├── .gitignore ├── LICENSE ├── README.md ├── base_ocr ├── README.md ├── __init__.py ├── __manifest__.py ├── models │ ├── __init__.py │ ├── ocr_provider.py │ ├── ocr_space.py │ └── open_ocr.py ├── security │ └── ir.model.access.csv └── views │ └── ocr_provider_views.xml └── document_ocr ├── README.md ├── __init__.py ├── __manifest__.py ├── data └── document_ocr_data.xml ├── models ├── __init__.py ├── document_ocr.py └── vendor_bill.py ├── security └── ir.model.access.csv └── views └── document_ocr_views.xml /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # UV 98 | # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | #uv.lock 102 | 103 | # poetry 104 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 105 | # This is especially recommended for binary packages to ensure reproducibility, and is more 106 | # commonly ignored for libraries. 107 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 108 | #poetry.lock 109 | 110 | # pdm 111 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 112 | #pdm.lock 113 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 114 | # in version control. 115 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control 116 | .pdm.toml 117 | .pdm-python 118 | .pdm-build/ 119 | 120 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 121 | __pypackages__/ 122 | 123 | # Celery stuff 124 | celerybeat-schedule 125 | celerybeat.pid 126 | 127 | # SageMath parsed files 128 | *.sage.py 129 | 130 | # Environments 131 | .env 132 | .venv 133 | env/ 134 | venv/ 135 | ENV/ 136 | env.bak/ 137 | venv.bak/ 138 | 139 | # Spyder project settings 140 | .spyderproject 141 | .spyproject 142 | 143 | # Rope project settings 144 | .ropeproject 145 | 146 | # mkdocs documentation 147 | /site 148 | 149 | # mypy 150 | .mypy_cache/ 151 | .dmypy.json 152 | dmypy.json 153 | 154 | # Pyre type checker 155 | .pyre/ 156 | 157 | # pytype static type analyzer 158 | .pytype/ 159 | 160 | # Cython debug symbols 161 | cython_debug/ 162 | 163 | # PyCharm 164 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 165 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 166 | # and can be added to the global gitignore or merged into this file. For a more nuclear 167 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 168 | #.idea/ 169 | 170 | # PyPI configuration file 171 | .pypirc 172 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2024 Anang Aji Rahmawan 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # odoo-ocr 2 | Odoo module that provides Optical Character Recognition (OCR) and information extraction capabilities for documents. 3 | 4 | # Demo 5 | https://github.com/user-attachments/assets/83478c82-f2db-4f9c-891e-fcecff3a09d5 6 | 7 | ## Prerequisites 8 | 9 | To use this module, you need to have: 10 | - An account and API key from [ocr.space](https://ocr.space/) 11 | - An account with [groq](https://groq.com/) 12 | 13 | ## Contributing 14 | 15 | 1. Fork the repository 16 | 2. Create a feature branch 17 | 3. Commit your changes 18 | 4. Push to the branch 19 | 5. Create a Pull Request 20 | 21 | ## Support 22 | 23 | For support, please: 24 | 1. Check existing issues 25 | 2. Create a new issue with detailed information 26 | 3. Contact the maintainers 27 | -------------------------------------------------------------------------------- /base_ocr/README.md: -------------------------------------------------------------------------------- 1 | # Base OCR 2 | 3 | Base module for integrating Optical Character Recognition (OCR) services in Odoo. 4 | 5 | ## Features 6 | 7 | - Flexible OCR provider management 8 | - Support for multiple OCR services 9 | - Configurable OCR settings 10 | - Easy integration with other modules 11 | 12 | ## Configuration 13 | 14 | 1. Go to Settings > Technical > OCR 15 | 2. Configure OCR provider settings 16 | - API keys 17 | - Endpoints 18 | - Default provider 19 | 20 | ## Usage 21 | 22 | ### OCR Provider Model 23 | 24 | The module provides `ocr.provider` model with these features: 25 | - Provider type selection 26 | - API configuration 27 | - Default provider setting 28 | - Company-specific settings 29 | 30 | ### Process Images 31 | 32 | ```python 33 | # Get default provider 34 | provider = env["ocr.provider"].get_default_provider() 35 | 36 | # Process image 37 | result = provider.process_image(image_data, filename="document.pdf") 38 | if