| Name | maktaba JSON |
| Version |
0.1.6
JSON |
| download |
| home_page | None |
| Summary | Production-ready RAG infrastructure for multilingual applications |
| upload_time | 2025-10-26 21:02:03 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
ai
embeddings
llm
rag
retrieval
vector-search
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Maktaba
[](https://github.com/nuhatech/maktaba/actions/workflows/ci.yml)
[](https://badge.fury.io/py/maktaba)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
**The library for building libraries** - By NuhaTech
> From the Arabic word for library, Maktaba is a modern RAG infrastructure for building intelligent knowledge systems in any language.
## Features
- 🔌 **Provider-agnostic**: Works with OpenAI, Cohere, Azure, and more
- 🚀 **Production-ready**: Built for scale with async-first design
- 🧩 **Modular**: Use only what you need
- 🌍 **Multilingual**: Optimized for Arabic and international languages
- 📊 **Type-safe**: Full type hints and Pydantic validation
- 🧪 **Well-tested**: Comprehensive test coverage
## Installation
### Using UV (Recommended)
```bash
# Install UV if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Add maktaba to your project
uv add maktaba
# With OpenAI + Qdrant
uv add "maktaba[openai,qdrant]"
# With all providers
uv add "maktaba[all]"
```
### Using pip
```bash
# Basic installation
pip install maktaba
# With OpenAI + Qdrant
pip install "maktaba[openai,qdrant]"
# With all providers
pip install "maktaba[all]"
```
## Quick Start
```python
from maktaba.pipeline import QueryPipeline
from maktaba.embedding import OpenAIEmbedder
from maktaba.storage import QdrantStore
from maktaba.reranking import CohereReranker
# Create pipeline
pipeline = QueryPipeline(
embedder=OpenAIEmbedder(api_key="..."),
vector_store=QdrantStore(url="http://localhost:6333", collection_name="docs"),
reranker=CohereReranker(api_key="...")
)
# Search with automatic reranking and citation formatting
result = await pipeline.search(
query="What is Tawhid?",
top_k=10,
rerank=True
)
# Use in your LLM prompt
print(result["formatted_context"]) # [1]: content... [2]: content...
print(result["citations"]) # [{id: 1, source: "...", score: 0.95}, ...]
```
## Development
### Running Checks Before Push
Before pushing to the remote repository, run all quality checks:
**Linux/Mac/Git Bash:**
```bash
./scripts/check.sh
```
**Windows CMD:**
```cmd
scripts\check.bat
```
This will run:
- Ruff linting
- MyPy type checking
- Pytest tests
All checks must pass before pushing.
## Documentation
- Overview: docs/Overview.md
- Quickstart: docs/Quickstart.md
- Pipelines: docs/Pipelines.md
- Providers: docs/Providers.md
- Examples: docs/Examples.md
- Troubleshooting: docs/Troubleshooting.md
Website (coming soon): maktaba.nuhatech.com
## License
MIT License - see [LICENSE](LICENSE)
## About NuhaTech
Built by [NuhaTech](https://nuhatech.com) - creators of Kutub and Muqabia.
Raw data
{
"_id": null,
"home_page": null,
"name": "maktaba",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ai, embeddings, llm, rag, retrieval, vector-search",
"author": null,
"author_email": "NuhaTech <contact@nuhatech.com>",
"download_url": "https://files.pythonhosted.org/packages/3b/cc/7ef2625b13c234efaf16a7135d334055db50c6d7ad94e3a93d1e01cbf2ae/maktaba-0.1.6.tar.gz",
"platform": null,
"description": "# Maktaba\n\n[](https://github.com/nuhatech/maktaba/actions/workflows/ci.yml)\n[](https://badge.fury.io/py/maktaba)\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n\n**The library for building libraries** - By NuhaTech\n\n> From the Arabic word for library, Maktaba is a modern RAG infrastructure for building intelligent knowledge systems in any language.