Metadata-Version: 2.4
Name: llmforge
Version: 0.0.1
Summary: Placeholder package to reserve the llmforge name
Author-email: Anik Mallick <anik.mallick.code@gmail.com>
License: MIT
Keywords: llm,generative-ai,rag,prompt-engineering
Classifier: Development Status :: 1 - Planning
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Requires-Dist: black; extra == "dev"
Requires-Dist: mypy; extra == "dev"
Dynamic: license-file

 LLMForge

**LLMForge** is a structured framework for building reliable, context-aware LLM applications.  
It introduces modular prompting, contextual chunking, and developer-friendly tools for controlled generation.

> ⚠️ This is a placeholder package. Full features coming soon.

---

## 🚀 Features (Planned)

- 🔧 **Structured Prompting:** Define system and user prompts with composable, reusable components.
- 🧩 **Contextual Chunking:** Use advanced chunking strategies including LLM-assisted context-aware splitting.
- 📚 **Multi-Level RAG Support:** Summarize, tag, and manage references across multi-doc pipelines.
- 🧠 **Prompt Meta Control:** Inject data structure, generation intent, output formats, and few-shot examples into your prompt logic.
- 🔄 **LLM Workflow Templates:** Declarative flow control for chaining LLM calls.

---

## 📦 Installation

Install from [PyPI](https://pypi.org/project/llmforge):

```bash
pip install llmforge
```

---

## 🛠 Development Setup

If you're working on the project locally:

```bash
# Create virtual environment (optional but recommended)
python -m venv .venv
source .venv/bin/activate  # or .venv\\Scripts\\activate on Windows

# Install dependencies
uv pip install -e ".[dev]"
```

---

## 📄 License

This project is licensed under the terms of the [MIT License](LICENSE).

---

## 📬 Contact

Created by [Anik Mallick](mailto:anik.mallick.code@gmail.com) — feel free to reach out!
