940a406dce
Backup commit before executing remove-unused-code proposal. This includes all pending changes and new features. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
9.1 KiB
9.1 KiB
Design: OCR Processing Presets
Architecture Overview
┌─────────────────────────────────────────────────────────────────┐
│ Frontend │
├─────────────────────────────────────────────────────────────────┤
│ ┌──────────────────┐ ┌──────────────────────────────────┐ │
│ │ Preset Selector │───▶│ Advanced Parameter Panel │ │
│ │ (Simple Mode) │ │ (Expert Mode) │ │
│ └──────────────────┘ └──────────────────────────────────┘ │
│ │ │ │
│ └───────────┬───────────────┘ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ OCR Config JSON │ │
│ └─────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
│
▼ POST /api/v2/tasks
┌─────────────────────────────────────────────────────────────────┐
│ Backend │
├─────────────────────────────────────────────────────────────────┤
│ ┌──────────────────┐ ┌──────────────────────────────────┐ │
│ │ Preset Resolver │───▶│ OCR Config Validator │ │
│ └──────────────────┘ └──────────────────────────────────┘ │
│ │ │ │
│ └───────────┬───────────────┘ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ OCRService │ │
│ │ (with config) │ │
│ └─────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ PPStructureV3 │ │
│ │ (configured) │ │
│ └─────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
Data Models
OCRPreset Enum
class OCRPreset(str, Enum):
TEXT_HEAVY = "text_heavy" # Reports, articles, manuals
DATASHEET = "datasheet" # Technical datasheets, TDS
TABLE_HEAVY = "table_heavy" # Financial reports, spreadsheets
FORM = "form" # Applications, surveys
MIXED = "mixed" # General documents
CUSTOM = "custom" # User-defined settings
OCRConfig Model
class OCRConfig(BaseModel):
# Table Processing
table_parsing_mode: Literal["full", "conservative", "classification_only", "disabled"] = "conservative"
table_layout_threshold: float = Field(default=0.65, ge=0.0, le=1.0)
enable_wired_table: bool = True
enable_wireless_table: bool = False # Disabled by default (aggressive)
# Layout Detection
layout_detection_model: Optional[str] = "PP-DocLayout_plus-L"
layout_threshold: Optional[float] = Field(default=None, ge=0.0, le=1.0)
layout_nms_threshold: Optional[float] = Field(default=None, ge=0.0, le=1.0)
layout_merge_mode: Optional[Literal["large", "small", "union"]] = "union"
# Preprocessing
use_doc_orientation_classify: bool = True
use_doc_unwarping: bool = False # Causes distortion
use_textline_orientation: bool = True
# Recognition Modules
enable_chart_recognition: bool = True
enable_formula_recognition: bool = True
enable_seal_recognition: bool = False
enable_region_detection: bool = True
Preset Definitions
PRESET_CONFIGS: Dict[OCRPreset, OCRConfig] = {
OCRPreset.TEXT_HEAVY: OCRConfig(
table_parsing_mode="disabled",
table_layout_threshold=0.7,
enable_wired_table=False,
enable_wireless_table=False,
enable_chart_recognition=False,
enable_formula_recognition=False,
),
OCRPreset.DATASHEET: OCRConfig(
table_parsing_mode="conservative",
table_layout_threshold=0.65,
enable_wired_table=True,
enable_wireless_table=False, # Key: disable aggressive wireless
),
OCRPreset.TABLE_HEAVY: OCRConfig(
table_parsing_mode="full",
table_layout_threshold=0.5,
enable_wired_table=True,
enable_wireless_table=True,
),
OCRPreset.FORM: OCRConfig(
table_parsing_mode="conservative",
table_layout_threshold=0.6,
enable_wired_table=True,
enable_wireless_table=False,
),
OCRPreset.MIXED: OCRConfig(
table_parsing_mode="classification_only",
table_layout_threshold=0.55,
),
}
API Design
Task Creation with OCR Config
POST /api/v2/tasks
Content-Type: multipart/form-data
file: <binary>
processing_track: "ocr"
ocr_preset: "datasheet" # Optional: use preset
ocr_config: { # Optional: override specific params
"table_layout_threshold": 0.7
}
Get Available Presets
GET /api/v2/ocr/presets
Response:
{
"presets": [
{
"name": "datasheet",
"display_name": "Technical Datasheet",
"description": "Optimized for product specifications and technical documents",
"icon": "description",
"config": { ... }
},
...
]
}
Frontend Components
PresetSelector Component
interface PresetSelectorProps {
value: OCRPreset;
onChange: (preset: OCRPreset) => void;
showAdvanced: boolean;
onToggleAdvanced: () => void;
}
// Visual preset cards with icons:
// 📄 Text Heavy - Reports & Articles
// 📊 Datasheet - Technical Documents
// 📈 Table Heavy - Financial Reports
// 📝 Form - Applications & Surveys
// 📑 Mixed - General Documents
// ⚙️ Custom - Expert Settings
AdvancedConfigPanel Component
interface AdvancedConfigPanelProps {
config: OCRConfig;
onChange: (config: Partial<OCRConfig>) => void;
preset: OCRPreset; // To show which values differ from preset
}
// Sections:
// - Table Processing (collapsed by default)
// - Layout Detection (collapsed by default)
// - Preprocessing (collapsed by default)
// - Recognition Modules (collapsed by default)
Key Design Decisions
1. Preset as Default, Custom as Exception
Users should start with presets. Only expose advanced panel when:
- User explicitly clicks "Advanced Settings"
- User selects "Custom" preset
- User has previously saved custom settings
2. Conservative Defaults
All presets default to conservative settings:
enable_wireless_table: false(most aggressive, causes cell explosion)table_layout_threshold: 0.6+(reduce false table detection)use_doc_unwarping: false(causes distortion)
3. Config Inheritance
Custom config inherits from preset, only specified fields override:
final_config = PRESET_CONFIGS[preset].copy()
final_config.update(custom_overrides)
4. No Patch Behaviors
All post-processing patches are disabled by default:
cell_validation_enabled: falsegap_filling_enabled: falsetable_content_rebuilder_enabled: false
Focus on getting PP-Structure output right with proper configuration.