hawkins-rag

Name	hawkins-rag JSON
Version	0.1.0 JSON
	download
home_page	None
Summary	A Python package for building RAG systems with HawkinsDB and multiple data source integrations
upload_time	2024-12-25 17:20:49
maintainer	None
docs_url	None
author	HawkinsRAG Team
requires_python	>=3.11
license	MIT
keywords	ai embeddings hawkinsdb llm rag search
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # HawkinsRAG

A Python package for building Retrieval-Augmented Generation (RAG) systems with HawkinsDB and multiple data source integrations.

## Features
- Multiple data source support through specialized loaders
- Efficient text chunking and embedding
- Seamless integration with HawkinsDB
- Flexible configuration options
- Comprehensive error handling

## Installation

```bash
pip install hawkins-rag
```

## Quick Start

```python
from hawkins_rag import HawkinsRAG

# Initialize RAG system
rag = HawkinsRAG()

# Load document
result = rag.load_document("document.txt", source_type="text")

# Query content
response = rag.query("What is this document about?")
print(response)
```

## Supported Data Sources

HawkinsRAG supports multiple data sources through specialized loaders:

- Text files (txt, pdf, docx)
- Web content (YouTube, webpages)
- Structured data (JSON, CSV)
- APIs (GitHub, Gmail, Slack)
- Databases (MySQL, PostgreSQL)
- And many more!

## Configuration

```python
config = {
    "storage_type": "sqlite",  # or "postgres"
    "db_path": "hawkins_rag.db",
    "chunk_size": 500,
    "loader_config": {
        "youtube": {
            "api_key": "YOUR_YOUTUBE_API_KEY"
        },
        "github": {
            "token": "YOUR_GITHUB_TOKEN"
        }
    }
}

rag = HawkinsRAG(config=config)
```

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## Documentation

For detailed documentation, visit [HawkinsRAG Documentation](https://github.com/harishsg993010/HawkinsRAG/docs).

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "hawkins-rag",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.11",
    "maintainer_email": null,
    "keywords": "ai, embeddings, hawkinsdb, llm, rag, search",
    "author": "HawkinsRAG Team",
    "author_email": null,
    "download_url": null,
    "platform": null,
    "description": "# HawkinsRAG\n\nA Python package for building Retrieval-Augmented Generation (RAG) systems with HawkinsDB and multiple data source integrations.\n\n## Features\n- Multiple data source support through specialized loaders\n- Efficient text chunking and embedding\n- Seamless integration with HawkinsDB\n- Flexible configuration options\n- Comprehensive error handling\n\n## Installation\n\n```bash\npip install hawkins-rag\n```\n\n## Quick Start\n\n```python\nfrom hawkins_rag import HawkinsRAG\n\n# Initialize RAG system\nrag = HawkinsRAG()\n\n# Load document\nresult = rag.load_document(\"document.txt\", source_type=\"text\")\n\n# Query content\nresponse = rag.query(\"What is this document about?\")\nprint(response)\n```\n\n## Supported Data Sources\n\nHawkinsRAG supports multiple data sources through specialized loaders:\n\n- Text files (txt, pdf, docx)\n- Web content (YouTube, webpages)\n- Structured data (JSON, CSV)\n- APIs (GitHub, Gmail, Slack)\n- Databases (MySQL, PostgreSQL)\n- And many more!\n\n## Configuration\n\n```python\nconfig = {\n    \"storage_type\": \"sqlite\",  # or \"postgres\"\n    \"db_path\": \"hawkins_rag.db\",\n    \"chunk_size\": 500,\n    \"loader_config\": {\n        \"youtube\": {\n            \"api_key\": \"YOUR_YOUTUBE_API_KEY\"\n        },\n        \"github\": {\n            \"token\": \"YOUR_GITHUB_TOKEN\"\n        }\n    }\n}\n\nrag = HawkinsRAG(config=config)\n```\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Documentation\n\nFor detailed documentation, visit [HawkinsRAG Documentation](https://github.com/harishsg993010/HawkinsRAG/docs).\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "A Python package for building RAG systems with HawkinsDB and multiple data source integrations",
    "version": "0.1.0",
    "project_urls": {
        "Documentation": "https://github.com/harishsg993010/HawkinsRAG/docs",
        "Source": "https://github.com/harishsg993010/HawkinsRAG"
    },
    "split_keywords": [
        "ai",
        " embeddings",
        " hawkinsdb",
        " llm",
        " rag",
        " search"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "52d845cf4acab26131eff872e8bb5bf9fb5c9c3429e5dd65b0d7545eb056c9f5",
                "md5": "59f17e3877b281cf523f6eaa72eba164",
                "sha256": "54ad186f4823d075aa65d30c3c61a75d28afc50237fa0203d9a3bb4162bbdff8"
            },
            "downloads": -1,
            "filename": "hawkins_rag-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "59f17e3877b281cf523f6eaa72eba164",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.11",
            "size": 64573,
            "upload_time": "2024-12-25T17:20:49",
            "upload_time_iso_8601": "2024-12-25T17:20:49.594639Z",
            "url": "https://files.pythonhosted.org/packages/52/d8/45cf4acab26131eff872e8bb5bf9fb5c9c3429e5dd65b0d7545eb056c9f5/hawkins_rag-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-12-25 17:20:49",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "harishsg993010",
    "github_project": "HawkinsRAG",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "lcname": "hawkins-rag"
}