Document_RAG/setup.py at main · kedardg/Document_RAG · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
from setuptools import setup, find_packages

setup(
    name="doc_pipeline",
    version="0.1.0",
    author="AI Assistant",
    description="A modular pipeline for document parsing, chunking, and retrieval.",
    packages=find_packages(where="src"),
    package_dir={"": "src"},
    install_requires=[
        # Core document processing
        "PyMuPDF>=1.23.0",
        "camelot-py[cv]>=0.11.0",
        "pandas>=2.0.0",
        "pytesseract>=0.3.10",
        "Pillow>=10.0.0",

        # Google Cloud
        "google-cloud-documentai>=2.20.0",
        "google-cloud-aiplatform>=1.36.0",
        "google-protobuf>=4.24.0",

        # Text processing and chunking
        "langchain-text-splitters>=0.0.1",

        # Graph orchestration
        "langgraph>=0.0.40",

        # Vector and graph databases
        "qdrant-client>=1.6.0",
        "neo4j>=5.13.0",

        # Embeddings
        "fastembed>=0.1.0",

        # Data handling
        "numpy>=1.24.0",
        "typing-extensions>=4.0.0",

        # Configuration
        "python-dotenv>=1.0.0",
    ],
    extras_require={
        "dev": [
            "pytest>=7.0.0",
            "black>=23.0.0",
            "isort>=5.12.0",
            "mypy>=1.5.0",
        ],
        "notebooks": [
            "jupyter>=1.0.0",
            "matplotlib>=3.7.0",
        ]
    },
    python_requires=">=3.9",
    classifiers=[
        "Development Status :: 3 - Alpha",
        "Intended Audience :: Developers",
        "License :: OSI Approved :: MIT License",
        "Programming Language :: Python :: 3",
        "Programming Language :: Python :: 3.9",
        "Programming Language :: Python :: 3.10",
        "Programming Language :: Python :: 3.11",
    ],
)