result["success"]: 39 | text = result["text"] 40 | else: 41 | error = result["error"] 42 | ``` 43 | 44 | ### Extend Provider Types 45 | 46 | 1. Create new provider model inheriting `ocr.provider` 47 | 2. Implement `_process_[provider_type]` method 48 | 3. Add provider type to selection field 49 | 50 | Example: 51 | ```python 52 | class CustomProvider(models.Model): 53 | _inherit = "ocr.provider" 54 | 55 | def _process_custom(self, image_data, **kwargs): 56 | # Implement custom OCR processing 57 | return { 58 | "success": True, 59 | "text": "Extracted text", 60 | } 61 | ``` 62 | 63 | ## Contributing 64 | 65 | 1. Fork the repository 66 | 2. Create a feature branch 67 | 3. Commit your changes 68 | 4. Push to the branch 69 | 5. Create a Pull Request 70 | 71 | ## Support 72 | 73 | For support, please: 74 | 1. Check existing issues 75 | 2. Create a new issue with detailed information 76 | 3. Contact the maintainers 77 | -------------------------------------------------------------------------------- /base_ocr/__init__.py: -------------------------------------------------------------------------------- 1 | from . import models 2 | -------------------------------------------------------------------------------- /base_ocr/__manifest__.py: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Base OCR", 3 | "version": "18.0.1.0.0", 4 | "category": "Tools", 5 | "summary": "Base module for OCR providers integration", 6 | "sequence": 1, 7 | "description": """ 8 | Base OCR Provider Integration 9 | =========================== 10 | This module provides the base structure for integrating various OCR providers. 11 | Currently supported providers: 12 | - OCR.space 13 | 14 | This module serves as a foundation for other OCR-related modules. 15 | """, 16 | "author": "Anang Aji Rahmawan", 17 | "website": "https://github.com/0yik", 18 | "depends": ["base"], 19 | "data": [ 20 | "security/ir.model.access.csv", 21 | "views/ocr_provider_views.xml", 22 | ], 23 | "installable": True, 24 | "application": False, 25 | "auto_install": False, 26 | } 27 | -------------------------------------------------------------------------------- /base_ocr/models/__init__.py: -------------------------------------------------------------------------------- 1 | from . import ocr_provider 2 | from . import ocr_space 3 | from . import open_ocr 4 | -------------------------------------------------------------------------------- /base_ocr/models/ocr_provider.py: -------------------------------------------------------------------------------- 1 | import logging 2 | from odoo import models, fields, api, _ 3 | from odoo.exceptions import UserError 4 | 5 | _logger = logging.getLogger(__name__) 6 | 7 | 8 | class OCRProvider(models.Model): 9 | _name = "ocr.provider" 10 | _description = "OCR Provider" 11 | 12 | # Language code mappings for different providers 13 | LANGUAGE_MAPPINGS = { 14 | 'openocr': { 15 | 'ara': 'ara', # Arabic 16 | 'bul': 'bul', # Bulgarian 17 | 'chs': 'chi-sim', # Chinese (Simplified) 18 | 'cht': 'chi-tra', # Chinese (Traditional) 19 | 'hrv': 'hrv', # Croatian 20 | 'cze': 'ces', # Czech 21 | 'dan': 'dan', # Danish 22 | 'dut': 'nld', # Dutch 23 | 'eng': 'eng', # English 24 | 'fin': 'fin', # Finnish 25 | 'fre': 'fra', # French 26 | 'ger': 'deu', # German 27 | 'gre': 'ell', # Greek 28 | 'hun': 'hun', # Hungarian 29 | 'kor': 'kor', # Korean 30 | 'ita': 'ita', # Italian 31 | 'jpn': 'jpn', # Japanese 32 | 'pol': 'pol', # Polish 33 | 'por': 'por', # Portuguese 34 | 'rus': 'rus', # Russian 35 | 'slv': 'slv', # Slovenian 36 | 'spa': 'spa', # Spanish 37 | 'swe': 'swe', # Swedish 38 | 'tur': 'tur', # Turkish 39 | }, 40 | 'ocrspace': { 41 | 'ara': 'ara', # Arabic 42 | 'bul': 'bul', # Bulgarian 43 | 'chi-sim': 'chs', # Chinese (Simplified) 44 | 'chi-tra': 'cht', # Chinese (Traditional) 45 | 'hrv': 'hrv', # Croatian 46 | 'ces': 'cze', # Czech 47 | 'dan': 'dan', # Danish 48 | 'nld': 'dut', # Dutch 49 | 'eng': 'eng', # English 50 | 'fin': 'fin', # Finnish 51 | 'fra': 'fre', # French 52 | 'deu': 'ger', # German 53 | 'ell': 'gre', # Greek 54 | 'hun': 'hun', # Hungarian 55 | 'kor': 'kor', # Korean 56 | 'ita': 'ita', # Italian 57 | 'jpn': 'jpn', # Japanese 58 | 'pol': 'pol', # Polish 59 | 'por': 'por', # Portuguese 60 | 'rus': 'rus', # Russian 61 | 'slv': 'slv', # Slovenian 62 | 'spa': 'spa', # Spanish 63 | 'swe': 'swe', # Swedish 