File size: 10,969 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 |
"""
Document Processing CLI Commands
Commands:
sparknet document parse <file> - Parse and extract text from document
sparknet document extract <file> - Extract structured fields
sparknet document classify <file> - Classify document type
sparknet document analyze <file> - Full document analysis
"""
import typer
from typing import Optional, List
from pathlib import Path
import json
import sys
# Create document sub-app
document_app = typer.Typer(
name="document",
help="Document processing commands",
)
@document_app.command("parse")
def parse_document(
file_path: Path = typer.Argument(..., help="Path to document file"),
output: Optional[Path] = typer.Option(None, "--output", "-o", help="Output JSON file"),
ocr_engine: str = typer.Option("paddleocr", "--ocr", help="OCR engine: paddleocr, tesseract"),
dpi: int = typer.Option(300, "--dpi", help="Rendering DPI for PDFs"),
max_pages: Optional[int] = typer.Option(None, "--max-pages", help="Maximum pages to process"),
include_images: bool = typer.Option(False, "--images", help="Include cropped region images"),
):
"""
Parse a document and extract text with layout information.
Example:
sparknet document parse invoice.pdf -o result.json
"""
from loguru import logger
if not file_path.exists():
typer.echo(f"Error: File not found: {file_path}", err=True)
raise typer.Exit(1)
typer.echo(f"Parsing document: {file_path}")
try:
from ..document.pipeline import (
PipelineConfig,
get_document_processor,
)
from ..document.ocr import OCRConfig
# Build config
ocr_config = OCRConfig(engine=ocr_engine)
config = PipelineConfig(
ocr=ocr_config,
render_dpi=dpi,
max_pages=max_pages,
)
# Process document
processor = get_document_processor(config)
result = processor.process(str(file_path))
# Format output
output_data = {
"document_id": result.metadata.document_id,
"filename": result.metadata.filename,
"num_pages": result.metadata.num_pages,
"total_chunks": result.metadata.total_chunks,
"total_characters": result.metadata.total_characters,
"ocr_confidence": result.metadata.ocr_confidence_avg,
"chunks": [
{
"chunk_id": c.chunk_id,
"type": c.chunk_type.value,
"page": c.page,
"text": c.text[:500] + "..." if len(c.text) > 500 else c.text,
"confidence": c.confidence,
"bbox": {
"x_min": c.bbox.x_min,
"y_min": c.bbox.y_min,
"x_max": c.bbox.x_max,
"y_max": c.bbox.y_max,
},
}
for c in result.chunks
],
"full_text": result.full_text[:2000] + "..." if len(result.full_text) > 2000 else result.full_text,
}
# Output
if output:
with open(output, "w") as f:
json.dump(output_data, f, indent=2)
typer.echo(f"Results written to: {output}")
else:
typer.echo(json.dumps(output_data, indent=2))
typer.echo(f"\nProcessed {result.metadata.num_pages} pages, {len(result.chunks)} chunks")
except ImportError as e:
typer.echo(f"Error: Missing dependency - {e}", err=True)
raise typer.Exit(1)
except Exception as e:
typer.echo(f"Error processing document: {e}", err=True)
raise typer.Exit(1)
@document_app.command("extract")
def extract_fields(
file_path: Path = typer.Argument(..., help="Path to document file"),
schema: Optional[Path] = typer.Option(None, "--schema", "-s", help="Extraction schema YAML file"),
fields: Optional[List[str]] = typer.Option(None, "--field", "-f", help="Fields to extract (can use multiple)"),
output: Optional[Path] = typer.Option(None, "--output", "-o", help="Output JSON file"),
validate: bool = typer.Option(True, "--validate/--no-validate", help="Validate extraction"),
):
"""
Extract structured fields from a document.
