Implement watchdog client and automatic file indexing

.dockerignore

@@ -2,4 +2,3 @@
 __pycache__
 .git
 .env
-alembic/versions

.gitignore

@@ -52,4 +52,9 @@ docker-compose.override.yml
 # ======================
 .DS_Store
 Thumbs.db
-test_data/
+test_data/
+
+# ======================
+#Runtime files
+# ======================
+temp/

alembic/versions/ecca7b879961_genesis_migration.py

@@ -18,6 +18,7 @@
 branch_labels: Union[str, Sequence[str], None] = None
 depends_on: Union[str, Sequence[str], None] = None
 
+op.execute("CREATE EXTENSION IF NOT EXISTS vector")
 
 def upgrade() -> None:
     """Upgrade schema."""

alembic/versions/efb17bbdead1_add_watched_folders_table.py

@@ -0,0 +1,39 @@
+"""add watched folders table
+
+Revision ID: efb17bbdead1
+Revises: ecca7b879961
+Create Date: 2026-07-02 12:29:07.453901
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import pgvector.sqlalchemy
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'efb17bbdead1'
+down_revision: Union[str, Sequence[str], None] = 'ecca7b879961'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('watched_folders',
+    sa.Column('id', sa.Integer(), autoincrement=True, nullable=False),
+    sa.Column('folder_path', sa.Text(), nullable=False),
+    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('folder_path')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('watched_folders')
+    # ### end Alembic commands ###

app/main.py

@@ -2,6 +2,7 @@
 from app.routes import search
 from app.routes import upload
 from app.routes import files 
+from app.routes import watch
 
 app = FastAPI(
     title="WhereTF Backend"
@@ -10,6 +11,7 @@
 app.include_router(search.router)
 app.include_router(upload.router)
 app.include_router(files.router)
+app.include_router(watch.router)
 
 @app.get("/health", tags=["System"])
 def health_check():

app/models/__init__.py

@@ -1,3 +1,4 @@
 from app.models.file import File
 from app.models.content import FileContent
-from app.models.relationship import FileRelationship
+from app.models.relationship import FileRelationship
+from app.models.watched_folder import WatchedFolder

app/models/watched_folder.py

@@ -0,0 +1,27 @@
+from datetime import datetime
+
+from sqlalchemy import DateTime, Text
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy.sql import func
+
+from app.database import Base
+
+
+class WatchedFolder(Base):
+    __tablename__ = "watched_folders"
+
+    id: Mapped[int] = mapped_column(
+        primary_key=True,
+        autoincrement=True
+    )
+
+    folder_path: Mapped[str] = mapped_column(
+        Text,
+        unique=True,
+        nullable=False
+    )
+
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True),
+        server_default=func.now()
+    )

app/routes/files.py

@@ -66,4 +66,76 @@ def delete_file(file_id: uuid.UUID, db: Session = Depends(get_db)):
     db.delete(db_file)
     db.commit()
 
-    return {"status": "success", "message": f"File and vectors wiped successfully."}
+    return {"status": "success", "message": f"File and vectors wiped successfully."}
+
+
+class FilePathRequest(BaseModel):
+    file_path: str
+
+
+@router.post("/delete-by-path")
+def delete_file_by_path(req: FilePathRequest, db: Session = Depends(get_db)):
+
+    db_file = db.scalar(
+        select(File).where(File.file_path == req.file_path)
+    )
+
+    if not db_file:
+        raise HTTPException(status_code=404, detail="File not found")
+
+    db.delete(db_file)
+    db.commit()
+
+    return {
+        "status": "success",
+        "message": "File deleted successfully."
+    }
+
+class FileRenameRequest(BaseModel):
+    old_path: str
+    new_path: str
+
+@router.post("/rename")
+def rename_file(req: FileRenameRequest, db: Session = Depends(get_db)):
+
+    db_file = db.scalar(
+        select(File).where(File.file_path == req.old_path)
+    )
+
+    if not db_file:
+        raise HTTPException(status_code=404, detail="File not found")
+
+    db_file.file_path = req.new_path
+
+    db.commit()
+
+    return {
+        "status": "success",
+        "message": "File renamed successfully."
+    }
+
+class FileCheckRequest(BaseModel):
+    file_path: str
+    file_hash: str
+
+@router.post("/needs-indexing")
+def needs_indexing(req: FileCheckRequest, db: Session = Depends(get_db)):
+    db_file = db.scalar(
+        select(File).where(
+            File.file_path == req.file_path
+        )
+    )
+
+    if db_file is None:
+        return {
+            "needs_indexing": True
+        }
+
+    if db_file.file_hash == req.file_hash:
+        return {
+            "needs_indexing": False
+        }
+
+    return {
+        "needs_indexing": True
+    }