64 | 'tur': 'tur', # Turkish 65 | } 66 | } 67 | 68 | name = fields.Char(string="Name", required=True) 69 | provider_type = fields.Selection( 70 | [ 71 | ("ocrspace", "ocr.space"), 72 | ("openocr", "open-ocr"), 73 | ], 74 | string="Provider Type", 75 | required=True, 76 | ) 77 | api_key = fields.Char(string="API Key") 78 | api_endpoint = fields.Char(string="API Endpoint") 79 | active = fields.Boolean(default=True) 80 | company_id = fields.Many2one( 81 | "res.company", 82 | string="Company", 83 | required=True, 84 | default=lambda self: self.env.company, 85 | ) 86 | is_default = fields.Boolean(string="Default Provider") 87 | 88 | def _map_language_code(self, language): 89 | """Map language code between providers. 90 | 91 | Args: 92 | language (str): Source language code 93 | 94 | Returns: 95 | str: Mapped language code for target provider 96 | """ 97 | if not language: 98 | return 'eng' # Default to English 99 | 100 | # If language code exists in target provider mapping, return as is 101 | if language in self.LANGUAGE_MAPPINGS.get(self.provider_type, {}): 102 | return language 103 | 104 | # Try to find mapping from other provider 105 | for provider, mappings in self.LANGUAGE_MAPPINGS.items(): 106 | if provider != self.provider_type: 107 | # If we find the language in another provider's mapping 108 | if language in mappings: 109 | # Get the standard code (value) and then map it to target provider 110 | standard_code = mappings[language] 111 | # Find the key in target provider mapping that has this standard code as value 112 | for target_code, std_code in self.LANGUAGE_MAPPINGS[target_provider].items(): 113 | if std_code == standard_code: 114 | return target_code 115 | 116 | return 'eng' # Default to English if no mapping found 117 | 118 | @api.model 119 | def create(self, vals): 120 | if vals.get("is_default"): 121 | self.search( 122 | [ 123 | ("is_default", "=", True), 124 | ("company_id", "=", vals.get("company_id", self.env.company.id)), 125 | ] 126 | ).write({"is_default": False}) 127 | return super().create(vals) 128 | 129 | def write(self, vals): 130 | if vals.get("is_default"): 131 | self.search( 132 | [ 133 | ("is_default", "=", True), 134 | ("company_id", "=", self.company_id.id), 135 | ("id", "!=", self.id), 136 | ] 137 | ).write({"is_default": False}) 138 | return super().write(vals) 139 | 140 | def process_image(self, image_data, **kwargs): 141 | """Process the image using the selected OCR provider""" 142 | self.ensure_one() 143 | 144 | method_name = f"_process_{self.provider_type}" 145 | if hasattr(self, method_name): 146 | return getattr(self, method_name)(image_data, **kwargs) 147 | else: 148 | raise UserError( 149 | _("Provider type %s is not implemented") % self.provider_type 150 | ) 151 | 152 | @api.model 153 | def get_default_provider(self, company_id=None): 154 | """Get the default OCR provider for the company""" 155 | if not company_id: 156 | company_id = self.env.company.id 157 | return self.search( 158 | [("company_id", "=", company_id), ("is_default", "=", True)], limit=1 159 | ) 160 | -------------------------------------------------------------------------------- /base_ocr/models/ocr_space.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import logging 3 | import os 4 | from odoo import models, _ 5 | from odoo.exceptions import UserError 6 | 7 | _logger = logging.getLogger(__name__) 8 | 9 | 10 | class OCRSpaceProvider(models.Model): 11 | _inherit = "ocr.provider" 12 | 13 | def _process_ocrspace(self, image_data, filename=None, **kwargs): 14 | """Process image using OCR.space API.""" 15 | self.ensure_one() 16 | 17 | if not self.api_key: 18 | raise UserError( 19 | _("Please configure OCR.space API key in provider settings") 20 | ) 21 | 22 | if not self.api_endpoint: 23 | self.api_endpoint = "https://api.ocr.space/parse/image" 24 | 25 | # Get file extension from the filename 26 | ext = os.path.splitext(filename)[1].lstrip(".").upper() if filename else "PNG" 27 | 28 | headers = {"apikey": self.api_key} 29 | 30 | # Get mapped language code for OCR.space 31 | language = self._map_language_code(kwargs.get('language', 'eng')) 32 | 33 | payload = { 34 | "language": language, 35 | "isOverlayRequired": False, 36 | "OCREngine": 1, 37 | "isTable": True, 38 | "scale": True, 39 | "filetype": ext, 40 | } 41 | 42 | files = { 43 | "file": ( 44 | filename or f"document.