receipt-ocr 0.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- receipt_ocr-0.1.0/.gitignore +163 -0
- receipt_ocr-0.1.0/LICENSE +21 -0
- receipt_ocr-0.1.0/PKG-INFO +154 -0
- receipt_ocr-0.1.0/README.md +101 -0
- receipt_ocr-0.1.0/pyproject.toml +54 -0
- receipt_ocr-0.1.0/src/receipt_ocr/__about__.py +17 -0
- receipt_ocr-0.1.0/src/receipt_ocr/__init__.py +9 -0
- receipt_ocr-0.1.0/src/receipt_ocr/cli.py +89 -0
- receipt_ocr-0.1.0/src/receipt_ocr/parsers.py +23 -0
- receipt_ocr-0.1.0/src/receipt_ocr/prompts.py +35 -0
- receipt_ocr-0.1.0/src/receipt_ocr/providers.py +73 -0
|
@@ -0,0 +1,163 @@
|
|
|
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
|
+
# poetry
|
|
98
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
99
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
100
|
+
# commonly ignored for libraries.
|
|
101
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
102
|
+
#poetry.lock
|
|
103
|
+
|
|
104
|
+
# pdm
|
|
105
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
106
|
+
#pdm.lock
|
|
107
|
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
|
108
|
+
# in version control.
|
|
109
|
+
# https://pdm.fming.dev/#use-with-ide
|
|
110
|
+
.pdm.toml
|
|
111
|
+
|
|
112
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
113
|
+
__pypackages__/
|
|
114
|
+
|
|
115
|
+
# Celery stuff
|
|
116
|
+
celerybeat-schedule
|
|
117
|
+
celerybeat.pid
|
|
118
|
+
|
|
119
|
+
# SageMath parsed files
|
|
120
|
+
*.sage.py
|
|
121
|
+
|
|
122
|
+
# Environments
|
|
123
|
+
.env
|
|
124
|
+
.venv
|
|
125
|
+
env/
|
|
126
|
+
venv/
|
|
127
|
+
ENV/
|
|
128
|
+
env.bak/
|
|
129
|
+
venv.bak/
|
|
130
|
+
|
|
131
|
+
# Spyder project settings
|
|
132
|
+
.spyderproject
|
|
133
|
+
.spyproject
|
|
134
|
+
|
|
135
|
+
# Rope project settings
|
|
136
|
+
.ropeproject
|
|
137
|
+
|
|
138
|
+
# mkdocs documentation
|
|
139
|
+
/site
|
|
140
|
+
|
|
141
|
+
# mypy
|
|
142
|
+
.mypy_cache/
|
|
143
|
+
.dmypy.json
|
|
144
|
+
dmypy.json
|
|
145
|
+
|
|
146
|
+
# Pyre type checker
|
|
147
|
+
.pyre/
|
|
148
|
+
|
|
149
|
+
# pytype static type analyzer
|
|
150
|
+
.pytype/
|
|
151
|
+
|
|
152
|
+
# Cython debug symbols
|
|
153
|
+
cython_debug/
|
|
154
|
+
|
|
155
|
+
# PyCharm
|
|
156
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
157
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
158
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
159
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
160
|
+
#.idea/
|
|
161
|
+
|
|
162
|
+
.DS_Store
|
|
163
|
+
receipts/
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
MIT License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2025 Bhimraj Yadav
|
|
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.
|
|
@@ -0,0 +1,154 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: receipt-ocr
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: A package for extracting structured data from receipts.
|
|
5
|
+
Project-URL: Homepage, https://github.com/bhimrazy/receipt-ocr
|
|
6
|
+
Project-URL: Bug Tracker, https://github.com/bhimrazy/receipt-ocr/issues
|
|
7
|
+
Project-URL: Documentation, https://github.com/bhimrazy/receipt-ocr
|
|
8
|
+
Project-URL: Source Code, https://github.com/bhimrazy/receipt-ocr
|
|
9
|
+
Project-URL: Download, https://github.com/bhimrazy/receipt-ocr
|
|
10
|
+
Author-email: Bhimraj Yadav <bhimrajyadav977@gmail.com>
|
|
11
|
+
License: MIT License
|
|
12
|
+
|
|
13
|
+
Copyright (c) 2025 Bhimraj Yadav
|
|
14
|
+
|
|
15
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
16
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
17
|
+
in the Software without restriction, including without limitation the rights
|
|
18
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
19
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
20
|
+
furnished to do so, subject to the following conditions:
|
|
21
|
+
|
|
22
|
+
The above copyright notice and this permission notice shall be included in all
|
|
23
|
+
copies or substantial portions of the Software.
