0; extra == 'all'
Requires-Dist: colpali-engine>=0.3.13; extra == 'all'
Requires-Dist: duckdb>=1.0.0; extra == 'all'
Requires-Dist: gradio>=6.0.0; extra == 'all'
Requires-Dist: torch>=2.8.0; extra == 'all'
Requires-Dist: transformers>=4.57.1; extra == 'all'
Requires-Dist: voyageai>=0.3.0; extra == 'all'
Provides-Extra: gpu
Requires-Dist: colpali-engine>=0.3.13; extra == 'gpu'
Requires-Dist: torch>=2.8.0; extra == 'gpu'
Requires-Dist: transformers>=4.57.1; extra == 'gpu'
Provides-Extra: reporting
Requires-Dist: duckdb>=1.0.0; extra == 'reporting'
Requires-Dist: gradio>=6.0.0; extra == 'reporting'
Provides-Extra: reranker
Requires-Dist: cohere>=5.0.0; extra == 'reranker'
Requires-Dist: voyageai>=0.3.0; extra == 'reranker'
Description-Content-Type: text/markdown

# AutoRAG-Research

[![Release](https://img.shields.io/github/v/release/vkehfdl1/AutoRAG-Research)](https://img.shields.io/github/v/release/vkehfdl1/AutoRAG-Research)
[![Build status](https://img.shields.io/github/actions/workflow/status/vkehfdl1/AutoRAG-Research/main.yml?branch=main)](https://github.com/vkehfdl1/AutoRAG-Research/actions/workflows/main.yml?query=branch%3Amain)
[![Commit activity](https://img.shields.io/github/commit-activity/m/vkehfdl1/AutoRAG-Research)](https://img.shields.io/github/commit-activity/m/vkehfdl1/AutoRAG-Research)
[![License](https://img.shields.io/github/license/vkehfdl1/AutoRAG-Research)](https://img.shields.io/github/license/vkehfdl1/AutoRAG-Research)

Automate your RAG research.

- **Github repository**: <https://github.com/vkehfdl1/AutoRAG-Research/>
- **Documentation** <https://vkehfdl1.github.io/AutoRAG-Research/>

## Recommended Setup

The easiest way to get started is with the installation script:

```bash
curl -LsSf https://raw.githubusercontent.com/NomaDamas/AutoRAG-Research/main/scripts/install.sh -o install.sh
bash install.sh
```

The script will guide you through:
1. Setting up a Python environment (supports uv, venv, conda, pyenv, etc.)
2. Installing AutoRAG-Research
3. Configuring PostgreSQL (Docker or existing server)

## CLI Usage

AutoRAG-Research provides a CLI tool for managing RAG research workflows.

### Installation

```bash
pip install autorag-research
```

or

```bash
uv pip install autorag-research
```

### Quick Start

```bash
# 1. Initialize configuration files
autorag-research init

# 2. Edit database settings
vim configs/db.yaml # OR your preferred editor

# 3. Ingest a dataset
autorag-research ingest --name beir --extra dataset-name=scifact

# 4. Run experiments
autorag-research run --db-name=beir_scifact_test
```

### Commands

#### `init` - Initialize Configuration Files

Downloads default configuration files to `./configs/` directory.

```bash
autorag-research init
```

This creates:
- `configs/db.yaml` - Database connection settings
- `configs/experiment.yaml` - Experiment configuration
- `configs/pipelines/**/*.yaml` - Pipeline configurations
- `configs/metrics/**/*.yaml` - Metric configurations

#### `ingest` - Ingest Datasets

Ingest datasets into PostgreSQL. Each ingestor supports different datasets.

```bash
# Show available ingestors
autorag-research ingest --help
```

```bash
autorag-research ingest --name beir --embedding-model mock --query-limit 5 --min-corpus-cnt 10 --extra dataset-name=scifact
```

#### `list` - List Available Resources

```bash
# List available ingestors
autorag-research list ingestors

# List available pipelines
autorag-research list pipelines

# List available metrics
autorag-research list metrics

# List database schemas
autorag-research list databases
```

#### `run` - Run Experiments

Run experiment pipelines with metrics evaluation. **Requires `--db-name` to specify the target database schema.**

```bash
# Basic run (uses configs/experiment.yaml)
autorag-research run --db-name=beir_scifact_test --verbose
```

### Environment Variables

| Variable              | Description |
|-----------------------|-------------|
| `POSTGRES_PASSWORD`   | PostgreSQL password (recommended for security) |
| `AUTORAG_CONFIG_PATH` | Default configuration directory path |


## Implementing New Pipelines (with Claude Code)

This project includes specialized Claude Code agents for implementing new RAG pipelines from research papers.

### Quick Start

```bash
# Full workflow from paper to validated code
/implement-pipeline https://arxiv.org/abs/2212.10496
```
