| Name | lugacore JSON |
| Version |
0.1.0a1
JSON |
| download |
| home_page | None |
| Summary | A Naive RAG SDK using Gemini for embeddings, Qdrant for retrieval, and document loaders for building RAG piplines from scratch. |
| upload_time | 2025-10-30 15:36:40 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.12 |
| license | None |
| keywords |
rag
retrieval-augmented-generation
gemini
qdrant
sdk
ai
nlp
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<h1 align="center" >LugaCore</h1>
[](LICENSE)
A lightweight, modular Retrieval-Augmented-Generation (RAG) system built from fundamental python libraries for efficient, verifiable Q&A.
## **📘 Overview**
This project is a RAG framework built without reliance on high-level orchestration libraries. it demonstrates a ground-up implementation of the key RAG components.
## **✨ Features**
**Custom Document Processing**:
* **Self-implemented Text Splitter**: Recursive,semantic text splitting with token awareness logic for optimal chunk boundaries.
* **Custom Document Loader**: Direct .docx parsing via python-docx, preserving paragraphs.
**Intelligent Retrieval**:
* **Hybrid Search Engine**: combines dense semantic and sparse keyword retrieval within Qdrant for flexible query resolution.
* **Qdrant Integration**: Native support for:
* Vector indexing and collection management
* Batch upserts and attribute-based payload filtering
* Hybrid retrieval experimentation (dense + sparse)
**Gemini LLM Integration**
* **LLM-Driven Generation**: Uses **Gemini** exclusively for answer synthesis, summarization, and context-aware responses.
* **Context injection**: Dynamically augments user queries with retrieved context chunks.
* **Conversation Flow**: Uses [Gemini chat SDK](https://ai.google.dev/gemini-api/docs/text-generation) for multi-turn conversations keeping track of user queries and RAG responses to improve relevance.
**Modular & Transparent**
* 100% open and debuggable - designed for **learning**, **research**, and **low-level RAG experimentation**.
## **🚀 Installation & Quick Start**
Follow these steps to install **LangCore** from PyPI and start using your RAG powered by Gemini.
### 1. Create project directory (if not already created)
```bash
# setup
mkdir my_project
cd my_project
```
### 2. Create and activate Virtual environment
````bash
# create a virtual environment
python -m venv virt
#Activate it (windows)
source virt/scripts/activate
````
### 3. Install LugaCore from PyPI
````bash
pip install lugacore
````
### 4. Verify Installation
````bash
pip list | grep lugacore
````
### 5. Quick Start Example
````python
from lugacore import LugaCore
#Initialize RAG pipeline
rag = LugaCore(
qdrant_api_key="YOUR_QDRANT_API_KEY",
gemini_api_key="YOUR_GEMINI_API_KEY",
qdrant_url="YOUR_QDRANT_URL"
)
# Ingest documents
rag.load_document(filepath_or_buffer="path/to/your/file.docx")
#Query your knowledge base
response = rag.ask("What is physics?")
print(response)
````
## **🧩 Planed Features**
* Re-ranking.
* Knowledge Graph
* Caching layer
* Multimodal support (images,audio, video).
* Agentic pipelines
* Async & Sync support
Raw data
{
"_id": null,
"home_page": null,
"name": "lugacore",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": "rag, retrieval-augmented-generation, gemini, qdrant, sdk, ai, nlp",
"author": null,
"author_email": "Acram Kagimu <acramkagimu@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/0e/3b/f0e70c8d2d4e3894e47bb1328fd8b5aa49109f2a66edc887794802502987/lugacore-0.1.0a1.tar.gz",
"platform": null,
"description": "<h1 align=\"center\" >LugaCore</h1>\r\n\r\n[](LICENSE) \r\n\r\n\r\n\r\n\r\nA lightweight, modular Retrieval-Augmented-Generation (RAG) system built from fundamental python libraries for efficient, verifiable Q&A.\r\n\r\n## **\ud83d\udcd8 Overview**\r\nThis project is a RAG framework built without reliance on high-level orchestration libraries. it demonstrates a ground-up implementation of the key RAG components.\r\n\r\n## **\u2728 Features**\r\n**Custom Document Processing**:\r\n* **Self-implemented Text Splitter**: Recursive,semantic text splitting with token awareness logic for optimal chunk boundaries.\r\n* **Custom Document Loader**: Direct .docx parsing via python-docx, preserving paragraphs.