import subprocess
import re

# List of packages you want to include
packages = [
    "openai",
    "pandas",
    "python-dotenv",
    "fastapi",
    "uvicorn",
    "langchain-community",
    "langchain-openai",
    "pydantic",
    "pypdf",
    "pypandoc",
    "plum-dispatch==1.7.4",  # You specified exact version here
    "scikit-learn",
    "werkzeug",
    "python-multipart",
    "langgraph",
    "tiktoken",
    "langchainhub",
    "chromadb",
    "langchain",
    "langchain-text-splitters",
    "beautifulsoup4",
    "langchain-core",
    "PyPDF2",
    "reportlab",
    "python-docx"
]

# Get all installed packages with versions
result = subprocess.run(["pip", "freeze"], capture_output=True, text=True)
installed_packages = result.stdout.strip().split('\n')

# Create a dictionary of package names to their full name with version
package_dict = {}
for pkg in installed_packages:
    if '==' in pkg:
        name = pkg.split('==')[0].lower()
        package_dict[name] = pkg

# Write only the requested packages to requirements.txt
with open('requirements.txt', 'w') as f:
    for package in packages:
        # Handle cases where version is already specifixed
        if '==' in package:
            f.write(f"{package}\n")
            continue
            
        # Try to find the package in installed packages
        pkg_name = package.lower()
        if pkg_name in package_dict:
            f.write(f"{package_dict[pkg_name]}\n")
        else:
            # If not found, just write the package name
            f.write(f"{package}\n")
            print(f"Warning: {package} not found in installed packages")

print("requirements.txt has been generated.")