Full implementation - Vision AI, config, improved pipeline
Major changes: - vision_analyzer.py: Real OpenAI/Anthropic vision API integration - Component detection with confidence scores - Atomizer hints extraction (objectives, constraints, parameters) - Material and feature identification - Timeline correlation with transcript - config.py: Full configuration system - API settings (provider, keys, models) - Processing settings (Whisper model, frame interval, scene detection) - Output settings (BOM, hints, PDF template) - Config file support (~/.cad-documenter.toml) - audio_analyzer.py: Enhanced transcription - Audio stream detection - Graceful fallback for missing audio - Keyword extraction - Technical term detection - Timeline correlation - video_processor.py: Smart frame extraction - Scene change detection via ffmpeg - Configurable thresholds - Best frame selection - doc_generator.py: Improved output - Better Markdown templates - BOM CSV export - Atomizer hints JSON - Component cards - cli.py: Rich CLI with progress indicators - Config file support - --init-config flag - Verbose mode - Better error messages - tests: Comprehensive test suite
This commit is contained in:
Mario Lavoie
@@ -1,14 +1,28 @@
|
||||
"""CAD-Documenter CLI - Main entry point."""
|
||||
|
||||
import click
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from rich.console import Console
|
||||
|
||||
import click
|
||||
from rich.console import Console
|
||||
from rich.progress import Progress, SpinnerColumn, TextColumn
|
||||
from rich.panel import Panel
|
||||
|
||||
from .config import load_config, create_default_config
|
||||
from .pipeline import DocumentationPipeline
|
||||
|
||||
console = Console()
|
||||
|
||||
|
||||
def print_banner():
|
||||
"""Print welcome banner."""
|
||||
console.print(Panel.fit(
|
||||
"[bold blue]CAD-Documenter[/bold blue] v0.1.0\n"
|
||||
"[dim]Video walkthrough → Engineering documentation[/dim]",
|
||||
border_style="blue"
|
||||
))
|
||||
|
||||
|
||||
@click.command()
|
||||
@click.argument("video", type=click.Path(exists=True, path_type=Path))
|
||||
@click.option("-o", "--output", type=click.Path(path_type=Path), help="Output directory")
|
||||
@@ -16,8 +30,12 @@ console = Console()
|
||||
@click.option("--atomizer-hints", is_flag=True, help="Generate Atomizer FEA hints")
|
||||
@click.option("--bom", is_flag=True, help="Generate Bill of Materials")
|
||||
@click.option("--pdf", is_flag=True, help="Generate PDF via Atomaste Report Standard")
|
||||
@click.option("--frame-interval", default=2.0, help="Seconds between frame extractions")
|
||||
@click.option("--whisper-model", default="base", help="Whisper model size (tiny/base/small/medium/large)")
|
||||
@click.option("--frame-interval", type=float, help="Seconds between frame extractions")
|
||||
@click.option("--whisper-model", type=click.Choice(["tiny", "base", "small", "medium", "large"]), help="Whisper model size")
|
||||
@click.option("--api-provider", type=click.Choice(["openai", "anthropic"]), help="Vision API provider")
|
||||
@click.option("--config", "config_path", type=click.Path(exists=True, path_type=Path), help="Config file path")
|
||||
@click.option("--init-config", is_flag=True, help="Create default config file and exit")
|
||||
@click.option("-v", "--verbose", is_flag=True, help="Verbose output")
|
||||
@click.version_option()
|
||||
def main(
|
||||
video: Path,
|
||||
@@ -26,60 +44,169 @@ def main(
|
||||
atomizer_hints: bool,
|
||||
bom: bool,
|
||||
pdf: bool,
|
||||
frame_interval: float,
|
||||
whisper_model: str,
|
||||
frame_interval: float | None,
|
||||
whisper_model: str | None,
|
||||
api_provider: str | None,
|
||||
config_path: Path | None,
|
||||
init_config: bool,
|
||||
verbose: bool,
|
||||
):
|
||||
"""
|
||||
Generate engineering documentation from a CAD walkthrough video.
|
||||
|
||||
VIDEO: Path to the video file (.mp4, .mov, .avi, etc.)
