1

2026-05-17 10:14:14 -06:00
parent d8773b2508
commit 64b3d15b90
61 changed files with 7612 additions and 0 deletions
@@ -0,0 +1,281 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from fastapi import BackgroundTasks, FastAPI, File, HTTPException, Query, UploadFile
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse, PlainTextResponse
+
+from backend.app.config import settings
+from backend.app.managers.knowledge_manager import DuplicateSourceError, KnowledgeManager
+from backend.app.models.schemas import MarkdownUpdate, SubjectCreate, WeekCreate, WeekUpdate
+from backend.app.services.ingestion_service import IngestionService
+
+app = FastAPI(title="Knowledge Station", version="0.1.0")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["http://127.0.0.1:3000", "http://localhost:3000"],
+    allow_origin_regex=r"http://(127\.0\.0\.1|localhost):\d+",
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+manager = KnowledgeManager()
+ingestion = IngestionService(manager)
+
+
+@app.get("/health")
+def health() -> dict[str, str]:
+    return {"status": "ok"}
+
+
+@app.get("/settings/status")
+def settings_status() -> dict:
+    return {
+        "mistral_configured": bool(settings.mistral_api_key),
+        "deepgram_configured": bool(settings.deepgram_api_key),
+        "data_dir": str(settings.app_data_dir),
+        "database_path": str(settings.database_path),
+    }
+
+
+@app.post("/subjects")
+def create_subject(payload: SubjectCreate) -> dict:
+    try:
+        return manager.create_subject(payload.name)
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc)) from exc
+
+
+@app.get("/subjects")
+def list_subjects() -> list[dict]:
+    return manager.list_subjects()
+
+
+@app.get("/subjects/{subject_id}")
+def get_subject(subject_id: int) -> dict:
+    try:
+        return manager.get_subject(subject_id)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.delete("/subjects/{subject_id}")
+def delete_subject(subject_id: int) -> dict:
+    try:
+        manager.delete_subject(subject_id)
+        return {"status": "deleted"}
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.post("/subjects/{subject_id}/weeks")
+def create_week(subject_id: int, payload: WeekCreate) -> dict:
+    try:
+        return manager.create_week(subject_id, payload.number, payload.title)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks")
+def list_weeks(subject_id: int) -> list[dict]:
+    try:
+        manager.get_subject(subject_id)
+        return manager.list_weeks(subject_id)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks/{week_number}")
+def get_week(subject_id: int, week_number: int) -> dict:
+    try:
+        return manager.get_week(subject_id, week_number)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.put("/subjects/{subject_id}/weeks/{week_number}")
+def update_week(subject_id: int, week_number: int, payload: WeekUpdate) -> dict:
+    try:
+        return manager.update_week(subject_id, week_number, payload.number, payload.title)
+    except ValueError as exc:
+        raise HTTPException(status_code=400, detail=str(exc)) from exc
+
+
+@app.delete("/subjects/{subject_id}/weeks/{week_number}")
+def delete_week(subject_id: int, week_number: int) -> dict:
+    try:
+        manager.delete_week(subject_id, week_number)
+        return {"status": "deleted"}
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.post("/subjects/{subject_id}/weeks/{week_number}/files")
+def upload_file(
+    subject_id: int,
+    week_number: int,
+    background_tasks: BackgroundTasks,
+    file: UploadFile = File(...),
+    use_ocr: bool = Query(False, description="Usar Mistral OCR para PDFs"),
+    page_ranges: str | None = Query(None, description="Rangos de paginas PDF, por ejemplo: 1-5,8,10-12"),
+) -> dict:
+    try:
+        source = manager.save_upload(subject_id, week_number, file)
+        job = manager.create_job(source["id"], "Archivo recibido")
+        background_tasks.add_task(process_job, job["id"], source["id"], use_ocr, page_ranges)
+        return {"source": source, "job": job}
+    except DuplicateSourceError as exc:
+        raise HTTPException(status_code=409, detail=str(exc)) from exc
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/jobs/{job_id}")
+def get_job(job_id: int) -> dict:
+    try:
+        return manager.get_job(job_id)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.post("/jobs/{job_id}/retry")
+def retry_job(
+    job_id: int,
+    background_tasks: BackgroundTasks,
+    use_ocr: bool = Query(False),
+    page_ranges: str | None = Query(None),
+) -> dict:
+    try:
+        job = manager.get_job(job_id)
