tocmo0nlord/odoo-ai
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

Fix vision OCR response parsing for dict-returning ollama client versions

Browse Source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Carlos Garcia
2026-05-17 11:59:11 -04:00
parent 5b924e60de
commit b76d01b64f
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
agent_service/tools/receipt_parser.py
View File

@@ -117,7 +117,10 @@ def _ocr_image_vision(data: bytes, filename: str, ollama_url: str, model: str) -
'images': [data], 'images': [data],
}], }],
) )
text = (response.message.content or '').strip() if isinstance(response, dict):
text = (response.get('message', {}).get('content') or '').strip()
else:
text = (response.message.content or '').strip()
logger.debug('Vision OCR %s (%s): %d chars', filename, model, len(text)) logger.debug('Vision OCR %s (%s): %d chars', filename, model, len(text))
return text return text
except ImportError: except ImportError: