Metadata-Version: 2.4
Name: llm4smeft
Version: 0.1.0
Summary: LLM-driven interactive hypothesis generation for SMEFT global fits
Author: HEP
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: numpy<2
Requires-Dist: pandas
Requires-Dist: huggingface-hub<1.0.0,>=0.33.4
Requires-Dist: transformers<4.52.0,>=4.45.0
Requires-Dist: accelerate<1.0.0,>=0.26.0
Requires-Dist: langchain>=0.3.0
Requires-Dist: langchain-huggingface<1.3.0,>=0.1.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: torch
Requires-Dist: python-dotenv

# LLM4SMEFT

LLM-driven interactive hypothesis generation for SMEFT global fits. It works as a prior hyptheses inference to SMEFiT package. 

## Install

```bash
pip install llm4smeft
```


## Run

```bash
llm4smeft
```

This launches the interactive session (equivalent to the old
`./run.sh` / `python src/experiments/run_interactive.py`).

## Data

The SMEFiT summary records used by the retrieval module ship inside the
package (`llm4smeft/data/*.json`) and are located relative to the
installed package files, not the current working directory — so
`llm4smeft` works from any directory after `pip install`. Session
records accepted during a run are written back into that same
installed `data/` folder unless `LLM4SMEFT_DATA_DIR` is set to another
path.