app/routes/upload.py

@@ -1,7 +1,7 @@
 import os
 import shutil
 
-from fastapi import APIRouter, UploadFile, File, BackgroundTasks, HTTPException
+from fastapi import APIRouter, Form, UploadFile, File, BackgroundTasks, HTTPException
 
 from app.services.indexer import background_index_file
 
@@ -11,7 +11,8 @@
 @router.post("/upload/")
 async def upload_file(
     background_tasks: BackgroundTasks,
-    file: UploadFile = File(...)
+    file: UploadFile = File(...),
+    original_path: str = Form(...)
 ):
     """
     Accept a document and send it for background indexing.
@@ -27,7 +28,8 @@ async def upload_file(
 
         background_tasks.add_task(
             background_index_file,
-            temp_path
+            temp_path,
+            original_path
         )
 
         return {

app/routes/watch.py

@@ -0,0 +1,95 @@
+from pathlib import Path
+
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
+
+from app.database import SessionLocal
+from app.models import WatchedFolder
+
+router = APIRouter(tags=["Watch"])
+
+
+class WatchFolderRequest(BaseModel):
+    folder_path: str
+
+
+@router.post("/watch/folder")
+def add_watch_folder(req: WatchFolderRequest):
+
+    db = SessionLocal()
+
+    try:
+        existing = db.query(WatchedFolder).filter_by(
+            folder_path=req.folder_path
+        ).first()
+
+        if existing:
+            raise HTTPException(
+                status_code=409,
+                detail="Folder is already being watched."
+            )
+
+        watched_folder = WatchedFolder(
+            folder_path=req.folder_path
+        )
+
+        db.add(watched_folder)
+        db.commit()
+        db.refresh(watched_folder)
+
+        return {
+            "success": True,
+            "id": watched_folder.id,
+            "folder_path": watched_folder.folder_path
+        }
+
+    finally:
+        db.close()
+
+
+@router.get("/watch/folders")
+def get_watched_folders():
+
+    db = SessionLocal()
+
+    try:
+        folders = db.query(WatchedFolder).all()
+
+        return [
+            {
+                "id": folder.id,
+                "folder_path": folder.folder_path,
+                "created_at": folder.created_at
+            }
+            for folder in folders
+        ]
+
+    finally:
+        db.close()
+
+
+@router.delete("/watch/folder")
+def remove_watch_folder(req: WatchFolderRequest):
+
+    db = SessionLocal()
+
+    try:
+        folder = db.query(WatchedFolder).filter_by(
+            folder_path=req.folder_path
+        ).first()
+
+        if not folder:
+            raise HTTPException(
+                status_code=404,
+                detail="Folder not found."
+            )
+
+        db.delete(folder)
+        db.commit()
+
+        return {
+            "success": True
+        }
+
+    finally:
+        db.close()

app/services/archive.py

@@ -0,0 +1,21 @@
+import os
+import tempfile
+import zipfile
+
+
+def extract_zip(zip_path: str):
+
+    temp_dir = tempfile.mkdtemp()
+
+    with zipfile.ZipFile(zip_path, "r") as archive:
+        archive.extractall(temp_dir)
+
+    extracted_files = []
+
+    for root, _, files in os.walk(temp_dir):
+        for file in files:
+            extracted_files.append(
+                os.path.join(root, file)
+            )
+
+    return temp_dir, extracted_files