4af6b5b231
Extract bounding boxes from chunk doc_items provenance in the chunker, propagate through domain/service/API layers, and render highlighted bboxes on canvas when hovering a chunk card. Reset highlights on mode and page changes to prevent stale visual state.
126 lines
3.5 KiB
Python
126 lines
3.5 KiB
Python
"""Pydantic schemas — API request/response DTOs.
|
|
|
|
All responses use camelCase serialization to match the existing frontend contract
|
|
(originally served by the Spring Boot backend).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import datetime
|
|
|
|
from pydantic import BaseModel, ConfigDict, field_validator
|
|
|
|
|
|
def _to_camel(name: str) -> str:
|
|
parts = name.split("_")
|
|
return parts[0] + "".join(w.capitalize() for w in parts[1:])
|
|
|
|
|
|
class _CamelModel(BaseModel):
|
|
"""Base model that serializes field names to camelCase."""
|
|
|
|
model_config = ConfigDict(
|
|
alias_generator=_to_camel,
|
|
populate_by_name=True,
|
|
serialize_by_alias=True,
|
|
)
|
|
|
|
|
|
class DocumentResponse(_CamelModel):
|
|
id: str
|
|
filename: str
|
|
content_type: str | None = None
|
|
file_size: int | None = None
|
|
page_count: int | None = None
|
|
created_at: str | datetime
|
|
|
|
|
|
class AnalysisResponse(_CamelModel):
|
|
id: str
|
|
document_id: str = ""
|
|
document_filename: str | None = None
|
|
status: str
|
|
content_markdown: str | None = None
|
|
content_html: str | None = None
|
|
pages_json: str | None = None
|
|
chunks_json: str | None = None
|
|
has_document_json: bool = False
|
|
error_message: str | None = None
|
|
started_at: str | datetime | None = None
|
|
completed_at: str | datetime | None = None
|
|
created_at: str | datetime
|
|
|
|
|
|
class PipelineOptionsRequest(BaseModel):
|
|
"""Docling pipeline configuration options."""
|
|
|
|
do_ocr: bool = True
|
|
do_table_structure: bool = True
|
|
table_mode: str = "accurate" # "accurate" or "fast"
|
|
do_code_enrichment: bool = False
|
|
do_formula_enrichment: bool = False
|
|
do_picture_classification: bool = False
|
|
do_picture_description: bool = False
|
|
generate_picture_images: bool = False
|
|
generate_page_images: bool = False
|
|
images_scale: float = 1.0
|
|
|
|
@field_validator("table_mode")
|
|
@classmethod
|
|
def validate_table_mode(cls, v: str) -> str:
|
|
if v not in ("accurate", "fast"):
|
|
raise ValueError('table_mode must be "accurate" or "fast"')
|
|
return v
|
|
|
|
@field_validator("images_scale")
|
|
@classmethod
|
|
def validate_images_scale(cls, v: float) -> float:
|
|
if v <= 0 or v > 10:
|
|
raise ValueError("images_scale must be between 0 (exclusive) and 10")
|
|
return v
|
|
|
|
|
|
class ChunkingOptionsRequest(BaseModel):
|
|
"""Docling chunking configuration options."""
|
|
|
|
chunker_type: str = "hybrid" # "hybrid", "hierarchical"
|
|
max_tokens: int = 512
|
|
merge_peers: bool = True
|
|
repeat_table_header: bool = True
|
|
|
|
@field_validator("chunker_type")
|
|
@classmethod
|
|
def validate_chunker_type(cls, v: str) -> str:
|
|
if v not in ("hybrid", "hierarchical"):
|
|
raise ValueError('chunker_type must be "hybrid" or "hierarchical"')
|
|
return v
|
|
|
|
@field_validator("max_tokens")
|
|
@classmethod
|
|
def validate_max_tokens(cls, v: int) -> int:
|
|
if v < 64 or v > 8192:
|
|
raise ValueError("max_tokens must be between 64 and 8192")
|
|
return v
|
|
|
|
|
|
class ChunkBboxResponse(_CamelModel):
|
|
page: int
|
|
bbox: list[float]
|
|
|
|
|
|
class ChunkResponse(_CamelModel):
|
|
text: str
|
|
headings: list[str] = []
|
|
source_page: int | None = None
|
|
token_count: int = 0
|
|
bboxes: list[ChunkBboxResponse] = []
|
|
|
|
|
|
class CreateAnalysisRequest(BaseModel):
|
|
documentId: str # camelCase to match existing frontend contract
|
|
pipelineOptions: PipelineOptionsRequest | None = None
|
|
chunkingOptions: ChunkingOptionsRequest | None = None
|
|
|
|
|
|
class RechunkRequest(BaseModel):
|
|
chunkingOptions: ChunkingOptionsRequest
|