\n\n## Features\n\n- \ud83d\udd0c **Provider-agnostic**: Works with OpenAI, Cohere, Azure, and more\n- \ud83d\ude80 **Production-ready**: Built for scale with async-first design\n- \ud83e\udde9 **Modular**: Use only what you need\n- \ud83c\udf0d **Multilingual**: Optimized for Arabic and international languages\n- \ud83d\udcca **Type-safe**: Full type hints and Pydantic validation\n- \ud83e\uddea **Well-tested**: Comprehensive test coverage\n\n## Installation\n\n### Using UV (Recommended)\n\n```bash\n# Install UV if you haven't already\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n\n# Add maktaba to your project\nuv add maktaba\n\n# With OpenAI + Qdrant\nuv add \"maktaba[openai,qdrant]\"\n\n# With all providers\nuv add \"maktaba[all]\"\n```\n\n### Using pip\n\n```bash\n# Basic installation\npip install maktaba\n\n# With OpenAI + Qdrant\npip install \"maktaba[openai,qdrant]\"\n\n# With all providers\npip install \"maktaba[all]\"\n```\n\n## Quick Start\n\n```python\nfrom maktaba.pipeline import QueryPipeline\nfrom maktaba.embedding import OpenAIEmbedder\nfrom maktaba.storage import QdrantStore\nfrom maktaba.reranking import CohereReranker\n\n# Create pipeline\npipeline = QueryPipeline(\n embedder=OpenAIEmbedder(api_key=\"...\"),\n vector_store=QdrantStore(url=\"http://localhost:6333\", collection_name=\"docs\"),\n reranker=CohereReranker(api_key=\"...\")\n)\n\n# Search with automatic reranking and citation formatting\nresult = await pipeline.search(\n query=\"What is Tawhid?\",\n top_k=10,\n rerank=True\n)\n\n# Use in your LLM prompt\nprint(result[\"formatted_context\"]) # [1]: content... [2]: content...\nprint(result[\"citations\"]) # [{id: 1, source: \"...\", score: 0.95}, ...]\n```\n\n## Development\n\n### Running Checks Before Push\n\nBefore pushing to the remote repository, run all quality checks:\n\n**Linux/Mac/Git Bash:**\n```bash\n./scripts/check.sh\n```\n\n**Windows CMD:**\n```cmd\nscripts\\check.bat\n```\n\nThis will run:\n- Ruff linting\n- MyPy type checking\n- Pytest tests\n\nAll checks must pass before pushing.\n\n## Documentation\n\n- Overview: docs/Overview.md\n- Quickstart: docs/Quickstart.md\n- Pipelines: docs/Pipelines.md\n- Providers: docs/Providers.md\n- Examples: docs/Examples.md\n- Troubleshooting: docs/Troubleshooting.md\n\nWebsite (coming soon): maktaba.nuhatech.com\n\n## License\n\nMIT License - see [LICENSE](LICENSE)\n\n## About NuhaTech\n\nBuilt by [NuhaTech](https://nuhatech.com) - creators of Kutub and Muqabia.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Production-ready RAG infrastructure for multilingual applications",
"version": "0.1.6",
"project_urls": {
"Documentation": "https://maktaba.nuhatech.com",
"Homepage": "https://github.com/nuhatech/maktaba",
"Issues": "https://github.com/nuhatech/maktaba/issues",
"Repository": "https://github.com/nuhatech/maktaba"
},
"split_keywords": [
"ai",
" embeddings",
" llm",
" rag",
" retrieval",
" vector-search"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2393575f53394e66aa850624501f616eb0b60588b15b433d25ba7637086158c9",
"md5": "97db29e6ae2b7451d279b7c8c82728da",
"sha256": "1b2b10e027b47644f3ccb4fd66ea5bdf157b79aced3981b9ea361a23b14cc705"
},
"downloads": -1,
"filename": "maktaba-0.1.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "97db29e6ae2b7451d279b7c8c82728da",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 55041,
"upload_time": "2025-10-26T21:02:02",
"upload_time_iso_8601": "2025-10-26T21:02:02.237139Z",
"url": "https://files.pythonhosted.org/packages/23/93/575f53394e66aa850624501f616eb0b60588b15b433d25ba7637086158c9/maktaba-0.1.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "3bcc7ef2625b13c234efaf16a7135d334055db50c6d7ad94e3a93d1e01cbf2ae",
"md5": "612137a00bcf9d801245e9093b02de61",
"sha256": "dfefb6ce9c19a2d73d41ee73672ff0955088df105608d5b4b4cb43451f73a8a2"
},
"downloads": -1,
"filename": "maktaba-0.1.6.tar.gz",
"has_sig": false,
"md5_digest": "612137a00bcf9d801245e9093b02de61",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 472289,
"upload_time": "2025-10-26T21:02:03",
"upload_time_iso_8601": "2025-10-26T21:02:03.441174Z",
"url": "https://files.pythonhosted.org/packages/3b/cc/7ef2625b13c234efaf16a7135d334055db50c6d7ad94e3a93d1e01cbf2ae/maktaba-0.1.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-26 21:02:03",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nuhatech",
"github_project": "maktaba",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "maktaba"
}