\r\n\r\n**Intelligent Retrieval**:\r\n* **Hybrid Search Engine**: combines dense semantic and sparse keyword retrieval within Qdrant for flexible query resolution.\r\n* **Qdrant Integration**: Native support for:\r\n * Vector indexing and collection management\r\n * Batch upserts and attribute-based payload filtering\r\n * Hybrid retrieval experimentation (dense + sparse)\r\n\r\n**Gemini LLM Integration** \r\n* **LLM-Driven Generation**: Uses **Gemini** exclusively for answer synthesis, summarization, and context-aware responses.\r\n* **Context injection**: Dynamically augments user queries with retrieved context chunks.\r\n* **Conversation Flow**: Uses [Gemini chat SDK](https://ai.google.dev/gemini-api/docs/text-generation) for multi-turn conversations keeping track of user queries and RAG responses to improve relevance.\r\n\r\n**Modular & Transparent**\r\n* 100% open and debuggable - designed for **learning**, **research**, and **low-level RAG experimentation**.\r\n\r\n\r\n## **\ud83d\ude80 Installation & Quick Start**\r\nFollow these steps to install **LangCore** from PyPI and start using your RAG powered by Gemini.\r\n### 1. Create project directory (if not already created)\r\n```bash\r\n# setup\r\nmkdir my_project\r\ncd my_project\r\n```\r\n### 2. Create and activate Virtual environment\r\n\r\n````bash\r\n# create a virtual environment\r\npython -m venv virt\r\n\r\n#Activate it (windows)\r\nsource virt/scripts/activate\r\n````\r\n### 3. Install LugaCore from PyPI\r\n\r\n\r\n````bash\r\n pip install lugacore\r\n````\r\n### 4. Verify Installation\r\n\r\n````bash\r\npip list | grep lugacore\r\n````\r\n### 5. Quick Start Example\r\n\r\n````python\r\nfrom lugacore import LugaCore\r\n\r\n#Initialize RAG pipeline\r\nrag = LugaCore(\r\n qdrant_api_key=\"YOUR_QDRANT_API_KEY\",\r\n gemini_api_key=\"YOUR_GEMINI_API_KEY\",\r\n qdrant_url=\"YOUR_QDRANT_URL\"\r\n)\r\n\r\n# Ingest documents\r\nrag.load_document(filepath_or_buffer=\"path/to/your/file.docx\")\r\n\r\n#Query your knowledge base\r\nresponse = rag.ask(\"What is physics?\")\r\nprint(response)\r\n````\r\n## **\ud83e\udde9 Planed Features**\r\n\r\n* Re-ranking.\r\n* Knowledge Graph\r\n* Caching layer\r\n* Multimodal support (images,audio, video).\r\n* Agentic pipelines\r\n* Async & Sync support\r\n\r\n",
"bugtrack_url": null,
"license": null,
"summary": "A Naive RAG SDK using Gemini for embeddings, Qdrant for retrieval, and document loaders for building RAG piplines from scratch.",
"version": "0.1.0a1",
"project_urls": {
"Homepage": "https://github.com/Acram123-arch/lugacore",
"Issues": "https://github.com/Acram123-arch/lugacore/issues"
},
"split_keywords": [
"rag",
" retrieval-augmented-generation",
" gemini",
" qdrant",
" sdk",
" ai",
" nlp"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "dc6492875c63f75648eee7c229d45b2e6edb320f9b79e91bb7aa43dda7cf9bad",
"md5": "a0c4b8666610e3848c4bd5e7c6ff6076",
"sha256": "7d3a801242d1627e41958ece36358912f21ecbc74b8f65e40e18b7284f65a7eb"
},
"downloads": -1,
"filename": "lugacore-0.1.0a1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a0c4b8666610e3848c4bd5e7c6ff6076",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 13687,
"upload_time": "2025-10-30T15:36:39",
"upload_time_iso_8601": "2025-10-30T15:36:39.314432Z",
"url": "https://files.pythonhosted.org/packages/dc/64/92875c63f75648eee7c229d45b2e6edb320f9b79e91bb7aa43dda7cf9bad/lugacore-0.1.0a1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "0e3bf0e70c8d2d4e3894e47bb1328fd8b5aa49109f2a66edc887794802502987",
"md5": "7d8954eb2ce3ff8a6a47a3de0e95bf8f",
"sha256": "9b9d95b736170471f4bf652a6e6abc63df42bb1df24ff4635a9f74b4e52bebaa"
},
"downloads": -1,
"filename": "lugacore-0.1.0a1.tar.gz",
"has_sig": false,
"md5_digest": "7d8954eb2ce3ff8a6a47a3de0e95bf8f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 12884,
"upload_time": "2025-10-30T15:36:40",
"upload_time_iso_8601": "2025-10-30T15:36:40.795454Z",
"url": "https://files.pythonhosted.org/packages/0e/3b/f0e70c8d2d4e3894e47bb1328fd8b5aa49109f2a66edc887794802502987/lugacore-0.1.0a1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-30 15:36:40",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Acram123-arch",
"github_project": "lugacore",
"github_not_found": true,
"lcname": "lugacore"
}