{ext.lower()}", 45 | image_data, 46 | "application/octet-stream", 47 | ) 48 | } 49 | 50 | try: 51 | response = requests.post( 52 | self.api_endpoint, 53 | headers=headers, 54 | files=files, 55 | data=payload, 56 | timeout=30, 57 | ) 58 | response.raise_for_status() 59 | result = response.json() 60 | 61 | if not result.get("ParsedResults"): 62 | error_msg = result.get("ErrorMessage", "Unknown error occurred") 63 | _logger.error("OCR Error: %s", error_msg) 64 | raise UserError(_("OCR processing failed: %s") % error_msg) 65 | 66 | return { 67 | "success": True, 68 | "text": result["ParsedResults"][0].get("ParsedText", ""), 69 | "raw_response": result, 70 | } 71 | 72 | except requests.exceptions.RequestException as e: 73 | _logger.error("OCR API Request failed: %s", str(e)) 74 | return {"success": False, "error": str(e)} 75 | except ValueError as e: 76 | _logger.error("Invalid JSON response from OCR service: %s", str(e)) 77 | return {"success": False, "error": str(e)} 78 | except Exception as e: 79 | _logger.error("Error processing document: %s", str(e)) 80 | return {"success": False, "error": str(e)} 81 | -------------------------------------------------------------------------------- /base_ocr/models/open_ocr.py: -------------------------------------------------------------------------------- 1 | import requests 2 | import logging 3 | import base64 4 | import os 5 | from odoo import models, _ 6 | from odoo.exceptions import UserError 7 | 8 | _logger = logging.getLogger(__name__) 9 | 10 | 11 | class OpenOCRProvider(models.Model): 12 | _inherit = "ocr.provider" 13 | 14 | def _process_openocr(self, image_data, filename=None, **kwargs): 15 | """Process image using Open OCR API.""" 16 | self.ensure_one() 17 | 18 | if not self.api_endpoint: 19 | self.api_endpoint = "http://localhost:9292" 20 | 21 | # Get mapped language code for Open OCR 22 | language = self._map_language_code(kwargs.get("language", "eng")) 23 | 24 | try: 25 | # Convert image data to base64 26 | file_b64 = base64.b64encode(image_data).decode("utf-8") 27 | 28 | # Prepare request payload 29 | payload = { 30 | "img_base64": file_b64, 31 | "engine": "tesseract", 32 | "engine_args": {"lang": language}, 33 | } 34 | 35 | # Add PDF preprocessor if file is PDF 36 | if filename and filename.lower().endswith(".pdf"): 37 | payload["preprocessors"] = ["convert-pdf"] 38 | 39 | # Make request to Open OCR API 40 | headers = {"Content-Type": "application/json"} 41 | api_url = f"{self.api_endpoint}/ocr" 42 | _logger.info("Making request to Open OCR API: %s", api_url) 43 | 44 | response = requests.post(api_url, headers=headers, json=payload, timeout=30) 45 | 46 | _logger.info("Open OCR API Response Status: %s", response.status_code) 47 | 48 | response.raise_for_status() 49 | 50 | result = response.text 51 | 52 | return {"success": True, "text": result} 53 | 54 | except requests.exceptions.RequestException as e: 55 | error_msg = f"API Connection Error: {str(e)}" 56 | _logger.error("Open OCR API Error: %s", str(e)) 57 | return {"success": False, "error": error_msg} 58 | except Exception as e: 59 | error_msg = str(e) 60 | _logger.error("Open OCR Processing Error: %s", error_msg) 61 | return {"success": False, "error": error_msg} 62 | -------------------------------------------------------------------------------- /base_ocr/security/ir.model.access.csv: -------------------------------------------------------------------------------- 1 | id,name,model_id:id,group_id:id,perm_read,perm_write,perm_create,perm_unlink 2 | access_ocr_provider_user,ocr.provider.user,model_ocr_provider,base.group_user,1,0,0,0 3 | access_ocr_provider_manager,ocr.provider.manager,model_ocr_provider,base.group_system,1,1,1,1 4 | -------------------------------------------------------------------------------- /base_ocr/views/ocr_provider_views.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | ocr.provider.list 5 | ocr.provider 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | ocr.provider.form 19 | ocr.provider 20 | 21 |
22 | 23 |
24 | 25 | 28 |
29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 |
43 | 44 | 45 | 46 | 47 | OCR Providers 48 | ocr.provider 49 | list,form 50 | 51 |

52 | Create your first OCR provider 53 |

54 |

55 | Configure OCR providers to process documents using OCR technology. 56 |

