[project]
name = "docling-pdf-processor"
version = "0.2.0"
description = "PDF extraction pipeline using Docling – extracts text, pages, and figures; then uses a Vision LLM to summarise charts/graphs."
requires-python = ">=3.10"
readme = "README.md"
dependencies = [
    "docling>=2.0.0",
    "docling-core>=2.0.0",
    "Pillow>=10.0.0",
    "matplotlib>=3.8.0",
    "tqdm>=4.66.0",
    "llama_index",
    "numpy>=1.26.0",
    "langchain",
    "cohere",
    "llama-index-llms-groq",
    "llama-index-embeddings-huggingface",
    "gradio>=4.0",
    "python-dotenv>=1.0.0",
    "pydantic>=2.0",
    "pydantic-settings>=2.0",
    "python-json-logger>=2.0",
]

[project.scripts]
extract   = "docling_pdf_processor.cli:extract_command"
preprocess = "docling_pdf_processor.cli:preprocess_command"
app       = "docling_pdf_processor.cli:app_command"

[dependency-groups]
dev = [
    "ipykernel>=6.29.0",
    "jupyter>=1.0.0",
    "pytest>=8.0",
    "pytest-asyncio>=0.23",
]

[tool.hatch.build.targets.wheel]
packages = ["docling_pdf_processor"]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"