|
|
24
|
+
|
|
25
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
26
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
27
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
28
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
29
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
30
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
31
|
+
SOFTWARE.
|
|
32
|
+
License-File: LICENSE
|
|
33
|
+
Keywords: llm,ocr,receipts,tesseract
|
|
34
|
+
Classifier: Development Status :: 4 - Beta
|
|
35
|
+
Classifier: Environment :: Console
|
|
36
|
+
Classifier: Intended Audience :: Developers
|
|
37
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
38
|
+
Classifier: Natural Language :: English
|
|
39
|
+
Classifier: Operating System :: OS Independent
|
|
40
|
+
Classifier: Programming Language :: Python :: 3
|
|
41
|
+
Classifier: Programming Language :: Python :: 3.9
|
|
42
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
43
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
44
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
45
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
46
|
+
Classifier: Topic :: Scientific/Engineering :: Information Analysis
|
|
47
|
+
Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
48
|
+
Requires-Python: >=3.9
|
|
49
|
+
Requires-Dist: openai
|
|
50
|
+
Requires-Dist: pillow
|
|
51
|
+
Requires-Dist: python-dotenv
|
|
52
|
+
Description-Content-Type: text/markdown
|
|
53
|
+
|
|
54
|
+
# Receipt OCR Engine
|
|
55
|
+
|
|
56
|
+
This repository hosts a script and a Docker-compose setup for performing Optical Character Recognition (OCR) on receipt images.
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
|
|
60
|
+
## Star History
|
|
61
|
+
|
|
62
|
+
<a href="https://star-history.com/#bhimrazy/receipt-ocr&Date">
|
|
63
|
+
<picture>
|
|
64
|
+
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=bhimrazy/receipt-ocr&type=Date&theme=dark" />
|
|
65
|
+
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=bhimrazy/receipt-ocr&type=Date" />
|
|
66
|
+
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=bhimrazy/receipt-ocr&type=Date" />
|
|
67
|
+
</picture>
|
|
68
|
+
</a>
|
|
69
|
+
|
|
70
|
+
## Prerequisites
|
|
71
|
+
|
|
72
|
+
- Python 3.x
|
|
73
|
+
- Docker
|
|
74
|
+
- Docker-compose
|
|
75
|
+
|
|
76
|
+
## Installation
|
|
77
|
+
|
|
78
|
+
### Clone the repository
|
|
79
|
+
|
|
80
|
+
```bash
|
|
81
|
+
git clone https://github.com/bhimrazy/receipt-ocr.git
|
|
82
|
+
cd receipt-ocr
|
|
83
|
+
```
|
|
84
|
+
|
|
85
|
+
### Set up Python environment (if not using Docker)
|
|
86
|
+
- Install [tesseract](https://tesseract-ocr.github.io/tessdoc/Installation.html)
|
|
87
|
+
|
|
88
|
+
```bash
|
|
89
|
+
# Create and activate a virtual environment (optional but recommended)
|
|
90
|
+
python -m venv venv
|
|
91
|
+
source venv/bin/activate # For Windows, use venv\Scripts\activate
|
|
92
|
+
|
|
93
|
+
# Install dependencies
|
|
94
|
+
pip install -r requirements.txt
|
|
95
|
+
```
|
|
96
|
+
|
|
97
|
+
## Usage
|
|
98
|
+
|
|
99
|
+
### Running the script locally
|
|
100
|
+
|
|
101
|
+
#### `main.py`
|
|
102
|
+
|
|
103
|
+
The `main.py` script performs OCR on an input image of a receipt.
|
|
104
|
+
|
|
105
|
+
```bash
|
|
106
|
+
python main.py -i images/receipt.jpg
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
Replace `images/receipt.jpg` with the path to your receipt image.
|
|
110
|
+
>Please ensure that the image is well-lit and that the edges of the receipt are clearly visible and detectable within the image.