57 | 58 | 59 | 60 | 65 | 66 | 71 | 72 | -------------------------------------------------------------------------------- /document_ocr/README.md: -------------------------------------------------------------------------------- 1 | # Document OCR 2 | 3 | Document OCR is an Odoo module that provides Optical Character Recognition (OCR) and information extraction capabilities for documents. 4 | 5 | ## Features 6 | 7 | - Upload and process various document types (PDF, images) 8 | - OCR processing with configurable providers 9 | - Information extraction using LLM (Large Language Models) 10 | - Support for vendor bill processing 11 | - Flexible document type handling 12 | 13 | ## Installation 14 | 15 | ### Prerequisites 16 | 17 | 1. Install required Python packages: 18 | - dateparser 19 | 20 | 2. Configure OCR and LLM providers in Odoo settings 21 | 22 | ## Configuration 23 | 24 | 1. Go to Settings > Technical > OCR or LLM 25 | 2. Configure OCR provider settings 26 | 3. Configure LLM provider settings 27 | 28 | ## Usage 29 | 30 | 1. Navigate to Document OCR > Documents 31 | 2. Upload a document (PDF or image) 32 | 3. Select document type 33 | 4. Process document 34 | 5. Review extracted information 35 | 6. Create related records (e.g., vendor bills) 36 | 37 | ## Document Types 38 | 39 | ### Vendor Bills 40 | - Extracts vendor information 41 | - Identifies line items 42 | - Processes dates and amounts 43 | - Creates draft vendor bills 44 | 45 | ### Other Documents 46 | - Extracts general information 47 | - Customizable for specific needs 48 | 49 | ## Contributing 50 | 51 | 1. Fork the repository 52 | 2. Create a feature branch 53 | 3. Commit your changes 54 | 4. Push to the branch 55 | 5. Create a Pull Request 56 | 57 | ## Support 58 | 59 | For support, please: 60 | 1. Check existing issues 61 | 2. Create a new issue with detailed information 62 | 3. Contact the maintainers 63 | -------------------------------------------------------------------------------- /document_ocr/__init__.py: -------------------------------------------------------------------------------- 1 | from . import models -------------------------------------------------------------------------------- /document_ocr/__manifest__.py: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Document OCR", 3 | "version": "18.0.1.0.0", 4 | "category": "Document Management", 5 | "summary": "OCR Processing for Documents", 6 | "sequence": 10, 7 | "description": """ 8 | Process documents using OCR technology and extract information. 9 | Features: 10 | - Upload documents (PDF, images) 11 | - OCR processing 12 | - Information extraction 13 | - Vendor bill creation 14 | """, 15 | "author": "Anang Aji Rahmawan", 16 | "website": "https://github.com/0yik", 17 | "depends": ["base", "mail", "account", "product", "base_ocr", "base_llm"], 18 | "data": [ 19 | "security/ir.model.access.csv", 20 | "data/document_ocr_data.xml", 21 | "views/document_ocr_views.xml", 22 | ], 23 | "external_dependencies": { 24 | "python": ["dateparser"], 25 | }, 26 | "installable": True, 27 | "application": True, 28 | "auto_install": False, 29 | } 30 | -------------------------------------------------------------------------------- /document_ocr/data/document_ocr_data.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | Document OCR Sequence 7 | document.ocr 8 | DOC/%(year)s/ 9 | 5 10 | 11 | 12 | 13 | 14 | -------------------------------------------------------------------------------- /document_ocr/models/__init__.py: -------------------------------------------------------------------------------- 1 | from . import document_ocr 2 | from . import vendor_bill -------------------------------------------------------------------------------- /document_ocr/models/document_ocr.py: -------------------------------------------------------------------------------- 1 | import base64 2 | import json 3 | import logging 4 | import os 5 | import tempfile 6 | from odoo import models, fields, api, _ 7 | from odoo.exceptions import UserError 8 | 9 | _logger = logging.getLogger(__name__) 10 | 11 | 12 | class DocumentOCR(models.Model): 13 | _name = "document.ocr" 14 | _description = "Document OCR Processing" 15 | _inherit = ["mail.thread", "mail.activity.mixin"] 16 | 17 | name = fields.Char( 18 | string="Name", required=True, copy=False, readonly=True, default="/" 19 | ) 20 | document_file = fields.Binary(string="Document