Allow document uploads (PDF, DOCX, TXT, etc.) as focus group assets
- Expand allowed file types from images-only to also include: PDF, DOCX, DOC, TXT, MD, CSV, XLSX, XLS, PPTX, PPT, RTF - validate_asset_file: skip PIL validation for non-image files; 50MB limit for docs / 10MB for images - Correct MIME type detection for document extensions - Store asset_type: "document"|"image" in metadata - ImageDescriptionService: text files → LLM summary; binary docs → label; images → existing multimodal flow Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Vadym Samoilenko
parent
4b47b334d7
commit
33272cc677
2 changed files with 82 additions and 43 deletions
|
|
@ -1120,43 +1120,61 @@ def ensure_upload_folder(focus_group_id):
|
|||
else:
|
||||
raise OSError(f"Main uploads directory is not writable: {main_upload_dir}")
|
||||
|
||||
def is_allowed_file(filename, allowed_extensions={'jpg', 'jpeg', 'png'}):
|
||||
IMAGE_EXTENSIONS = {'jpg', 'jpeg', 'png', 'gif', 'webp', 'bmp', 'tiff'}
|
||||
DOCUMENT_EXTENSIONS = {'pdf', 'docx', 'doc', 'txt', 'md', 'csv', 'xlsx', 'xls', 'pptx', 'ppt', 'rtf'}
|
||||
ALLOWED_EXTENSIONS = IMAGE_EXTENSIONS | DOCUMENT_EXTENSIONS
|
||||
|
||||
DOCUMENT_MIME_TYPES = {
|
||||
'pdf': 'application/pdf',
|
||||
'docx': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
|
||||
'doc': 'application/msword',
|
||||
'txt': 'text/plain',
|
||||
'md': 'text/markdown',
|
||||
'csv': 'text/csv',
|
||||
'xlsx': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
|
||||
'xls': 'application/vnd.ms-excel',
|
||||
'pptx': 'application/vnd.openxmlformats-officedocument.presentationml.presentation',
|
||||
'ppt': 'application/vnd.ms-powerpoint',
|
||||
'rtf': 'application/rtf',
|
||||
}
|
||||
|
||||
def is_allowed_file(filename, allowed_extensions=None):
|
||||
"""Check if file has an allowed extension."""
|
||||
if allowed_extensions is None:
|
||||
allowed_extensions = ALLOWED_EXTENSIONS
|
||||
return '.' in filename and \
|
||||
filename.rsplit('.', 1)[1].lower() in allowed_extensions
|
||||
|
||||
def validate_image_file(file):
|
||||
"""Validate uploaded image file."""
|
||||
def validate_asset_file(file):
|
||||
"""Validate uploaded asset file (images and documents)."""
|
||||
if not file:
|
||||
return False, "No file provided"
|
||||
|
||||
|
||||
if file.filename == '':
|
||||
return False, "No file selected"
|
||||
|
||||
|
||||
if not is_allowed_file(file.filename):
|
||||
return False, "File type not allowed. Only JPG, JPEG, and PNG files are permitted"
|
||||
|
||||
# Check file size (10MB limit) by reading the content length from the file stream
|
||||
return False, f"File type not allowed. Supported types: images (JPG, PNG, GIF, WebP) and documents (PDF, DOCX, TXT, XLSX, etc.)"
|
||||
|
||||
# Check file size (50MB limit for documents, 10MB for images)
|
||||
ext = file.filename.rsplit('.', 1)[1].lower() if '.' in file.filename else ''
|
||||
size_limit = 50 * 1024 * 1024 if ext in DOCUMENT_EXTENSIONS else 10 * 1024 * 1024
|
||||
try:
|
||||
# Store current position
|
||||
current_pos = file.tell()
|
||||
|
||||
# Seek to end to get size
|
||||
file.seek(0, os.SEEK_END)
|
||||
file_size = file.tell()
|
||||
|
||||
# Reset to original position
|
||||
file.seek(current_pos)
|
||||
|
||||
if file_size > 10 * 1024 * 1024: # 10MB in bytes
|
||||
return False, "File size exceeds 10MB limit"
|
||||
|
||||
if file_size > size_limit:
|
||||
limit_mb = size_limit // (1024 * 1024)
|
||||
return False, f"File size exceeds {limit_mb}MB limit"
|
||||
except Exception as e:
|
||||
# If we can't check size, allow it to proceed but log the issue
|
||||
logger.warning(f"Could not validate file size: {e}")
|
||||
|
||||
|
||||
return True, "Valid file"
|
||||
|
||||
# Keep old name as alias for backwards compat
|
||||
validate_image_file = validate_asset_file
|
||||
|
||||
def save_uploaded_file_directly(file, file_path):
|
||||
"""Save uploaded file directly to avoid temporary file issues."""
