File size: 9,539 Bytes
1a7ee60 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 | """
FastAPI Server for IDP System
Provides REST API endpoints for Hugging Face Spaces deployment
CORS-enabled for Next.js frontend integration
"""
# Fix for TensorFlow/PaddlePaddle mutex warnings on macOS
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
os.environ['OMP_NUM_THREADS'] = '1'
os.environ['OPENBLAS_NUM_THREADS'] = '1'
os.environ['MKL_NUM_THREADS'] = '1'
os.environ['VECLIB_MAXIMUM_THREADS'] = '1'
os.environ['NUMEXPR_NUM_THREADS'] = '1'
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import warnings
warnings.filterwarnings('ignore')
from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse
import uvicorn
import logging
from typing import Optional
import tempfile
from pathlib import Path
import traceback
from inference_pipeline import IDPPipeline
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)
# Initialize FastAPI app
app = FastAPI(
title="IDP API",
description="Intelligent Document Processing API for invoices, receipts, and forms",
version="1.0.0"
)
# Configure CORS for Next.js frontend
app.add_middleware(
CORSMiddleware,
allow_origins=[
"*", # Allow all origins (for development)
# For production, specify your Vercel domain:
# "https://your-app.vercel.app",
# "https://*.vercel.app",
],
allow_credentials=True,
allow_methods=["*"], # Allow all HTTP methods
allow_headers=["*"], # Allow all headers
)
# Global pipeline instance (loaded once at startup)
pipeline: Optional[IDPPipeline] = None
@app.on_event("startup")
async def startup_event():
"""Initialize pipeline on server startup"""
global pipeline
logger.info("Starting IDP API server...")
logger.info("Initializing inference pipeline...")
try:
# Initialize with CPU by default (change use_gpu=True if GPU available)
pipeline = IDPPipeline(
classifier_model_path="models/classifier/best_classifier.pt",
ner_model_path="models/ner/best_ner.pt",
use_gpu=False, # Set to True if deploying on GPU
ocr_confidence_threshold=0.5
)
logger.info("Pipeline initialized successfully!")
except Exception as e:
logger.error(f"Failed to initialize pipeline: {str(e)}")
logger.error(traceback.format_exc())
# Continue startup anyway to allow health check
@app.on_event("shutdown")
async def shutdown_event():
"""Cleanup on server shutdown"""
logger.info("Shutting down IDP API server...")
@app.get("/")
async def root():
"""Root endpoint"""
return {
"message": "IDP API is running",
"version": "1.0.0",
"endpoints": {
"health_check": "GET /health",
"process_document": "POST /process",
}
}
@app.get("/health")
async def health_check():
"""
Health check endpoint
Returns status and model loading state
Next.js usage:
```javascript
const response = await fetch('https://your-space.hf.space/health');
const data = await response.json();
console.log(data.status); // "ok"
```
"""
models_loaded = pipeline is not None
return {
"status": "ok",
"models_loaded": models_loaded,
"version": "1.0.0"
}
@app.post("/process")
async def process_document(
file: UploadFile = File(...),
adaptive_threshold: bool = False,
page_number: Optional[int] = None
):
"""
Process a document (PDF or image) and extract structured data
Args:
file: Uploaded file (PDF, PNG, JPEG, JPG)
adaptive_threshold: Apply adaptive thresholding for poor quality scans
page_number: For PDFs, process specific page (None = all pages)
Returns:
JSON response with extracted document fields
Next.js usage:
```javascript
const formData = new FormData();
formData.append('file', fileBlob); // File from input element
const response = await fetch('https://your-space.hf.space/process', {
method: 'POST',
body: formData,
});
const result = await response.json();
console.log(result.pages[0].document_type); // "INVOICE", "RECEIPT", etc.
console.log(result.pages[0].fields); // Extracted fields
```
Response format:
```json
{
"file_type": "image" | "pdf",
"total_pages": 1,
"processed_pages": 1,
"pages": [
{
"document_type": "INVOICE",
"classification_confidence": 0.96,
"fields": {
"invoice_number": {
"value": "INV-12345",
"confidence": 0.92,
"bbox": [x1, y1, x2, y2],
"source": "ner"
},
"date": {
"value": "2025-11-28",
"confidence": 0.88,
...
},
...
},
"processing_time": {
"total": 1.23,
...
}
}
]
}
```
"""
# Check if pipeline is loaded
if pipeline is None:
logger.error("Pipeline not initialized")
raise HTTPException(
status_code=503,
detail="Service unavailable: Pipeline not initialized"
)
# Validate file type
allowed_extensions = {'.pdf', '.png', '.jpg', '.jpeg', '.bmp', '.tiff'}
file_ext = Path(file.filename).suffix.lower()
if file_ext not in allowed_extensions:
raise HTTPException(
status_code=400,
detail=f"Unsupported file type: {file_ext}. Allowed: {allowed_extensions}"
)
# Check file size (limit to 10MB)
max_size = 10 * 1024 * 1024 # 10 MB
file_size = 0
# Save uploaded file to temporary location
try:
with tempfile.NamedTemporaryFile(delete=False, suffix=file_ext) as tmp:
# Read and write in chunks to check size
while True:
chunk = await file.read(1024 * 1024) # Read 1MB at a time
if not chunk:
break
file_size += len(chunk)
if file_size > max_size:
os.remove(tmp.name)
raise HTTPException(
status_code=413,
detail=f"File too large: {file_size / (1024*1024):.2f}MB. Max: 10MB"
)
tmp.write(chunk)
tmp_path = tmp.name
logger.info(f"Processing file: {file.filename} ({file_size / 1024:.2f}KB)")
# Process document
result = pipeline.process_document(
file_path=tmp_path,
adaptive_threshold=adaptive_threshold,
page_number=page_number
)
# Add filename to response
result['filename'] = file.filename
result['file_size_kb'] = file_size / 1024
logger.info(f"Successfully processed {file.filename}")
return JSONResponse(content=result)
except HTTPException:
# Re-raise HTTP exceptions
raise
except Exception as e:
logger.error(f"Error processing document: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(
status_code=500,
detail=f"Error processing document: {str(e)}"
)
finally:
# Clean up temporary file
if 'tmp_path' in locals() and os.path.exists(tmp_path):
try:
os.remove(tmp_path)
except:
pass
@app.post("/process/batch")
async def process_batch(
files: list[UploadFile] = File(...)
):
"""
Process multiple documents in batch
Args:
files: List of uploaded files
Returns:
JSON response with results for each file
Note: For large batches, consider using the single /process endpoint
in parallel from the client side for better control
"""
if len(files) > 5:
raise HTTPException(
status_code=400,
detail="Maximum 5 files per batch request"
)
results = []
for file in files:
try:
result = await process_document(file)
results.append({
"filename": file.filename,
"status": "success",
"data": result
})
except Exception as e:
logger.error(f"Error processing {file.filename}: {str(e)}")
results.append({
"filename": file.filename,
"status": "error",
"error": str(e)
})
return JSONResponse(content={"results": results})
if __name__ == "__main__":
# Run server
# For development:
uvicorn.run(
app,
host="0.0.0.0",
port=7860, # Default Hugging Face Spaces port
log_level="info"
)
# For production on Hugging Face Spaces, Dockerfile will handle this
|