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, progress=gr.Progress()):
    start_time = time.time()
    if not video_path:
        return [None] * 29  # Return None for all outputs

    progress(0, desc="Starting analysis...")
    progress(0.2, desc="Starting transcription and diarization")
    transcription = diarize_audio(video_path)
    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, general_impressions = create_charts(results)
    progress(1.0, desc="Charts generation complete.")

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

    output_components = [transcription]  # transcript

    for i, (speaker_id, speaker_charts) in enumerate(charts.items(), start=1):
        speaker_explanations = explanations[speaker_id]
        speaker_general_impression = general_impressions[speaker_id]

        speaker_section = [
            gr.Markdown(f"## {speaker_id}", visible=True),
            gr.Textbox(value=speaker_general_impression, label="General Impression",
                       visible=True),
            gr.Plot(value=speaker_charts.get("attachment", None), visible=True),
            gr.Plot(value=speaker_charts.get("dimensions", None), visible=True),

            gr.Textbox(value=speaker_explanations.get("attachment", ""), label="Attachment Styles Explanation",
                       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)
        output_components.append(gr.update(visible=True))
        
    # Hide unused tabs
    for j in range(i, 3):
        output_components.extend([gr.update(visible=False)] * 9)  # Hide components
        output_components.append(gr.update(visible=False))  # Hide the tab 
        
    # Pad with None for any missing speakers
    while len(output_components) < 28:
        output_components.extend([gr.update(visible=False)] * 9)

    output_components.append(f"Completed in {int(execution_time)} seconds.")  # execution info

    return output_components

def update_output(*args):
    return [gr.update(value=arg, visible=arg is not None) for arg in args]

def use_example():
    return "examples/Scenes.From.A.Marriage.US.mp4"

with gr.Blocks() as iface:
    gr.Markdown("# AI Personality Detection")
    
    with gr.Row():
        with gr.Column(scale=3):
            gr.Markdown("Upload a video")
            video_input = gr.Video(label="Upload Video")
            analyze_button = gr.Button("Analyze")
        with gr.Column(scale=1):
            gr.Markdown("Example Video")
            example_video = gr.Video("examples/Scenes.From.A.Marriage.US.mp4", label="Example Video")
            use_example_button = gr.Button("Use Example Video")

    # Create output components
    output_components = []

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

    # In the interface definition
    speaker_tabs = []
    for i in range(3):
        with gr.Tab(f"Speaker {i+1}", visible=False) as tab:
            speaker_tabs.append(tab)
            with gr.Row():
                output_components.extend([
                    gr.Markdown(visible=False),
                    gr.Textbox(label="General Impression", visible=False),
                    gr.Plot(visible=False),
                    gr.Plot(visible=False),
                    gr.Textbox(label="Attachment Styles Explanation", 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],
        outputs=output_components + speaker_tabs,  # Add speaker_tabs to the outputs
        show_progress=True
    )

    use_example_button.click(
        fn=use_example,
        inputs=[],
        outputs=[video_input],
    ).then(fn=analyze_video,
    inputs=[video_input],
    outputs=output_components + speaker_tabs,  # Add speaker_tabs to the outputs
    show_progress=True
    )

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