Files
personal-ai-assistant/backend/app/utils/file_storage.py
dolgolyov.alexei 8b8fe916f0 Phase 4: Documents & Memory — upload, FTS, AI tools, context injection
Backend:
- Document + MemoryEntry models with Alembic migration (GIN FTS index)
- File upload endpoint with path traversal protection (sanitized filenames)
- Background document text extraction (PyMuPDF)
- Full-text search on extracted_text via PostgreSQL tsvector/tsquery
- Memory CRUD with enum-validated categories/importance, field allow-list
- AI tools: save_memory, search_documents, get_memory (Claude function calling)
- Tool execution loop in stream_ai_response (multi-turn tool use)
- Context assembly: injects critical memory + relevant doc excerpts
- File storage abstraction (local filesystem, S3-swappable)
- Secure file deletion (DB flush before disk delete)

Frontend:
- Document upload dialog (drag-and-drop + file picker)
- Document list with status badges, search, download (via authenticated blob)
- Document viewer with extracted text preview
- Memory list grouped by category with importance color coding
- Memory editor with category/importance dropdowns
- Documents + Memory pages with full CRUD
- Enabled sidebar navigation for both sections

Review fixes applied:
- Sanitized upload filenames (path traversal prevention)
- Download via axios blob (not bare <a href>, preserves auth)
- Route ordering: /search before /{id}/reindex
- Memory update allows is_active=False + field allow-list
- MemoryEditor form resets on mode switch
- Literal enum validation on category/importance schemas
- DB flush before file deletion for data integrity

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 13:46:59 +03:00

35 lines
913 B
Python

import uuid
from pathlib import Path
import aiofiles
from app.config import settings
def _get_upload_dir(user_id: uuid.UUID, doc_id: uuid.UUID) -> Path:
path = Path(settings.UPLOAD_DIR) / str(user_id) / str(doc_id)
path.mkdir(parents=True, exist_ok=True)
return path
async def save_upload(user_id: uuid.UUID, doc_id: uuid.UUID, filename: str, content: bytes) -> str:
directory = _get_upload_dir(user_id, doc_id)
file_path = directory / filename
async with aiofiles.open(file_path, "wb") as f:
await f.write(content)
return str(file_path)
def get_file_path(storage_path: str) -> Path:
return Path(storage_path)
def delete_file(storage_path: str) -> None:
path = Path(storage_path)
if path.exists():
path.unlink()
# Clean up empty parent dirs
parent = path.parent
if parent.exists() and not any(parent.iterdir()):
parent.rmdir()