|
||||
try:
|
||||
|
|
@ -1343,12 +1361,18 @@ async def upload_assets(focus_group_id):
|
|||
# Get file info
|
||||
file_size = os.path.getsize(file_path)
|
||||
|
||||
# Determine mime type
|
||||
detected_mime = file.mimetype
|
||||
if not detected_mime or detected_mime in ('application/octet-stream', ''):
|
||||
detected_mime = DOCUMENT_MIME_TYPES.get(file_extension, f"image/{file_extension}")
|
||||
|
||||
# Create asset metadata
|
||||
asset_metadata = {
|
||||
"filename": unique_filename,
|
||||
"original_name": original_filename,
|
||||
"size": file_size,
|
||||
"mime_type": file.mimetype or f"image/{file_extension}",
|
||||
"mime_type": detected_mime,
|
||||
"asset_type": "document" if file_extension in DOCUMENT_EXTENSIONS else "image",
|
||||
"upload_date": datetime.datetime.now(datetime.timezone.utc),
|
||||
"file_path": file_path
|
||||
}
|
||||
|
|
|
|||
|
|
@ -21,45 +21,60 @@ class ImageDescriptionError(Exception):
|
|||
class ImageDescriptionService:
|
||||
"""Service for generating AI-powered descriptions of creative assets."""
|
||||
|
||||
IMAGE_EXTENSIONS = {'jpg', 'jpeg', 'png', 'gif', 'webp', 'bmp', 'tiff'}
|
||||
TEXT_EXTENSIONS = {'txt', 'md', 'csv', 'rtf'}
|
||||
|
||||
@staticmethod
|
||||
async def generate_description(focus_group_id: str, asset_filename: str) -> str:
|
||||
"""
|
||||
Generate a detailed AI description of a creative asset image.
|
||||
|
||||
Args:
|
||||
focus_group_id: The focus group ID containing the asset
|
||||
asset_filename: The filename of the asset to describe
|
||||
|
||||
Returns:
|
||||
A detailed description of the image
|
||||
|
||||
Raises:
|
||||
ImageDescriptionError: If description generation fails
|
||||
Generate a detailed AI description of a creative asset (image or document).
|
||||
|
||||
For images: uses multimodal LLM.
|
||||
For text documents: reads content and summarizes with LLM.
|
||||
For other documents (pdf, docx, xlsx): returns a descriptive label.
|
||||
"""
|
||||
try:
|
||||
print(f"🎨 DESCRIPTION: Generating AI description for {asset_filename}")
|
||||
|
||||
|
||||
# Resolve the full path to the asset
|
||||
asset_path = ConversationContextService._resolve_asset_path(focus_group_id, asset_filename)
|
||||
print(f"🔍 DESCRIPTION: Resolved asset path: {asset_path}")
|
||||
|
||||
|
||||
# Check if file exists
|
||||
if not os.path.exists(asset_path):
|
||||
print(f"❌ DESCRIPTION: File does not exist at path: {asset_path}")
|
||||
# List files in the directory to help debug
|
||||
asset_dir = os.path.dirname(asset_path)
|
||||
if os.path.exists(asset_dir):
|
||||
files_in_dir = os.listdir(asset_dir)
|
||||
print(f"🔍 DESCRIPTION: Files in directory {asset_dir}: {files_in_dir}")
|
||||
else:
|
||||
print(f"❌ DESCRIPTION: Directory does not exist: {asset_dir}")
|
||||
raise ImageDescriptionError(f"Asset file not found: {asset_path}")
|
||||
|
||||
# Verify the image can be loaded (optional validation)
|
||||
|
||||
ext = asset_filename.rsplit('.', 1)[-1].lower() if '.' in asset_filename else ''
|
||||
|
||||
# ── Non-image: text files ──────────────────────────────────────────────
|
||||
if ext in ImageDescriptionService.TEXT_EXTENSIONS:
|
||||
try:
|
||||
with open(asset_path, 'r', encoding='utf-8', errors='replace') as f:
|
||||
content = f.read(8000) # first 8k chars
|
||||
from app.models.focus_group import FocusGroup
|
||||
focus_group = await FocusGroup.find_by_id(focus_group_id)
|
||||
llm_model = focus_group.get('llm_model') if focus_group else None
|
||||
summary = await LLMService.generate_content(
|
||||
prompt=f"Summarize this document in 2-3 sentences for focus group context:\n\n{content}",
|
||||
temperature=0.3,
|
||||
model_name=llm_model
|
||||
)
|
||||
return summary.strip()
|
||||
except Exception as e:
|
||||
return f"Text document: {asset_filename}"
|
||||
|
||||
# ── Non-image: binary documents (pdf, docx, xlsx, etc.) ───────────────
|
||||
if ext not in ImageDescriptionService.IMAGE_EXTENSIONS:
|
||||
ext_label = ext.upper() if ext else 'Document'
|
||||
original = asset_filename.split('-')[-1] if '-' in asset_filename else asset_filename
|
||||
return f"{ext_label} document: {original}"
|
||||
|
||||
# ── Image: validate with PIL ──────────────────────────────────────────
|
||||
try:
|
||||
image = Image.open(asset_path)
|
||||
print(f"🖼️ DESCRIPTION: Validated image {asset_filename} ({image.size[0]}x{image.size[1]})")
|
||||
image.close() # Close the image since we're passing the path to LLM
|
||||
image.close()
|
||||
except Exception as e:
|
||||
raise ImageDescriptionError(f"Failed to validate image {asset_filename}: {str(e)}")
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue