urieljareth/Estacion-de-Documentos
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

OCR de imagenes con Mistral: ImageProcessor (png/jpg/webp/gif/bmp/tiff), modelo mistral-ocr-latest y recuperacion de fuentes unknown

Browse Source
This commit is contained in:
urieljareth
2026-09-13 22:39:39 -06:00
parent 239a7510c6
commit 15cf00cc42
12 changed files with 79 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/services/ingestion_service.py
+14 -3
View File
@@ -6,6 +6,7 @@ from backend.app.managers.knowledge_manager import KnowledgeManager
from backend.app.services.markdown_builder import build_markdown
from backend.app.services.processors.audio_processor import AudioProcessor
from backend.app.services.processors.docx_processor import DocxProcessor
from backend.app.services.processors.image_processor import ImageProcessor
from backend.app.services.processors.pdf_processor import PdfProcessor
from backend.app.services.processors.text_processor import TextProcessor
from backend.app.services.processors.video_processor import VideoProcessor
@@ -19,7 +20,8 @@ class IngestionService:
source = self.manager.get_source(source_id)
context = self.manager.get_week_context(source["week_id"])
path = Path(source["stored_path"])
processor = self._processor_for(source["source_type"], use_ocr, page_ranges)
source_type = self._resolve_source_type(source, path)
processor = self._processor_for(source_type, use_ocr, page_ranges)
processed = processor.process(path)
markdown = build_markdown(
title=processed.title,
@@ -29,14 +31,21 @@ class IngestionService:
"subject_slug": context["subject_slug"],
"week": context["week_number"],
"source_file": source["original_name"],
"source_type": source["source_type"],
"source_type": source_type,
"processor": processed.processor,
"page_ranges": page_ranges if source["source_type"] == "pdf" and page_ranges else None,
"page_ranges": page_ranges if source_type == "pdf" and page_ranges else None,
"language": "es",
},
)
return self.manager.create_document(source_id, processed.title, markdown, processor=processed.processor, page_ranges=page_ranges)
def _resolve_source_type(self, source: dict, path: Path) -> str:
if source["source_type"] != "unknown":
return source["source_type"]
# Archivos subidos antes de soportar su formato quedaron como
# ``unknown``; al reprocesarlos se recalcula el tipo por extension.
return self.manager.refresh_source_type(source["id"])
def _processor_for(self, source_type: str, use_ocr: bool, page_ranges: str | None):
if source_type == "text":
return TextProcessor()
@@ -44,6 +53,8 @@ class IngestionService:
return DocxProcessor()
if source_type == "pdf":
return PdfProcessor(use_ocr=use_ocr, page_ranges=page_ranges)
if source_type == "image":
return ImageProcessor()
if source_type == "audio":
return AudioProcessor()
if source_type == "video":