app.py

import gradio as gr
import google.generativeai as genai
import requests
import base64
import json
from tenacity import retry, stop_after_attempt, wait_fixed

def fetch_github_files(github_url, personal_access_token):
    # ... (keep this function as is) ...

def process_chunk_with_gemini(chunk, gemini_api_key):
    genai.configure(api_key=gemini_api_key)
    model = genai.GenerativeModel('gemini-2.5-pro-preview-03-25')
    
    prompt = f"""
    Analyze the following file content for open-source license information:

    {chunk}

    Please provide:
    1. A numbered list with the name dependency and version as the title 
    2. 1st bullet under title has a brief summary of what the dependency does
    3. 2nd bullet under title has the license name
    4. 3rd bullet under title has a hyperlink to the license file
    5. Provide no other information such as greeting or summary as the purpose is to catalog and document all open source licenses used.
    """

    response = model.generate_content(prompt)
    return response.text

@retry(stop=stop_after_attempt(3), wait=wait_fixed(2))
def process_with_gemini(file_content, gemini_api_key):
    # Split the content into chunks of approximately 4000 characters
    chunk_size = 4000
    chunks = [file_content[i:i+chunk_size] for i in range(0, len(file_content), chunk_size)]
    
    results = []
    for chunk in chunks:
        result = process_chunk_with_gemini(chunk, gemini_api_key)
        results.append(result)
    
    # Combine the results
    combined_result = "\n\n".join(results)
    return combined_result

def process_input(github_url, personal_access_token, gemini_api_key):
    if not github_url.startswith("https://github.com/"):
        return "Error: Invalid GitHub URL. Please use the format: https://github.com/username/repository.git"
    if not personal_access_token.strip():
        return "Error: Personal Access Token is empty. Please provide a valid token."
    
    file_content = fetch_github_files(github_url, personal_access_token)
    if file_content.startswith("Error:"):
        return file_content
    
    try:
        # Process the file content with Gemini
        analysis = process_with_gemini(file_content, gemini_api_key)
        return analysis
    except Exception as e:
        return f"Error processing the files: {str(e)}"

iface = gr.Interface(
    fn=process_input,
    inputs=[
        gr.Textbox(label="GitHub Repository URL (format: https://github.com/username/repository.git)"),
        gr.Textbox(label="GitHub Personal Access Token", type="password"),
        gr.Textbox(label="Gemini API Key", type="password"),
    ],
    outputs=gr.Textbox(label="License Information and Analysis"),
    title="Open Source License Extractor",
    description="Provide a GitHub repository URL to analyze open-source licenses from dependency files.",
)

if __name__ == "__main__":
    iface.launch()