Example:
sparknet document extract invoice.pdf -f "invoice_number" -f "total_amount"
sparknet document extract contract.pdf --schema contract_schema.yaml
"""
from loguru import logger
if not file_path.exists():
typer.echo(f"Error: File not found: {file_path}", err=True)
raise typer.Exit(1)
if not schema and not fields:
typer.echo("Error: Provide --schema or --field options", err=True)
raise typer.Exit(1)
typer.echo(f"Extracting fields from: {file_path}")
try:
from ..document.schemas.extraction import ExtractionSchema, FieldDefinition
from ..agents.document_agent import DocumentAgent
# Build extraction schema
if schema:
import yaml
with open(schema) as f:
schema_data = yaml.safe_load(f)
extraction_schema = ExtractionSchema(**schema_data)
else:
# Build from field names
field_defs = [
FieldDefinition(
name=f,
field_type="string",
required=True,
)
for f in fields
]
extraction_schema = ExtractionSchema(
name="cli_extraction",
fields=field_defs,
)
# Run extraction with agent
import asyncio
agent = DocumentAgent()
asyncio.run(agent.load_document(str(file_path)))
result = asyncio.run(agent.extract_fields(extraction_schema))
# Format output
output_data = {
"document": str(file_path),
"fields": result.fields,
"confidence": result.confidence,
"evidence": [
{
"chunk_id": e.chunk_id,
"page": e.page,
"snippet": e.snippet,
}
for e in result.evidence
] if result.evidence else [],
}
# Validate if requested
if validate and result.fields:
from ..document.validation import get_extraction_critic
critic = get_extraction_critic()
evidence_chunks = [
{"text": e.snippet, "page": e.page, "chunk_id": e.chunk_id}
for e in result.evidence
] if result.evidence else []
validation = critic.validate_extraction(result.fields, evidence_chunks)
output_data["validation"] = {
"status": validation.overall_status.value,
"confidence": validation.overall_confidence,
"should_accept": validation.should_accept,
"abstain_reason": validation.abstain_reason,
}
# Output
if output:
with open(output, "w") as f:
json.dump(output_data, f, indent=2)
typer.echo(f"Results written to: {output}")
else:
typer.echo(json.dumps(output_data, indent=2))
except ImportError as e:
typer.echo(f"Error: Missing dependency - {e}", err=True)
raise typer.Exit(1)
except Exception as e:
typer.echo(f"Error extracting fields: {e}", err=True)
raise typer.Exit(1)
@document_app.command("classify")
def classify_document(
file_path: Path = typer.Argument(..., help="Path to document file"),
output: Optional[Path] = typer.Option(None, "--output", "-o", help="Output JSON file"),
):
"""
Classify document type.
Example:
sparknet document classify document.pdf
"""
from loguru import logger
if not file_path.exists():
typer.echo(f"Error: File not found: {file_path}", err=True)
raise typer.Exit(1)
typer.echo(f"Classifying document: {file_path}")
try:
from ..agents.document_agent import DocumentAgent
import asyncio
agent = DocumentAgent()
asyncio.run(agent.load_document(str(file_path)))
classification = asyncio.run(agent.classify())
output_data = {
"document": str(file_path),
"document_type": classification.document_type.value,
"confidence": classification.confidence,
"reasoning": classification.reasoning,
"metadata": classification.metadata,
}
if output:
with open(output, "w") as f:
json.dump(output_data, f, indent=2)
typer.echo(f"Results written to: {output}")
else:
typer.echo(json.dumps(output_data, indent=2))
except Exception as e:
typer.echo(f"Error classifying document: {e}", err=True)
raise typer.Exit(1)
@document_app.command("ask")
def ask_document(
file_path: Path = typer.Argument(..., help="Path to document file"),
question: str = typer.Argument(..., help="Question to ask about the document"),
output: Optional[Path] = typer.Option(None, "--output", "-o", help="Output JSON file"),
):
"""
Ask a question about a document.
Example:
sparknet document ask invoice.pdf "What is the total amount?"
"""
from loguru import logger
if not file_path.exists():
typer.echo(f"Error: File not found: {file_path}", err=True)
raise typer.Exit(1)
typer.echo(f"Processing question for: {file_path}")
try:
from ..agents.document_agent import DocumentAgent
import asyncio
agent = DocumentAgent()
asyncio.run(agent.load_document(str(file_path)))
answer, evidence = asyncio.run(agent.answer_question(question))
output_data = {
"document": str(file_path),
"question": question,
"answer": answer,
"evidence": [
{
"chunk_id": e.chunk_id,
"page": e.page,
"snippet": e.snippet,
"confidence": e.confidence,
}
for e in evidence
] if evidence else [],
}
if output:
with open(output, "w") as f:
json.dump(output_data, f, indent=2)
typer.echo(f"Results written to: {output}")
else:
typer.echo(f"\nQuestion: {question}")
typer.echo(f"\nAnswer: {answer}")
if evidence:
typer.echo(f"\nEvidence ({len(evidence)} sources):")
for e in evidence[:3]:
typer.echo(f" - Page {e.page + 1}: {e.snippet[:100]}...")
except Exception as e:
typer.echo(f"Error processing question: {e}", err=True)
raise typer.Exit(1)
|