+        if not job.get("source_id"):
+            raise HTTPException(status_code=400, detail="El trabajo no tiene fuente asociada")
+        manager.update_job(job_id, "queued", "Reintento en cola")
+        background_tasks.add_task(process_job, job_id, job["source_id"], use_ocr, page_ranges)
+        return manager.get_job(job_id)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks/{week_number}/jobs")
+def list_week_jobs(subject_id: int, week_number: int) -> list[dict]:
+    try:
+        return manager.list_jobs_for_week(subject_id, week_number)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks/{week_number}/sources")
+def list_sources(subject_id: int, week_number: int) -> list[dict]:
+    try:
+        return manager.list_sources(subject_id, week_number)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.delete("/sources/{source_id}")
+def delete_source(source_id: int) -> dict:
+    try:
+        manager.delete_source(source_id)
+        return {"status": "deleted"}
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.post("/sources/{source_id}/reprocess")
+def reprocess_source(
+    source_id: int,
+    background_tasks: BackgroundTasks,
+    use_ocr: bool = Query(False),
+    page_ranges: str | None = Query(None),
+) -> dict:
+    try:
+        source = manager.get_source(source_id)
+        if manager.source_has_active_job(source_id):
+            raise HTTPException(status_code=409, detail="La fuente ya tiene un trabajo en cola o en proceso")
+        job = manager.create_job(source["id"], "Reprocesamiento en cola")
+        background_tasks.add_task(process_job, job["id"], source["id"], use_ocr, page_ranges)
+        return {"source": source, "job": job}
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks/{week_number}/documents")
+def list_documents(subject_id: int, week_number: int) -> list[dict]:
+    try:
+        return manager.list_documents(subject_id, week_number)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/documents/{document_id}")
+def get_document(document_id: int) -> dict:
+    try:
+        return manager.get_document(document_id)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/documents/{document_id}/markdown", response_class=PlainTextResponse)
+def get_document_markdown(document_id: int) -> str:
+    try:
+        document = manager.get_document(document_id)
+        return Path(document["markdown_path"]).read_text(encoding="utf-8")
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.put("/documents/{document_id}/markdown")
+def update_document_markdown(document_id: int, payload: MarkdownUpdate) -> dict:
+    try:
+        return manager.update_document_markdown(document_id, payload.content)
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/documents/{document_id}/download")
+def download_document(document_id: int) -> FileResponse:
+    try:
+        document = manager.get_document(document_id)
+        path = Path(document["markdown_path"])
+        return FileResponse(path, filename=path.name, media_type="text/markdown")
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.delete("/documents/{document_id}")
+def delete_document(document_id: int) -> dict:
+    try:
+        manager.delete_document(document_id)
+        return {"status": "deleted"}
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks/{week_number}/export")
+def export_week(subject_id: int, week_number: int) -> FileResponse:
+    try:
+        path = manager.export_week_markdown(subject_id, week_number)
+        return FileResponse(path, filename=path.name, media_type="text/markdown")
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@app.get("/subjects/{subject_id}/weeks/{week_number}/export.zip")
+def export_week_zip(subject_id: int, week_number: int) -> FileResponse:
+    try:
+        path = manager.export_week_markdown_zip(subject_id, week_number)
+        return FileResponse(path, filename=path.name, media_type="application/zip")
+    except ValueError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+def process_job(job_id: int, source_id: int, use_ocr: bool, page_ranges: str | None = None) -> None:
+    manager.update_job(job_id, "processing", "Procesando archivo")
+    manager.update_source_status(source_id, "processing")
+    try:
+        document = ingestion.process_source(source_id, use_ocr=use_ocr, page_ranges=page_ranges)
+        manager.update_job(job_id, "completed", "Documento procesado", document_id=document["id"])
+    except Exception as exc:
+        manager.update_source_status(source_id, "failed")
+        manager.update_job(job_id, "failed", str(exc))