|
|
111
|
+
<img src="https://github.com/bhimrazy/receipt-ocr/assets/46085301/2ea009f0-9e15-42b2-9f15-063a8ec169f1" alt="Receipt Image" width="300" height="400">
|
|
112
|
+
|
|
113
|
+
|
|
114
|
+
### Using Docker-compose
|
|
115
|
+
|
|
116
|
+
The repository includes a Docker-compose setup for running the OCR engine as a service.
|
|
117
|
+
|
|
118
|
+
```bash
|
|
119
|
+
docker-compose up
|
|
120
|
+
```
|
|
121
|
+
|
|
122
|
+
Once the service is up and running, you can perform OCR on receipt images by sending a POST request to `http://localhost:8000/ocr/` with the image file.
|
|
123
|
+
|
|
124
|
+
## API Endpoint
|
|
125
|
+
|
|
126
|
+
The OCR functionality can be accessed via a FastAPI endpoint:
|
|
127
|
+
|
|
128
|
+
- **POST** `/ocr/`: Upload a receipt image file to perform OCR. The response will contain the extracted text from the receipt.
|
|
129
|
+
|
|
130
|
+
Example usage with cURL:
|
|
131
|
+
|
|
132
|
+
```bash
|
|
133
|
+
curl -X 'POST' \
|
|
134
|
+
'http://localhost:8000/ocr/' \
|
|
135
|
+
-H 'accept: application/json' \
|
|
136
|
+
-H 'Content-Type: multipart/form-data' \
|
|
137
|
+
-F 'file=@images/paper-cash-sell-receipt-vector-23876532.jpg;type=image/jpeg'
|
|
138
|
+
```
|
|
139
|
+
|
|
140
|
+
## Using Gemini
|
|
141
|
+
- Gemini Docs:https://ai.google.dev/tutorials/python_quickstart
|
|
142
|
+
- LinkedIn Post: https://www.linkedin.com/feed/update/urn:li:activity:7145860319150505984/
|
|
143
|
+
|
|
144
|
+
|
|
145
|
+
|
|
146
|
+
|
|
147
|
+
## License
|
|
148
|
+
|
|
149
|
+
This project is licensed under the terms of the MIT license.
|
|
150
|
+
|
|
151
|
+
## References
|
|
152
|
+
- [Automatically OCR’ing Receipts and Scans](https://pyimagesearch.com/2021/10/27/automatically-ocring-receipts-and-scans/)
|
|
153
|
+
|
|
154
|
+
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
# Receipt OCR Engine
|
|
2
|
+
|
|
3
|
+
This repository hosts a script and a Docker-compose setup for performing Optical Character Recognition (OCR) on receipt images.
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
## Star History
|
|
8
|
+
|
|
9
|
+
<a href="https://star-history.com/#bhimrazy/receipt-ocr&Date">
|
|
10
|
+
<picture>
|
|
11
|
+
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=bhimrazy/receipt-ocr&type=Date&theme=dark" />
|
|
12
|
+
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=bhimrazy/receipt-ocr&type=Date" />
|
|
13
|
+
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=bhimrazy/receipt-ocr&type=Date" />
|
|
14
|
+
</picture>
|
|
15
|
+
</a>
|
|
16
|
+
|
|
17
|
+
## Prerequisites
|
|
18
|
+
|
|
19
|
+
- Python 3.x
|
|
20
|
+
- Docker
|
|
21
|
+
- Docker-compose
|
|
22
|
+
|
|
23
|
+
## Installation
|
|
24
|
+
|
|
25
|
+
### Clone the repository
|
|
26
|
+
|
|
27
|
+
```bash
|
|
28
|
+
git clone https://github.com/bhimrazy/receipt-ocr.git
|
|
29
|
+
cd receipt-ocr
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
### Set up Python environment (if not using Docker)
|
|
33
|
+
- Install [tesseract](https://tesseract-ocr.github.io/tessdoc/Installation.html)
|
|
34
|
+
|
|
35
|
+
```bash
|
|
36
|
+
# Create and activate a virtual environment (optional but recommended)
|
|
37
|
+
python -m venv venv
|
|
38
|
+
source venv/bin/activate # For Windows, use venv\Scripts\activate
|
|
39
|
+
|
|
40
|
+
# Install dependencies
|
|
41
|
+
pip install -r requirements.txt
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
## Usage
|
|
45
|
+
|
|
46
|
+
### Running the script locally
|
|
47
|
+
|
|
48
|
+
#### `main.py`
|
|
49
|
+
|
|
50
|
+
The `main.py` script performs OCR on an input image of a receipt.