File", required=True) 21 | document_filename = fields.Char(string="Filename") 22 | file_type = fields.Selection( 23 | [("pdf", "PDF"), ("image", "Image")], 24 | string="File Type", 25 | compute="_compute_file_type", 26 | store=True, 27 | ) 28 | document_type = fields.Selection( 29 | [("other", "Other")], 30 | string="Document Type", 31 | required=True, 32 | ondelete={"other": "set default"}, 33 | default="other", 34 | ) 35 | state = fields.Selection( 36 | [ 37 | ("draft", "Draft"), 38 | ("processing", "Processing"), 39 | ("done", "Done"), 40 | ("error", "Error"), 41 | ], 42 | string="Status", 43 | default="draft", 44 | readonly=True, 45 | tracking=True, 46 | ) 47 | related_record = fields.Reference( 48 | selection="_get_reference_models", string="Related Record", readonly=True 49 | ) 50 | ocr_result = fields.Text(string="OCR Result", readonly=True) 51 | parsed_data = fields.Text(string="Parsed Data", readonly=True) 52 | error_message = fields.Text(string="Error Message", readonly=True) 53 | company_id = fields.Many2one( 54 | "res.company", 55 | string="Company", 56 | required=True, 57 | default=lambda self: self.env.company, 58 | ) 59 | ocr_language = fields.Selection([ 60 | ('eng', 'English'), 61 | ('ara', 'Arabic'), 62 | ('bel', 'Belarusian'), 63 | ('ben', 'Bengali'), 64 | ('bul', 'Bulgarian'), 65 | ('ces', 'Czech'), 66 | ('dan', 'Danish'), 67 | ('deu', 'German'), 68 | ('ell', 'Greek'), 69 | ('fin', 'Finnish'), 70 | ('fra', 'French'), 71 | ('heb', 'Hebrew'), 72 | ('hin', 'Hindi'), 73 | ('ind', 'Indonesian'), 74 | ('isl', 'Icelandic'), 75 | ('ita', 'Italian'), 76 | ('jpn', 'Japanese'), 77 | ('kor', 'Korean'), 78 | ('nld', 'Dutch'), 79 | ('nor', 'Norwegian'), 80 | ('pol', 'Polish'), 81 | ('por', 'Portuguese'), 82 | ('ron', 'Romanian'), 83 | ('rus', 'Russian'), 84 | ('spa', 'Spanish'), 85 | ('swe', 'Swedish'), 86 | ('tha', 'Thai'), 87 | ('tur', 'Turkish'), 88 | ('ukr', 'Ukrainian'), 89 | ('vie', 'Vietnamese'), 90 | ('chi-sim', 'Chinese Simplified'), 91 | ('chi-tra', 'Chinese Traditional') 92 | ], string='OCR Language', required=True, default='eng', 93 | help="Language used for OCR processing. If not specified, English will be used.") 94 | ocr_provider_id = fields.Many2one( 95 | "ocr.provider", 96 | string="OCR Provider", 97 | default=lambda self: self.env["ocr.provider"].get_default_provider(), 98 | ) 99 | llm_provider_id = fields.Many2one( 100 | "llm.provider", 101 | string="LLM Provider", 102 | default=lambda self: self.env["llm.provider"].get_default_provider() 103 | ) 104 | 105 | @api.model 106 | def _get_reference_models(self): 107 | models = self.env["ir.model"].search([]) 108 | return [(model.model, model.name) for model in models] 109 | 110 | def _process_data_other(self, parsed_data): 111 | pass 112 | 113 | @api.model_create_multi 114 | def create(self, vals_list): 115 | for vals in vals_list: 116 | if vals.get("name", "/") == "/": 117 | vals["name"] = self.env["ir.sequence"].next_by_code("document.ocr") 118 | return super().create(vals_list) 119 | 120 | @api.depends("document_file", "document_filename") 121 | def _compute_file_type(self): 122 | for record in self: 123 | if not record.document_file or not record.document_filename: 124 | record.file_type = False 125 | continue 126 | 127 | ext = os.path.splitext(record.document_filename)[1].lower() 128 | if ext in [".pdf"]: 129 | record.file_type = "pdf" 130 | elif ext in [".jpg", ".jpeg", ".png", ".gif", ".bmp", ".tiff", ".tif"]: 131 | record.file_type = "image" 132 | else: 133 | raise UserError( 134 | _("Unsupported file type. Please upload a PDF or image file.") 135 | ) 136 | 137 | def _get_prompt_template(self): 138 | """Get the prompt template based on document type""" 139 | return """You MUST respond with ONLY a JSON object containing 140 | the key information from this document, no explanations or other text.""" 141 | 142 | @api.onchange("llm_provider_id") 143 | def _onchange_llm_provider(self): 144 | if self.llm_provider_id: 145 | self.llm_provider_id = self.llm_provider_id.id 146 | 147 | def process_document(self): 148 | self.ensure_one() 149 | if not self.document_file: 150 | raise UserError(_("Please upload a document file first.")) 151 | 152 | if not self.ocr_provider_id: 153 | raise UserError(_("Please configure an OCR provider in settings.")) 