|
||||
"""
|
||||
console.print(f"[bold blue]CAD-Documenter[/bold blue] v0.1.0")
|
||||
console.print(f"Processing: [cyan]{video}[/cyan]")
|
||||
|
||||
Examples:
|
||||
|
||||
cad-doc walkthrough.mp4
|
||||
|
||||
cad-doc video.mp4 --output ./docs --bom --atomizer-hints
|
||||
|
||||
cad-doc video.mp4 --pdf --whisper-model medium
|
||||
"""
|
||||
print_banner()
|
||||
|
||||
# Handle --init-config
|
||||
if init_config:
|
||||
default_path = Path.home() / ".cad-documenter.toml"
|
||||
create_default_config(default_path)
|
||||
console.print(f"[green]✓[/green] Created config file: {default_path}")
|
||||
console.print("[dim]Edit this file to configure API keys and defaults.[/dim]")
|
||||
return
|
||||
|
||||
# Load configuration
|
||||
config = load_config(config_path)
|
||||
|
||||
# Override config with CLI options
|
||||
if frame_interval is not None:
|
||||
config.processing.frame_interval = frame_interval
|
||||
if whisper_model is not None:
|
||||
config.processing.whisper_model = whisper_model
|
||||
if api_provider is not None:
|
||||
config.api.provider = api_provider
|
||||
|
||||
# Check API key
|
||||
if not frames_only and not config.api.api_key:
|
||||
provider = config.api.provider.upper()
|
||||
console.print(f"[red]Error:[/red] No API key found for {config.api.provider}.")
|
||||
console.print(f"Set [cyan]{provider}_API_KEY[/cyan] environment variable or add to config file.")
|
||||
console.print(f"\nTo create a config file: [cyan]cad-doc --init-config[/cyan]")
|
||||
sys.exit(1)
|
||||
|
||||
console.print(f"Processing: [cyan]{video.name}[/cyan]")
|
||||
if verbose:
|
||||
console.print(f" API: {config.api.provider} ({config.api.vision_model or 'default'})")
|
||||
console.print(f" Whisper: {config.processing.whisper_model}")
|
||||
|
||||
# Default output directory
|
||||
if output is None:
|
||||
output = video.parent / f"{video.stem}_docs"
|
||||
|
||||
|
||||
output.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Run pipeline
|
||||
pipeline = DocumentationPipeline(
|
||||
video_path=video,
|
||||
output_dir=output,
|
||||
frame_interval=frame_interval,
|
||||
whisper_model=whisper_model,
|
||||
)
|
||||
|
||||
console.print(f"Output: [cyan]{output}[/cyan]")
|
||||
|
||||
# Initialize pipeline
|
||||
try:
|
||||
pipeline = DocumentationPipeline(
|
||||
video_path=video,
|
||||
output_dir=output,
|
||||
config=config,
|
||||
)
|
||||
except ValueError as e:
|
||||
console.print(f"[red]Configuration error:[/red] {e}")
|
||||
sys.exit(1)
|
||||
|
||||
# Frames only mode
|
||||
if frames_only:
|
||||
console.print("[yellow]Extracting frames only...[/yellow]")
|
||||
pipeline.extract_frames()
|
||||
console.print(f"[green]✓[/green] Frames saved to {output / 'frames'}")
|
||||
with Progress(
|
||||
SpinnerColumn(),
|
||||
TextColumn("[progress.description]{task.description}"),
|
||||
console=console,
|
||||
) as progress:
|
||||
progress.add_task("Extracting frames...", total=None)
|
||||
frames = pipeline.extract_frames()
|
||||
|
||||
console.print(f"[green]✓[/green] Extracted {len(frames)} frames to {output / 'frames'}")
|
||||
return
|
||||
|
||||
|
||||
# Full pipeline
|
||||
console.print("[yellow]Step 1/4:[/yellow] Extracting frames...")
|
||||
frames = pipeline.extract_frames()
|
||||
console.print(f" [green]✓[/green] Extracted {len(frames)} frames")
|
||||
|
||||
console.print("[yellow]Step 2/4:[/yellow] Transcribing audio...")
|
||||
transcript = pipeline.transcribe_audio()
|
||||
console.print(f" [green]✓[/green] Transcribed {len(transcript.segments)} segments")
|
||||
|
||||
console.print("[yellow]Step 3/4:[/yellow] Analyzing components...")
|
||||
analysis = pipeline.analyze_components(frames, transcript)
|
||||
console.print(f" [green]✓[/green] Identified {len(analysis.components)} components")
|
||||
|
||||
console.print("[yellow]Step 4/4:[/yellow] Generating documentation...")