|
|
51
|
+
|
|
52
|
+
```bash
|
|
53
|
+
python main.py -i images/receipt.jpg
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
Replace `images/receipt.jpg` with the path to your receipt image.
|
|
57
|
+
>Please ensure that the image is well-lit and that the edges of the receipt are clearly visible and detectable within the image.
|
|
58
|
+
<img src="https://github.com/bhimrazy/receipt-ocr/assets/46085301/2ea009f0-9e15-42b2-9f15-063a8ec169f1" alt="Receipt Image" width="300" height="400">
|
|
59
|
+
|
|
60
|
+
|
|
61
|
+
### Using Docker-compose
|
|
62
|
+
|
|
63
|
+
The repository includes a Docker-compose setup for running the OCR engine as a service.
|
|
64
|
+
|
|
65
|
+
```bash
|
|
66
|
+
docker-compose up
|
|
67
|
+
```
|
|
68
|
+
|
|
69
|
+
Once the service is up and running, you can perform OCR on receipt images by sending a POST request to `http://localhost:8000/ocr/` with the image file.
|
|
70
|
+
|
|
71
|
+
## API Endpoint
|
|
72
|
+
|
|
73
|
+
The OCR functionality can be accessed via a FastAPI endpoint:
|
|
74
|
+
|
|
75
|
+
- **POST** `/ocr/`: Upload a receipt image file to perform OCR. The response will contain the extracted text from the receipt.
|
|
76
|
+
|
|
77
|
+
Example usage with cURL:
|
|
78
|
+
|
|
79
|
+
```bash
|
|
80
|
+
curl -X 'POST' \
|
|
81
|
+
'http://localhost:8000/ocr/' \
|
|
82
|
+
-H 'accept: application/json' \
|
|
83
|
+
-H 'Content-Type: multipart/form-data' \
|
|
84
|
+
-F 'file=@images/paper-cash-sell-receipt-vector-23876532.jpg;type=image/jpeg'
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
## Using Gemini
|
|
88
|
+
- Gemini Docs:https://ai.google.dev/tutorials/python_quickstart
|
|
89
|
+
- LinkedIn Post: https://www.linkedin.com/feed/update/urn:li:activity:7145860319150505984/
|
|
90
|
+
|
|
91
|
+
|
|
92
|
+
|
|
93
|
+
|
|
94
|
+
## License
|
|
95
|
+
|
|
96
|
+
This project is licensed under the terms of the MIT license.
|
|
97
|
+
|
|
98
|
+
## References
|
|
99
|
+
- [Automatically OCR’ing Receipts and Scans](https://pyimagesearch.com/2021/10/27/automatically-ocring-receipts-and-scans/)
|
|
100
|
+
|
|
101
|
+
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
|
|
2
|
+
[project]
|
|
3
|
+
name = "receipt-ocr"
|
|
4
|
+
dynamic = ["version"]
|
|
5
|
+
description = "A package for extracting structured data from receipts."
