852c9013b5
All checks were successful
Deploy to Staging / Build Images (pull_request) Successful in 5m59s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 31s
Deploy to Staging / Verify Staging (pull_request) Successful in 2m19s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 7s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
OCR Service (Python/FastAPI):
- POST /extract for synchronous OCR extraction
- POST /jobs and GET /jobs/{job_id} for async processing
- Image preprocessing (deskew, denoise) for accuracy
- HEIC conversion via pillow-heif
- Redis job queue for async processing
Backend (Fastify):
- POST /api/ocr/extract - authenticated proxy to OCR
- POST /api/ocr/jobs - async job submission
- GET /api/ocr/jobs/:jobId - job polling
- Multipart file upload handling
- JWT authentication required
File size limits: 10MB sync, 200MB async
Processing time target: <3 seconds for typical photos
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
70 lines
2.1 KiB
Python
70 lines
2.1 KiB
Python
"""OCR extraction endpoints."""
|
|
import logging
|
|
|
|
from fastapi import APIRouter, File, HTTPException, Query, UploadFile
|
|
|
|
from app.models import OcrResponse
|
|
from app.services import ocr_service
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(prefix="/extract", tags=["extract"])
|
|
|
|
# Maximum file size for synchronous processing (10MB)
|
|
MAX_SYNC_SIZE = 10 * 1024 * 1024
|
|
|
|
|
|
@router.post("", response_model=OcrResponse)
|
|
async def extract_text(
|
|
file: UploadFile = File(..., description="Image file to process"),
|
|
preprocess: bool = Query(True, description="Apply image preprocessing"),
|
|
) -> OcrResponse:
|
|
"""
|
|
Extract text from an uploaded image using OCR.
|
|
|
|
Supports HEIC, JPEG, PNG, and PDF (first page only) formats.
|
|
Processing time target: <3 seconds for typical photos.
|
|
|
|
- **file**: Image file (max 10MB for sync processing)
|
|
- **preprocess**: Whether to apply deskew/denoise preprocessing (default: true)
|
|
"""
|
|
# Validate file presence
|
|
if not file.filename:
|
|
raise HTTPException(status_code=400, detail="No file provided")
|
|
|
|
# Read file content
|
|
content = await file.read()
|
|
file_size = len(content)
|
|
|
|
# Validate file size
|
|
if file_size > MAX_SYNC_SIZE:
|
|
raise HTTPException(
|
|
status_code=413,
|
|
detail=f"File too large for sync processing. Max: {MAX_SYNC_SIZE // (1024*1024)}MB. Use /jobs for larger files.",
|
|
)
|
|
|
|
if file_size == 0:
|
|
raise HTTPException(status_code=400, detail="Empty file provided")
|
|
|
|
logger.info(
|
|
f"Processing file: {file.filename}, "
|
|
f"size: {file_size} bytes, "
|
|
f"content_type: {file.content_type}"
|
|
)
|
|
|
|
# Perform OCR extraction
|
|
result = ocr_service.extract(
|
|
file_bytes=content,
|
|
content_type=file.content_type,
|
|
preprocess=preprocess,
|
|
)
|
|
|
|
if not result.success:
|
|
logger.warning(f"OCR extraction failed for {file.filename}")
|
|
raise HTTPException(
|
|
status_code=422,
|
|
detail="Failed to extract text from image. Ensure the file is a valid image format.",
|
|
)
|
|
|
|
return result
|