154 | 155 | try: 156 | self.state = "processing" 157 | _logger.info("Processing document: %s", self.name) 158 | 159 | # Create a temporary directory 160 | with tempfile.TemporaryDirectory() as temp_dir: 161 | # Save binary data to temporary file 162 | binary_data = base64.b64decode(self.document_file) 163 | temp_input = os.path.join(temp_dir, self.document_filename) 164 | with open(temp_input, "wb") as f: 165 | f.write(binary_data) 166 | 167 | # Process with OCR 168 | ocr_result = self.with_context(document_id=self)._process_ocr(temp_input) 169 | if not ocr_result.get("ParsedResults"): 170 | raise UserError(_("OCR processing failed. Please try again.")) 171 | 172 | # Parse OCR result 173 | parsed_text = ocr_result["ParsedResults"][0]["ParsedText"] 174 | parsed_json = self._parse_text_to_json(parsed_text) 175 | 176 | # Store results 177 | self.ocr_result = parsed_text 178 | self.parsed_data = json.dumps(parsed_json) 179 | 180 | # Process according to document type 181 | method_name = f"_process_data_{self.document_type}" 182 | if hasattr(self, method_name): 183 | getattr(self, method_name)(parsed_json) 184 | else: 185 | raise UserError( 186 | _("Document type %s is not implemented") % self.document_type 187 | ) 188 | 189 | self.state = "done" 190 | 191 | except Exception as e: 192 | error_msg = str(e) 193 | _logger.error("Error processing document: %s", error_msg) 194 | self.state = "error" 195 | self.error_message = error_msg 196 | raise UserError(_("Error processing document: %s") % error_msg) 197 | 198 | def _parse_text_to_json(self, text): 199 | if not self.llm_provider_id: 200 | raise UserError(_("Please select an LLM provider.")) 201 | 202 | prompt = f"""{self._get_prompt_template()} 203 | 204 | Input text to convert: 205 | {text} 206 | """ 207 | 208 | result = self.llm_provider_id.process_prompt( 209 | prompt, 210 | response_format={"type": "json_object"}, 211 | temperature=0.1, 212 | ) 213 | if result.get("success"): 214 | return result["content"] 215 | else: 216 | raise UserError(_("Error parsing document text: %s") % result.get("error")) 217 | 218 | def _process_ocr(self, file_path): 219 | """Process document with OCR provider.""" 220 | try: 221 | with open(file_path, "rb") as file: 222 | file_data = file.read() 223 | 224 | # Process with OCR provider 225 | result = self.ocr_provider_id.process_image( 226 | file_data, filename=os.path.basename(file_path), language=self.ocr_language 227 | ) 228 | 229 | if result.get("success"): 230 | return {"ParsedResults": [{"ParsedText": result["text"]}]} 231 | else: 232 | raise UserError( 233 | _("OCR processing failed: %s") 234 | % result.get("error", "Unknown error") 235 | ) 236 | except Exception as e: 237 | _logger.error("OCR Error: %s", str(e)) 238 | raise UserError(str(e)) 239 | -------------------------------------------------------------------------------- /document_ocr/models/vendor_bill.py: -------------------------------------------------------------------------------- 1 | from odoo import models, fields, api 2 | 3 | 4 | class VendorBill(models.Model): 5 | _inherit = "document.ocr" 6 | 7 | document_type = fields.Selection( 8 | selection_add=[("vendor_bill", "Vendor Bill")], 9 | ondelete={"vendor_bill": "cascade"}, 10 | string="Document Type", 11 | required=True, 12 | ) 13 | 14 | def _get_prompt_template(self): 15 | """Get the prompt template based on document type""" 16 | result = super()._get_prompt_template() 17 | if self.document_type == "vendor_bill": 18 | return """ 19 | You MUST respond with ONLY a JSON object in this EXACT format, no explanations or other text: 20 | { 21 | "vendor_name": "string", 22 | "invoice_number": "string", 23 | "date": "YYYY-MM-DD", 24 | "line_items": [ 25 | { 26 | "product": "string", 27 | "description": "string", 28 | "quantity": number, 29 | "price": number, 30 | "subtotal": number 31 | } 32 | ], 33 | "total": number, 34 | "total_tax": number, 35 | "total_discount": number 36 | } 37 | """ 38 | return result 39 | 40 | def _parse_date(self, date_str): 41 | """Parse date string to YYYY-MM-DD format using dateparser.""" 