|
|
6
|
+
authors = [{ name = "Bhimraj Yadav", email = "bhimrajyadav977@gmail.com" }]
|
|
7
|
+
license = { file = "LICENSE" }
|
|
8
|
+
readme = "README.md"
|
|
9
|
+
requires-python = ">=3.9"
|
|
10
|
+
classifiers = [
|
|
11
|
+
"Environment :: Console",
|
|
12
|
+
"Natural Language :: English",
|
|
13
|
+
"Development Status :: 4 - Beta",
|
|
14
|
+
"Intended Audience :: Developers",
|
|
15
|
+
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
16
|
+
"Topic :: Scientific/Engineering :: Information Analysis",
|
|
17
|
+
"License :: OSI Approved :: MIT License",
|
|
18
|
+
"Operating System :: OS Independent",
|
|
19
|
+
"Programming Language :: Python :: 3",
|
|
20
|
+
"Programming Language :: Python :: 3.9",
|
|
21
|
+
"Programming Language :: Python :: 3.10",
|
|
22
|
+
"Programming Language :: Python :: 3.11",
|
|
23
|
+
"Programming Language :: Python :: 3.12",
|
|
24
|
+
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
25
|
+
]
|
|
26
|
+
keywords = ["ocr", "receipts", "llm", "tesseract"]
|
|
27
|
+
dependencies = ["openai", "python-dotenv", "Pillow"]
|
|
28
|
+
|
|
29
|
+
[project.urls]
|
|
30
|
+
Homepage = "https://github.com/bhimrazy/receipt-ocr"
|
|
31
|
+
"Bug Tracker" = "https://github.com/bhimrazy/receipt-ocr/issues"
|
|
32
|
+
Documentation = "https://github.com/bhimrazy/receipt-ocr"
|
|
33
|
+
"Source Code" = "https://github.com/bhimrazy/receipt-ocr"
|
|
34
|
+
Download = "https://github.com/bhimrazy/receipt-ocr"
|
|
35
|
+
|
|
36
|
+
[project.scripts]
|
|
37
|
+
receipt-ocr = "receipt_ocr.cli:main"
|
|
38
|
+
|
|
39
|
+
[build-system]
|
|
40
|
+
requires = ["hatchling"]
|
|
41
|
+
build-backend = "hatchling.build"
|
|
42
|
+
|
|
43
|
+
[tool.hatch.version]
|
|
44
|
+
path = "src/receipt_ocr/__about__.py"
|
|
45
|
+
pattern = "__version__ = \"(?P<version>.+)\""
|
|
46
|
+
|
|
47
|
+
[tool.hatch.build]
|
|
48
|
+
include = ["/src/receipt_ocr"]
|
|
49
|
+
|
|
50
|
+
[tool.hatch.metadata]
|
|
51
|
+
allow-direct-references = true
|
|
52
|
+
|
|
53
|
+
[dependency-groups]
|
|
54
|
+
dev = ["pytest", "coverage", "codecov", "pytest-cov"]
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
__version__ = "0.1.0"
|
|
2
|
+
__docs__ = "A package for extracting structured data from receipts."
|
|
3
|
+
__author__ = "Bhimraj Yadav"
|
|
4
|
+
__author_email__ = "bhimrajyadav977@gmail.com"
|
|
5
|
+
__license__ = "MIT"
|
|
6
|
+
__copyright__ = "Copyright (c) 2025 Bhimraj Yadav"
|
|
7
|
+
__homepage__ = "https://github.com/bhimrazy/receipt-ocr"
|
|
8
|
+
|
|
9
|
+
__all__ = [
|
|
10
|
+
"__author__",
|
|
11
|
+
"__author_email__",
|
|
12
|
+
"__copyright__",
|
|
13
|
+
"__docs__",
|
|
14
|
+
"__homepage__",
|
|
15
|
+
"__license__",
|
|
16
|
+
"__version__",
|
|
17
|
+
]
|
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
import argparse
|
|
2
|
+
import os
|
|
3
|
+
import json
|
|
4
|
+
from .providers import OpenAIProvider
|
|
5
|
+
from .parsers import ReceiptParser
|
|
6
|
+
from dotenv import load_dotenv
|
|
7
|
+
|
|
8
|
+
load_dotenv()
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
class ReceiptProcessor:
|
|
12
|
+
"""
|
|
13
|
+
Process a receipt image and return a structured JSON object.
|
|
14
|
+
"""
|
|
15
|
+
|
|
16
|
+
def __init__(self, provider, parser):
|
|
17
|
+
"""
|
|
18
|
+
Initialize the receipt processor.
|
|
19
|
+
"""
|
|
20
|
+
self.provider = provider
|
|
21
|
+
self.parser = parser
|
|
22
|
+
|
|
23
|
+
def process_receipt(self, image_path: str, json_schema: dict, model: str) -> dict:
|
|
24
|
+
"""
|
|
25
|
+
Process a receipt image and return a structured JSON object.
|
|
26
|
+
"""
|
|
27
|
+
response = self.provider.get_response(image_path, json_schema, model)
|
|
28
|
+
return self.parser.parse(response)
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
def main():
|
|
32
|
+
"""
|
|
33
|
+
Main function for the CLI.
