Duplicate from deprem-ml/deprem-ocr

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -0,0 +1,13 @@
+---
+title: Deprem OCR
+emoji: 👀
+colorFrom: green
+colorTo: blue
+sdk: gradio
+sdk_version: 3.17.0
+app_file: app.py
+pinned: true
+duplicated_from: deprem-ml/deprem-ocr
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,141 @@
+from easyocr import Reader
+import gradio as gr
+import openai
+import ast
+import os
+
+from openai_api import OpenAI_API
+import utils
+
+
+openai.api_key = os.getenv("API_KEY")
+reader = Reader(["tr"])
+
+
+def get_text(input_img):
+    result = reader.readtext(input_img, detail=0)
+    return " ".join(result)
+
+
+# Submit button
+def get_parsed_address(input_img):
+
+    address_full_text = get_text(input_img)
+    return openai_response(address_full_text)
+
+
+# Open API on change
+def text_dict(input):
+    eval_result = ast.literal_eval(input)
+    utils.write_db(eval_result)
+
+    return (
+        str(eval_result["city"]),
+        str(eval_result["distinct"]),
+        str(eval_result["neighbourhood"]),
+        str(eval_result["street"]),
+        str(eval_result["address"]),
+        str(eval_result["tel"]),
+        str(eval_result["name_surname"]),
+        str(eval_result["no"]),
+    )
+
+
+def openai_response(ocr_input):
+    prompt = f"""Tabular Data Extraction You are a highly intelligent and accurate tabular data extractor from 
+            plain text input and especially from emergency text that carries address information, your inputs can be text 
+            of arbitrary size, but the output should be in [{{'tabular': {{'entity_type': 'entity'}} }}] JSON format Force it 
+            to only extract keys that are shared as an example in the examples section, if a key value is not found in the 
+            text input, then it should be ignored. Have only city, distinct, neighbourhood, 
+            street, no, tel, name_surname, address Examples: Input: Deprem sırasında evimizde yer alan adresimiz: İstanbul, 
+            Beşiktaş, Yıldız Mahallesi, Cumhuriyet Caddesi No: 35, cep telefonu numaram 5551231256, adim Ahmet Yilmaz 
+            Output: {{'city': 'İstanbul', 'distinct': 'Beşiktaş', 'neighbourhood': 'Yıldız Mahallesi', 'street': 'Cumhuriyet Caddesi', 'no': '35', 'tel': '5551231256', 'name_surname': 'Ahmet Yılmaz', 'address': 'İstanbul, Beşiktaş, Yıldız Mahallesi, Cumhuriyet Caddesi No: 35'}}
+            Input: {ocr_input}
+            Output:
+        """
+
+    openai_client = OpenAI_API()
+    response = openai_client.single_request(prompt)
+    resp = response["choices"][0]["text"]
+    print(resp)
+    resp = eval(resp.replace("'{", "{").replace("}'", "}"))
+    resp["input"] = ocr_input
+    dict_keys = [
+        "city",
+        "distinct",
+        "neighbourhood",
+        "street",
+        "no",
+        "tel",
+        "name_surname",
+        "address",
+        "input",
+    ]
+    for key in dict_keys:
+        if key not in resp.keys():
+            resp[key] = ""
+    return resp
+
+def ner_response(ocr_input):
+    API_URL = "https://api-inference.huggingface.co/models/deprem-ml/deprem-ner"
+    headers = {"Authorization": "Bearer xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
+
+    def query(payload):
+        response = requests.post(API_URL, headers=headers, json=payload)
+        return response.json()
+
+    output = query({
+        "inputs": ocr_input,
+    })
+    return output
+
+# User Interface
+with gr.Blocks() as demo:
+    gr.Markdown(
+        """
+    # Enkaz Bildirme Uygulaması
+    """
+    )
+    gr.Markdown(
+        "Bu uygulamada ekran görüntüsü sürükleyip bırakarak AFAD'a enkaz bildirimi yapabilirsiniz. Mesajı metin olarak da girebilirsiniz, tam adresi ayrıştırıp döndürür. API olarak kullanmak isterseniz sayfanın en altında use via api'ya tıklayın."
+    )
+    with gr.Row():
+        img_area = gr.Image(label="Ekran Görüntüsü yükleyin 👇")
+        ocr_result = gr.Textbox(label="Metin yükleyin 👇 ")
+    open_api_text = gr.Textbox(label="Tam Adres")
+    submit_button = gr.Button(label="Yükle")
+    with gr.Column():
+        with gr.Row():
+            city = gr.Textbox(label="İl")
+            distinct = gr.Textbox(label="İlçe")
+        with gr.Row():
+            neighbourhood = gr.Textbox(label="Mahalle")
+            street = gr.Textbox(label="Sokak/Cadde/Bulvar")
+        with gr.Row():
+            tel = gr.Textbox(label="Telefon")
+        with gr.Row():
+            name_surname = gr.Textbox(label="İsim Soyisim")
+            address = gr.Textbox(label="Adres")
+        with gr.Row():
+            no = gr.Textbox(label="Kapı No")
+
+    submit_button.click(
+        get_parsed_address,
+        inputs=img_area,
+        outputs=open_api_text,
+        api_name="upload_image",
+    )
+
+    ocr_result.change(
+        openai_response, ocr_result, open_api_text, api_name="upload-text"
+    )
+
+    open_api_text.change(
+        text_dict,
+        open_api_text,
+        [city, distinct, neighbourhood, street, address, tel, name_surname, no],
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()

openai_api.py

@@ -0,0 +1,30 @@
+import openai
+import os
+
+class OpenAI_API:
+    def __init__(self):
+        self.openai_api_key = ""
+
+    def single_request(self, address_text):
+
+        openai.api_type = "azure"
+        openai.api_base = "https://damlaopenai.openai.azure.com/"
+        openai.api_version = "2022-12-01"
+        openai.api_key = os.getenv("API_KEY")
+
+        response = openai.Completion.create(
+            engine="Davinci-003",
+            prompt=address_text,
+            temperature=0.9,
+            max_tokens=256,
+            top_p=1.0,
+            n=1,
+            logprobs=0,
+            echo=False,
+            stop=None,
+            frequency_penalty=0,
+            presence_penalty=0,
+            best_of=1,
+        )
+
+        return response

requirements.txt

@@ -0,0 +1,5 @@
+openai
+Pillow
+easyocr
+gradio
+deta

utils.py

@@ -0,0 +1,35 @@
+import cv2
+import csv
+import json
+from deta import Deta
+import os
+
+
+def preprocess_img(inp_image):
+    gray = cv2.cvtColor(inp_image, cv2.COLOR_BGR2GRAY)
+    gray_img = cv2.bitwise_not(gray)
+    return gray_img
+
+def save_csv(mahalle, il, sokak, apartman):
+    adres_full = [mahalle, il, sokak, apartman]
+
+    with open("adress_book.csv", "a", encoding="utf-8") as f:
+        write = csv.writer(f)
+        write.writerow(adres_full)
+    return adres_full
+
+
+def get_json(mahalle, il, sokak, apartman):
+    adres = {"mahalle": mahalle, "il": il, "sokak": sokak, "apartman": apartman}
+    dump = json.dumps(adres, indent=4, ensure_ascii=False)
+    return dump
+
+
+def write_db(data_dict):
+    # 2) initialize with a project key
+    deta_key = os.getenv('DETA_KEY')
+    deta = Deta(deta_key)
+
+    # 3) create and use as many DBs as you want!
+    users = deta.Base("deprem-ocr")
+    users.insert(data_dict)