From f12bd3e16fd3fed5e571ce834fd50a9ebfd49d22 Mon Sep 17 00:00:00 2001
From: neozhu <neo.js.cn@gmail.com>
Date: Wed, 13 Mar 2024 13:08:54 +0000
Subject: [PATCH 1/7] =?UTF-8?q?=F0=9F=8D=97=20Add=20new=20feature:=20Imple?=
 =?UTF-8?q?ment=20Chinese=20label=20recognition=20with=20PaddleOCR?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../examples/paddleocr/.dockerignore          |  11 ++
 label_studio_ml/examples/paddleocr/Dockerfile |  32 +++++
 label_studio_ml/examples/paddleocr/README.md  | 125 ++++++++++++++++++
 label_studio_ml/examples/paddleocr/_wsgi.py   | 119 +++++++++++++++++
 .../examples/paddleocr/docker-compose.yml     |  27 ++++
 .../examples/paddleocr/example.env            |  11 ++
 .../examples/paddleocr/paddleocr_ch.py        | 122 +++++++++++++++++
 .../examples/paddleocr/requirements.txt       |  13 ++
 .../examples/paddleocr/supervisord.conf       |  24 ++++
 label_studio_ml/examples/paddleocr/uwsgi.ini  |  10 ++
 10 files changed, 494 insertions(+)
 create mode 100644 label_studio_ml/examples/paddleocr/.dockerignore
 create mode 100644 label_studio_ml/examples/paddleocr/Dockerfile
 create mode 100644 label_studio_ml/examples/paddleocr/README.md
 create mode 100644 label_studio_ml/examples/paddleocr/_wsgi.py
 create mode 100644 label_studio_ml/examples/paddleocr/docker-compose.yml
 create mode 100644 label_studio_ml/examples/paddleocr/example.env
 create mode 100644 label_studio_ml/examples/paddleocr/paddleocr_ch.py
 create mode 100644 label_studio_ml/examples/paddleocr/requirements.txt
 create mode 100644 label_studio_ml/examples/paddleocr/supervisord.conf
 create mode 100644 label_studio_ml/examples/paddleocr/uwsgi.ini

diff --git a/label_studio_ml/examples/paddleocr/.dockerignore b/label_studio_ml/examples/paddleocr/.dockerignore
new file mode 100644
index 00000000..164c0f16
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/.dockerignore
@@ -0,0 +1,11 @@
+Dockerfile
+README.md
+*.pyc
+*.pyo
+*.pyd
+__pycache__
+.pytest_cache
+.idea
+docker-compose.yml
+data
+logs
\ No newline at end of file
diff --git a/label_studio_ml/examples/paddleocr/Dockerfile b/label_studio_ml/examples/paddleocr/Dockerfile
new file mode 100644
index 00000000..983e1d57
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/Dockerfile
@@ -0,0 +1,32 @@
+FROM python:3.10
+
+WORKDIR /tmp
+COPY requirements.txt .
+
+ENV PYTHONUNBUFFERED=True \
+    PORT=${PORT:-9090} \
+    PIP_CACHE_DIR=/.cache
+
+# Installing libGL
+RUN apt-get update && apt-get install -y \
+    libgl1-mesa-dev
+
+RUN apt-get install -y poppler-utils libpoppler-cpp-dev libglib2.0-0
+
+
+RUN pip install --upgrade pip \
+ && pip install -r requirements.txt
+ 
+
+#COPY uwsgi.ini /etc/uwsgi/
+COPY supervisord.conf /etc/supervisor/conf.d/
+
+WORKDIR /app
+
+COPY * /app/
+
+EXPOSE 9090
+
+CMD ["/usr/local/bin/supervisord", \
+     "-c", \
+     "/etc/supervisor/conf.d/supervisord.conf"]
diff --git a/label_studio_ml/examples/paddleocr/README.md b/label_studio_ml/examples/paddleocr/README.md
new file mode 100644
index 00000000..0dc24ca4
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/README.md
@@ -0,0 +1,125 @@
+## Interactive BBOX OCR using Tesseract
+Using an OCR engine for Interactive ML-Assisted Labelling, this functionality
+can speed up annotation for layout detection, classification and recognition
+models.
+
+Tesseract is used for OCR but minimal adaptation is needed to connect other OCR
+engines or models.
+
+Tested againt Label Studio 1.10.1, with basic support for both Label Studio
+Local File Storage and S3-compatible storage, with a example data storage with
+Minio.
+
+### Setup process
+0. Download and install Docker with Docker Compose. For MacOS and Windows users,
+   we suggest using Docker Desktop. You will also need to have git installed.
+
+1. Launch LabelStudio.
+
+   ```
+   docker run -it \
+      -p 8080:8080 \
+      -v `pwd`/mydata:/label-studio/data \
+      heartexlabs/label-studio:latest
+   ```
+
+   Optionally, you may enable local file serving in Label Studio
+
+   ```
+   docker run -it \
+      -p 8080:8080 \
+      -v `pwd`/mydata:/label-studio/data \
+      --env LABEL_STUDIO_LOCAL_FILES_SERVING_ENABLED=true \
+      --env LABEL_STUDIO_LOCAL_FILES_DOCUMENT_ROOT=/label-studio/data/images \
+      heartexlabs/label-studio:latest
+   ```
+   If you're using local file serving, be sure to get a copy of the API token from
+   Label Studio to connect the model.
+
+2. Create a new project for Tesseract OCR. In the project **Settings** set up the **Labeling Interface**.
+
+   Fill in the following template code. It's important to specify `smart="true"` in RectangleLabels.
