File size: 2,817 Bytes
d520909 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
"""
SPARKNET CLI Main Entry Point
Usage:
sparknet document parse <file>
sparknet document extract <file> --schema <schema.yaml>
sparknet rag index <file>
sparknet rag ask <question>
"""
import typer
from typing import Optional
from pathlib import Path
import json
import sys
from .document import document_app
from .rag import rag_app
# Create main app
app = typer.Typer(
name="sparknet",
help="SPARKNET Document Intelligence CLI",
add_completion=False,
)
# Register sub-commands
app.add_typer(document_app, name="document", help="Document processing commands")
app.add_typer(rag_app, name="rag", help="RAG and retrieval commands")
@app.command()
def version():
"""Show SPARKNET version."""
typer.echo("SPARKNET Document Intelligence v0.1.0")
@app.command()
def info():
"""Show system information and configuration."""
from loguru import logger
import platform
typer.echo("SPARKNET Document Intelligence")
typer.echo("=" * 40)
typer.echo(f"Python: {platform.python_version()}")
typer.echo(f"Platform: {platform.system()} {platform.release()}")
typer.echo()
# Check component availability
typer.echo("Components:")
# OCR
try:
from paddleocr import PaddleOCR
typer.echo(" [✓] PaddleOCR")
except ImportError:
typer.echo(" [✗] PaddleOCR (install with: pip install paddleocr)")
try:
import pytesseract
typer.echo(" [✓] Tesseract")
except ImportError:
typer.echo(" [✗] Tesseract (install with: pip install pytesseract)")
# Vector Store
try:
import chromadb
typer.echo(" [✓] ChromaDB")
except ImportError:
typer.echo(" [✗] ChromaDB (install with: pip install chromadb)")
# Ollama
try:
import httpx
with httpx.Client(timeout=2.0) as client:
resp = client.get("http://localhost:11434/api/tags")
if resp.status_code == 200:
models = resp.json().get("models", [])
typer.echo(f" [✓] Ollama ({len(models)} models)")
else:
typer.echo(" [✗] Ollama (not responding)")
except Exception:
typer.echo(" [✗] Ollama (not running)")
@app.callback()
def main_callback(
verbose: bool = typer.Option(False, "--verbose", "-v", help="Enable verbose output"),
quiet: bool = typer.Option(False, "--quiet", "-q", help="Suppress output"),
):
"""SPARKNET Document Intelligence CLI."""
from loguru import logger
import sys
# Configure logging
logger.remove()
if verbose:
logger.add(sys.stderr, level="DEBUG")
elif not quiet:
logger.add(sys.stderr, level="INFO")
def main():
"""Main entry point."""
app()
if __name__ == "__main__":
main()
|