|
||||
doc_path = pipeline.generate_documentation(analysis, atomizer_hints=atomizer_hints, bom=bom)
|
||||
console.print(f" [green]✓[/green] Documentation saved to {doc_path}")
|
||||
|
||||
with Progress(
|
||||
SpinnerColumn(),
|
||||
TextColumn("[progress.description]{task.description}"),
|
||||
console=console,
|
||||
) as progress:
|
||||
|
||||
# Step 1: Extract frames
|
||||
task1 = progress.add_task("[cyan]Step 1/4:[/cyan] Extracting frames...", total=None)
|
||||
frames = pipeline.extract_frames()
|
||||
progress.update(task1, description=f"[green]✓[/green] Extracted {len(frames)} frames")
|
||||
progress.remove_task(task1)
|
||||
|
||||
# Step 2: Transcribe
|
||||
task2 = progress.add_task("[cyan]Step 2/4:[/cyan] Transcribing audio...", total=None)
|
||||
transcript = pipeline.transcribe_audio()
|
||||
seg_count = len(transcript.segments) if transcript.segments else 0
|
||||
progress.update(task2, description=f"[green]✓[/green] Transcribed {seg_count} segments")
|
||||
progress.remove_task(task2)
|
||||
|
||||
if verbose and transcript.full_text:
|
||||
console.print(Panel(
|
||||
transcript.full_text[:500] + ("..." if len(transcript.full_text) > 500 else ""),
|
||||
title="Transcript Preview",
|
||||
border_style="dim"
|
||||
))
|
||||
|
||||
# Step 3: Analyze
|
||||
task3 = progress.add_task("[cyan]Step 3/4:[/cyan] Analyzing components...", total=None)
|
||||
analysis = pipeline.analyze_components(frames, transcript)
|
||||
comp_count = len(analysis.components)
|
||||
progress.update(task3, description=f"[green]✓[/green] Identified {comp_count} components")
|
||||
progress.remove_task(task3)
|
||||
|
||||
if verbose and analysis.components:
|
||||
console.print("\n[bold]Components found:[/bold]")
|
||||
for c in analysis.components:
|
||||
console.print(f" • {c.name} ({c.material or 'material unknown'})")
|
||||
|
||||
# Step 4: Generate documentation
|
||||
task4 = progress.add_task("[cyan]Step 4/4:[/cyan] Generating documentation...", total=None)
|
||||
doc_path = pipeline.generate_documentation(
|
||||
analysis,
|
||||
atomizer_hints=atomizer_hints or config.output.include_atomizer_hints,
|
||||
bom=bom or config.output.include_bom,
|
||||
)
|
||||
progress.update(task4, description=f"[green]✓[/green] Documentation generated")
|
||||
progress.remove_task(task4)
|
||||
|
||||
# Generate PDF if requested
|
||||
if pdf:
|
||||
console.print("[yellow]Generating PDF...[/yellow]")
|
||||
pdf_path = pipeline.generate_pdf(doc_path)
|
||||
console.print(f" [green]✓[/green] PDF saved to {pdf_path}")
|
||||
|
||||
console.print(f"\n[bold green]Done![/bold green] Output: {output}")
|
||||
console.print("[cyan]Generating PDF...[/cyan]")
|
||||
try:
|
||||
pdf_path = pipeline.generate_pdf(doc_path)
|
||||
console.print(f"[green]✓[/green] PDF: {pdf_path}")
|
||||
except Exception as e:
|
||||
console.print(f"[yellow]Warning:[/yellow] PDF generation failed: {e}")
|
||||
|
||||
# Summary
|
||||
console.print()
|
||||
console.print(Panel.fit(
|
||||
f"[bold green]Documentation complete![/bold green]\n\n"
|
||||
f"📄 [cyan]{doc_path}[/cyan]\n"
|
||||
f"📊 {len(analysis.components)} components documented\n"
|
||||
f"🖼️ {len(frames)} frames extracted",
|
||||
title="Summary",
|
||||
border_style="green"
|
||||
))
|
||||
|
||||
# Show atomizer hints summary if generated
|
||||
if (atomizer_hints or config.output.include_atomizer_hints) and analysis.atomizer_hints:
|
||||
hints = analysis.atomizer_hints
|
||||
if hints.objectives or hints.constraints:
|
||||
console.print("\n[bold]Atomizer Hints:[/bold]")
|
||||
for obj in hints.objectives[:3]:
|
||||
console.print(f" 🎯 {obj['direction'].capitalize()} {obj['name']}")
|
||||
for constraint in hints.constraints[:3]:
|
||||
console.print(f" 📏 {constraint['type']}: {constraint['value']}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user