|
|
34
|
+
"""
|
|
35
|
+
parser = argparse.ArgumentParser(
|
|
36
|
+
description="Extract information from a receipt image."
|
|
37
|
+
)
|
|
38
|
+
parser.add_argument("image_path", type=str, help="The path to the receipt image.")
|
|
39
|
+
parser.add_argument(
|
|
40
|
+
"--schema_path", type=str, help="The path to a custom JSON schema file."
|
|
41
|
+
)
|
|
42
|
+
parser.add_argument(
|
|
43
|
+
"--model",
|
|
44
|
+
type=str,
|
|
45
|
+
default="gpt-4-vision-preview",
|
|
46
|
+
help="The model to use for the LLM.",
|
|
47
|
+
)
|
|
48
|
+
parser.add_argument("--api_key", type=str, help="The API key for the LLM provider.")
|
|
49
|
+
parser.add_argument(
|
|
50
|
+
"--base_url", type=str, help="The base URL for the LLM provider."
|
|
51
|
+
)
|
|
52
|
+
args = parser.parse_args()
|
|
53
|
+
|
|
54
|
+
# Load the JSON schema
|
|
55
|
+
if args.schema_path:
|
|
56
|
+
with open(args.schema_path, "r") as f:
|
|
57
|
+
json_schema = json.load(f)
|
|
58
|
+
else:
|
|
59
|
+
json_schema = {
|
|
60
|
+
"merchant_name": "string",
|
|
61
|
+
"merchant_address": "string",
|
|
62
|
+
"transaction_date": "string",
|
|
63
|
+
"transaction_time": "string",
|
|
64
|
+
"total_amount": "number",
|
|
65
|
+
"line_items": [
|
|
66
|
+
{
|
|
67
|
+
"item_name": "string",
|
|
68
|
+
"item_quantity": "number",
|
|
69
|
+
"item_price": "number",
|
|
70
|
+
}
|
|
71
|
+
],
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
# Initialize the provider and parser
|
|
75
|
+
provider = OpenAIProvider(api_key=args.api_key, base_url=args.base_url)
|
|
76
|
+
parser = ReceiptParser()
|
|
77
|
+
|
|
78
|
+
# Initialize the processor
|
|
79
|
+
processor = ReceiptProcessor(provider, parser)
|
|
80
|
+
|
|
81
|
+
# Process the receipt
|
|
82
|
+
result = processor.process_receipt(args.image_path, json_schema, args.model)
|
|
83
|
+
|
|
84
|
+
# Print the result
|
|
85
|
+
print(json.dumps(result, indent=4))
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
if __name__ == "__main__":
|
|
89
|
+
main()
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
import json
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
class ReceiptParser:
|
|
5
|
+
"""
|
|
6
|
+
Parser for the LLM's response.
|
|
7
|
+
"""
|
|
8
|
+
|
|
9
|
+
def parse(self, response: str) -> dict:
|
|
10
|
+
"""
|
|
11
|
+
Parse the LLM's response and return a JSON object.
|
|
12
|
+
"""
|
|
13
|
+
try:
|
|
14
|
+
# The response is often wrapped in a code block
|
|
15
|
+
response = response.strip()
|
|
16
|
+
if response.startswith("```json"):
|
|
17
|
+
response = response[7:-4]
|
|
18
|
+
elif response.startswith("```"):
|
|
19
|
+
response = response[3:-3]
|
|
20
|
+
return json.loads(response)
|
|
21
|
+
except json.JSONDecodeError:
|
|
22
|
+
# Handle the case where the response is not valid JSON
|
|
23
|
+
return {"error": "The LLM's response was not valid JSON."}
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
SYSTEM_PROMPT = """
|
|
2
|
+
You are a world-class receipt processing expert. Your task is to accurately extract information from a receipt image and provide it in a structured JSON format.
