feat: implement PDF/image preprocessing, post-processing, and dots.ocr integration prep

G.2.3 - PDF/Image Support:
- Add preprocessing.py with PDF→images conversion (pdf2image)
- Add image loading and normalization
- Add file type detection and validation
- Support for PDF, PNG, JPEG, WebP, TIFF

G.2.4 - Pre/Post-processing:
- Add postprocessing.py with structured output builders
- build_chunks() - semantic chunks for RAG
- build_qa_pairs() - Q&A extraction
- build_markdown() - Markdown conversion
- Text normalization and chunking logic

G.1.3 - dots.ocr Integration Prep:
- Update model_loader.py with proper error handling
- Add USE_DUMMY_PARSER and ALLOW_DUMMY_FALLBACK flags
- Update inference.py to work with images list
- Add parse_document_from_images() function
- Ready for actual model integration

Configuration:
- Add PDF_DPI, IMAGE_MAX_SIZE, PAGE_RANGE settings
- Add parser mode flags (USE_DUMMY_PARSER, ALLOW_DUMMY_FALLBACK)

API Updates:
- Update endpoints to use new preprocessing pipeline
- Integrate post-processing for all output modes
- Remove temp file handling (work directly with bytes)
This commit is contained in:
Apple
2025-11-15 13:19:07 -08:00
parent 0f6cfe046f
commit 4befecc425
6 changed files with 762 additions and 122 deletions

View File

@@ -3,7 +3,7 @@ Configuration for PARSER Service
"""
import os
from typing import Literal
from typing import Literal, Optional
from pydantic_settings import BaseSettings
@@ -25,6 +25,17 @@ class Settings(BaseSettings):
MAX_FILE_SIZE_MB: int = int(os.getenv("MAX_FILE_SIZE_MB", "50"))
TEMP_DIR: str = os.getenv("TEMP_DIR", "/tmp/parser")
# PDF processing
PDF_DPI: int = int(os.getenv("PDF_DPI", "200"))
PAGE_RANGE: Optional[str] = os.getenv("PAGE_RANGE", None) # e.g., "1-20" for pages 1-20
# Image processing
IMAGE_MAX_SIZE: int = int(os.getenv("IMAGE_MAX_SIZE", "2048")) # Max size for longest side
# Parser mode
USE_DUMMY_PARSER: bool = os.getenv("USE_DUMMY_PARSER", "false").lower() == "true"
ALLOW_DUMMY_FALLBACK: bool = os.getenv("ALLOW_DUMMY_FALLBACK", "true").lower() == "true"
# Runtime
RUNTIME_TYPE: Literal["local", "remote"] = os.getenv("RUNTIME_TYPE", "local")
RUNTIME_URL: str = os.getenv("RUNTIME_URL", "http://parser-runtime:11435")