42 | if not date_str: 43 | return False 44 | 45 | try: 46 | import dateparser 47 | 48 | parsed_date = dateparser.parse( 49 | date_str, 50 | settings={ 51 | "PREFER_DAY_OF_MONTH": "first", 52 | "PREFER_DATES_FROM": "past", 53 | "RETURN_AS_TIMEZONE_AWARE": False, 54 | "DATE_ORDER": "DMY", 55 | }, 56 | ) 57 | if parsed_date: 58 | return fields.Date.to_string(parsed_date.date()) 59 | except Exception as e: 60 | _logger.warning("Date parsing failed for %s: %s", date_str, str(e)) 61 | 62 | return fields.Date.today() 63 | 64 | def _process_data_vendor_bill(self, parsed_data): 65 | """Create vendor bill from parsed data""" 66 | # Find or create vendor 67 | partner = self.env["res.partner"].search( 68 | [("name", "ilike", parsed_data.get("vendor_name"))], limit=1 69 | ) 70 | 71 | if not partner: 72 | partner = self.env["res.partner"].create( 73 | { 74 | "name": parsed_data.get("vendor_name"), 75 | "company_type": "company", 76 | "is_company": True, 77 | } 78 | ) 79 | 80 | lines = [] 81 | # Add regular product lines with no tax 82 | for item in parsed_data.get("line_items", []): 83 | product = self.env["product.product"].search( 84 | [("name", "ilike", item.get("product"))], limit=1 85 | ) 86 | 87 | if not product: 88 | product = self.env["product.product"].create( 89 | { 90 | "name": item.get("product"), 91 | "type": "service", 92 | "purchase_ok": True, 93 | } 94 | ) 95 | 96 | lines.append( 97 | ( 98 | 0, 99 | 0, 100 | { 101 | "product_id": product.id, 102 | "name": item.get("description") or product.name, 103 | "quantity": item.get("quantity", 1.0), 104 | "price_unit": item.get("price", 0.0), 105 | "tax_ids": [(5, 0, 0)], # Clear all taxes 106 | }, 107 | ) 108 | ) 109 | 110 | # Add tax line if present 111 | if parsed_data.get("total_tax"): 112 | tax_product = self.env["product.product"].search( 113 | [("name", "=", "Tax")], limit=1 114 | ) or self.env["product.product"].create( 115 | { 116 | "name": "Tax", 117 | "type": "service", 118 | "purchase_ok": True, 119 | } 120 | ) 121 | 122 | lines.append( 123 | ( 124 | 0, 125 | 0, 126 | { 127 | "product_id": tax_product.id, 128 | "name": "Tax", 129 | "quantity": 1.0, 130 | "price_unit": parsed_data.get("total_tax", 0.0), 131 | "tax_ids": [(5, 0, 0)], # No tax on tax line 132 | }, 133 | ) 134 | ) 135 | 136 | # Add discount line if present 137 | if parsed_data.get("total_discount"): 138 | discount_product = self.env["product.product"].search( 139 | [("name", "=", "Discount")], limit=1 140 | ) or self.env["product.product"].create( 141 | { 142 | "name": "Discount", 143 | "type": "service", 144 | "purchase_ok": True, 145 | } 146 | ) 147 | 148 | lines.append( 149 | ( 150 | 0, 151 | 0, 152 | { 153 | "product_id": discount_product.id, 154 | "name": "Discount", 155 | "quantity": 1.0, 156 | "price_unit": -abs( 157 | parsed_data.get("total_discount", 0.0) 158 | ), # Always make discount negative 159 | "tax_ids": [(5, 0, 0)], # No tax on discount line 160 | }, 161 | ) 162 | ) 163 | 164 | # Create the vendor bill with parsed date 165 | bill = self.env["account.move"].create( 166 | { 167 | "move_type": "in_invoice", 168 | "partner_id": partner.id, 169 | "invoice_date": self._parse_date(parsed_data.get("date")), 170 | "ref": parsed_data.get("invoice_number"), 171 | "invoice_line_ids": lines, 172 | } 173 | ) 174 | 175 | # Set the related record 176 | self.related_record = bill 177 | -------------------------------------------------------------------------------- /document_ocr/security/ir.model.access.csv: -------------------------------------------------------------------------------- 1 | id,name,model_id:id,group_id:id,perm_read,perm_write,perm_create,perm_unlink 2 | access_document_ocr_user,document.ocr.user,model_document_ocr,base.group_user,1,1,1,0 3 | access_document_ocr_manager,document.ocr.manager,model_document_ocr,base.group_system,1,1,1,1 4 | -------------------------------------------------------------------------------- /document_ocr/views/document_ocr_views.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | document.ocr.tree 5 | document.ocr 6 | list 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | document.ocr.form 22 | document.ocr 23 | form 24 | 25 |
26 |
27 |
30 | 31 |
32 |

33 | 34 |

35 |
36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 |
54 |

Document Preview

55 | 56 |
57 | 58 |
59 |

PDF Preview

60 | 61 |
62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 |
73 | 74 | 75 | 76 | 77 | Document OCR 78 | document.ocr 79 | list,form 80 | 81 |

82 | Upload a document to process with OCR 83 |

84 | 85 | 86 | 87 | 88 | 92 | 93 | 98 | 99 | --------------------------------------------------------------------------------