|
|
3
|
+
|
|
4
|
+
Here is an example of a desired JSON output:
|
|
5
|
+
|
|
6
|
+
```json
|
|
7
|
+
{{
|
|
8
|
+
"merchant_name": "Example Store",
|
|
9
|
+
"merchant_address": "123 Main St, Anytown, USA 12345",
|
|
10
|
+
"transaction_date": "2023-01-01",
|
|
11
|
+
"transaction_time": "12:34:56",
|
|
12
|
+
"total_amount": 75.50,
|
|
13
|
+
"line_items": [
|
|
14
|
+
{{
|
|
15
|
+
"item_name": "Item 1",
|
|
16
|
+
"item_quantity": 2,
|
|
17
|
+
"item_price": 20.00
|
|
18
|
+
}},
|
|
19
|
+
{{
|
|
20
|
+
"item_name": "Item 2",
|
|
21
|
+
"item_quantity": 1,
|
|
22
|
+
"item_price": 35.50
|
|
23
|
+
}}
|
|
24
|
+
]
|
|
25
|
+
}}
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
Please extract the information from the receipt image and provide it in the following JSON schema:
|
|
29
|
+
|
|
30
|
+
```json
|
|
31
|
+
{{json_schema_content}}
|
|
32
|
+
```
|
|
33
|
+
"""
|
|
34
|
+
|
|
35
|
+
USER_PROMPT = "Please extract the information from this receipt image."
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
import os
|
|
2
|
+
from abc import ABC, abstractmethod
|
|
3
|
+
from openai import OpenAI
|
|
4
|
+
from PIL import Image
|
|
5
|
+
import base64
|
|
6
|
+
import io
|
|
7
|
+
import json
|
|
8
|
+
from .prompts import SYSTEM_PROMPT, USER_PROMPT
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
class LLMProvider(ABC):
|
|
12
|
+
"""
|
|
13
|
+
Abstract base class for LLM providers.
|
|
14
|
+
"""
|
|
15
|
+
|
|
16
|
+
@abstractmethod
|
|
17
|
+
def get_response(self, image_path: str, json_schema: dict, model: str) -> str:
|
|
18
|
+
"""
|
|
19
|
+
Get the response from the LLM provider.
|
|
20
|
+
"""
|
|
21
|
+
pass
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
class OpenAIProvider(LLMProvider):
|
|
25
|
+
"""
|
|
26
|
+
LLM provider for OpenAI-compatible APIs.
|
|
27
|
+
"""
|
|
28
|
+
|
|
29
|
+
def __init__(self, api_key: str = None, base_url: str = None):
|
|
30
|
+
"""
|
|
31
|
+
Initialize the OpenAI provider.
|
|
32
|
+
"""
|
|
33
|
+
self.api_key = api_key or os.getenv("OPENAI_API_KEY")
|
|
34
|
+
self.base_url = base_url or os.getenv("OPENAI_BASE_URL")
|
|
35
|
+
self.client = OpenAI(api_key=self.api_key, base_url=self.base_url)
|
|
36
|
+
|
|
37
|
+
def get_response(self, image_path: str, json_schema: dict, model: str) -> str:
|
|
38
|
+
"""
|
|
39
|
+
Get the response from the OpenAI API.
|
|
40
|
+
"""
|
|
41
|
+
# Load the image
|
|
42
|
+
image = Image.open(image_path)
|
|
43
|
+
|
|
44
|
+
# Convert the image to base64
|
|
45
|
+
buffered = io.BytesIO()
|
|
46
|
+
image.save(buffered, format="PNG")
|
|
47
|
+
img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
|
|
48
|
+
|
|
49
|
+
# Create the system prompt
|
|
50
|
+
system_prompt = SYSTEM_PROMPT
|
|
51
|
+
|
|
52
|
+
response = self.client.chat.completions.create(
|
|
53
|
+
model=model,
|
|
54
|
+
response_format={"type": "json_object"},
|
|
55
|
+
messages=[
|
|
56
|
+
{
|
|
57
|
+
"role": "system",
|
|
58
|
+
"content": system_prompt,
|
|
59
|
+
},
|
|
60
|
+
{
|
|
61
|
+
"role": "user",
|
|
62
|
+
"content": [
|
|
63
|
+
{"type": "text", "text": USER_PROMPT},
|
|
64
|
+
{
|
|
65
|
+
"type": "image_url",
|
|
66
|
+
"image_url": {"url": f"data:image/png;base64,{img_str}"},
|
|
67
|
+
},
|
|
68
|
+
],
|
|
69
|
+
},
|
|
70
|
+
],
|
|
71
|
+
)
|
|
72
|
+
|
|
73
|
+
return response.choices[0].message.content
|