app.py

import gradio as gr
from llm_loader import load_model
from processing import process_input
from transcription_diarization import diarize_audio
from visualization import create_charts
import time
from config import openai_api_key

# Load the model
llm = load_model(openai_api_key)


def analyze_video(video_path, language, progress=gr.Progress()):
    start_time = time.time()
    if not video_path:
        return [gr.Markdown("Please upload a video file.")] + [gr.update(visible=False)] * 49 + [
            "Analysis not started."]

    progress(0, desc="Starting analysis...")
    progress(0.2, desc="Starting transcription and diarization")
    transcription = diarize_audio(video_path, language)
    print("Transcription:", transcription)  # Debug print
    progress(0.5, desc="Transcription and diarization complete.")

    progress(0.6, desc="Processing transcription")
    results = process_input(transcription, llm)
    progress(0.7, desc="Transcription processing complete.")

    progress(0.9, desc="Generating charts")
    charts, explanations = create_charts(results)
    progress(1.0, desc="Charts generation complete.")

    end_time = time.time()
    execution_time = end_time - start_time

    output_components = []

    # Add transcript near the beginning
    output_components.append(gr.Textbox(value=transcription, label="Transcript", lines=10, visible=True))
    
    for speaker_id, speaker_charts in charts.items():
        markdown_content = f"""
        | {speaker_id} |
        |-----------|
        """
        speaker_explanations = explanations[speaker_id]
        speaker_section = [
            gr.Markdown(markdown_content, visible=True),
            gr.Plot(value=speaker_charts.get("attachment", None), visible=True),
            gr.Textbox(value=speaker_explanations.get("attachment", ""), label="Attachment Styles Explanation",
                       visible=True),
            gr.Plot(value=speaker_charts.get("dimensions", None), visible=True),
            gr.Plot(value=speaker_charts.get("bigfive", None), visible=True),
            gr.Textbox(value=speaker_explanations.get("bigfive", ""), label="Big Five Traits Explanation",
                       visible=True),
            gr.Plot(value=speaker_charts.get("personality", None), visible=True),
            gr.Textbox(value=speaker_explanations.get("personality", ""), label="Personality Disorders Explanation",
                       visible=True),
        ]
        output_components.extend(speaker_section)

    while len(output_components) < 49:
        output_components.extend([gr.update(visible=False)] * 8)

    # Add execution info
    output_components.append(
        gr.Textbox(value=f"Completed in {int(execution_time)} seconds.", label="Execution Information", visible=True))

    return output_components


with gr.Blocks() as iface:
    gr.Markdown("# AI Personality Detection")
    gr.Markdown("Upload a video")

    video_input = gr.Video(label="Upload Video")
    language_dropdown = gr.Dropdown(
        choices=["English", "Hebrew", "Arabic", "French", "German", "Italian", "Japanese", "Chinese", "Auto-detect"],
        value="English",
        label="Transcription Language"
    )
    analyze_button = gr.Button("Analyze")

    # Create output components
    output_components = []

    # Add transcript output near the top
    execution_info_box = gr.Textbox(label="Execution Information", value="N/A", lines=1)
    output_components.append(execution_info_box)

    for _ in range(3):  # Assuming maximum of 3 speakers
        output_components.extend([
            gr.Markdown(visible=False),
            gr.Plot(visible=False),
            gr.Textbox(label="Attachment Styles Explanation", visible=False),
            gr.Plot(visible=False),
            gr.Plot(visible=False),
            gr.Textbox(label="Big Five Traits Explanation", visible=False),
            gr.Plot(visible=False),
            gr.Textbox(label="Personality Disorders Explanation", visible=False),
        ])

    # Add execution info component
    transcript_output = gr.Textbox(label="Transcript", lines=10, visible=False)
    output_components.append(transcript_output)

    analyze_button.click(
        fn=analyze_video,
        inputs=[video_input, language_dropdown],
        outputs=output_components,
        show_progress=True
    )

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