+   ```
+   <View>    
+      <Image name="image" value="$ocr" zoom="true" zoomControl="false"
+            rotateControl="true" width="100%" height="100%"
+            maxHeight="auto" maxWidth="auto"/>
+      
+      <RectangleLabels name="bbox" toName="image" strokeWidth="1" smart="true">
+         <Label value="Label1" background="green"/>
+         <Label value="Label2" background="blue"/>
+         <Label value="Label3" background="red"/>
+      </RectangleLabels>
+
+      <TextArea name="transcription" toName="image" 
+      editable="true" perRegion="true" required="false" 
+      maxSubmissions="1" rows="5" placeholder="Recognized Text" 
+      displayMode="region-list"/>
+   </View>
+   ```
+
+3. Download the Label Studio Machine Learning backend backend repository.
+   ```
+   git clone https://github.com/humansignal/label-studio-ml-backend
+   cd label-studio-ml-backend/label_studio_ml/examples/tesseract
+   ```
+
+4. Configure the backend and the Minio server by editing the `example.env` file. If you opted to use Label Studio
+   Local File Storage, be sure to set the `LABEL_STUDIO_HOST` and `LABEL_STUDIO_ACCESS_TOKEN` variables. If you're
+   using the Minio storage example, set the `MINIO_ROOT_USER` AND `MINIO_ROOT_PASSWORD` variables, and make the 
+   `AWS_ACCESS_KEY_ID` AND `AWS_SECRET_ACCESS_KEY` variables equal to those values. You may optionally connect to your
+   own AWS cloud storage by setting those variables. Note that you may need to make additional software changes to the
+   `tesseract.py` file to match your particular infrastructure configuration.
+
+   ```
+   LABEL_STUDIO_HOST=http://host.docker.internal:8080
+   LABEL_STUDIO_ACCESS_TOKEN=<optional token for local file access>
+
+   AWS_ACCESS_KEY_ID=<set to MINIO_ROOT_USER for minio example>
+   AWS_SECRET_ACCESS_KEY=<set to MINIO_ROOT_PASSWORD for minio example>
+   AWS_ENDPOINT=http://host.docker.internal:9000
+
+   MINIO_ROOT_USER=<username>
+   MINIO_ROOT_PASSWORD=<password>
+   MINIO_API_CORS_ALLOW_ORIGIN=*
+   ```
+
+5. Start the Tesseract and minio servers.
+
+   ```
+   docker compose up
+   ```
+
+6. Upload tasks.
+
+   If you're using the Label Studio Local File Storage option, upload images
+   directly to Label Studio using the Label Studio interface.
+
+   If you're using minio for task storage, log into the minio control panel at
+   `http://localhost:9001`. Create a new bucket, making a note of the name, and
+   upload your tasks to minio. Set the visibility of the tasks to be public.
+   Furtner configuration of your cloud storage is beyond the scope of this
+   tutorial, and you will want to configure your storage according to your
+   particular needs. 
+
+7. If using minio, In the project **Settings**, set up the **Cloud storage**.
+
+   Add your source S3 storage by connecting to the S3 Endpoint
+   `http://host.docker.internal:9000`, using the bucket name from the previous
+   step, and Access Key ID and Secret Access Key as configured in the previous
+   steps. For the minio example, uncheck **Use pre-signed URLS**. Check the
+   connection and save the storage.
+
+8. Open the **Machine Learning** settings and click **Add Model**.
+
+   Add the URL `http://host.docker.internal:9090` and save the model as an ML backend.
+
+9. To use this functionality, activate `Auto-Annotation` and use `Autotdetect` rectangle for drawing boxes
+
+Example below :
+
+![ls_demo_ocr](https://user-images.githubusercontent.com/17755198/165186574-05f0236f-a5f2-4179-ac90-ef11123927bc.gif)
+
+Reference links : 
+- https://labelstud.io/blog/Improve-OCR-quality-with-Tesseract-and-Label-Studio.html
+- https://labelstud.io/blog/release-130.html
diff --git a/label_studio_ml/examples/paddleocr/_wsgi.py b/label_studio_ml/examples/paddleocr/_wsgi.py
new file mode 100644
index 00000000..4b8f0e59
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/_wsgi.py
@@ -0,0 +1,119 @@
+import json
+import os
+import argparse
+import logging
+import logging.config
+
+logging.config.dictConfig({
+  "version": 1,
+  "formatters": {
+    "standard": {
+      "format": "[%(asctime)s] [%(levelname)s] [%(name)s::%(funcName)s::%(lineno)d] %(message)s"
+    }
+  },
+  "handlers": {
+    "console": {
+      "class": "logging.StreamHandler",
+      "level": "DEBUG",
+      "stream": "ext://sys.stdout",
+      "formatter": "standard"
+    }
+  },
+  "root": {
+    "level": "ERROR",
+    "handlers": [
+      "console"
+    ],
+    "propagate": True
+  }
+})
+
+from label_studio_ml.api import init_app
+from paddleocr_ch import paddleocrLabeling
+
+
+_DEFAULT_CONFIG_PATH = os.path.join(os.path.dirname(__file__), 'config.json')
+
+
+def get_kwargs_from_config(config_path=_DEFAULT_CONFIG_PATH):
+    if not os.path.exists(config_path):
+        return dict()
+    with open(config_path) as f:
+        config = json.load(f)
+    assert isinstance(config, dict)
+    return config
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Label studio')
+    parser.add_argument(
+        '-p', '--port', dest='port', type=int, default=9090,
+        help='Server port')
+    parser.add_argument(
+        '--host', dest='host', type=str, default='0.0.0.0',
+        help='Server host')
+    parser.add_argument(
+        '--kwargs', '--with', dest='kwargs', metavar='KEY=VAL', nargs='+', type=lambda kv: kv.split('='),
+        help='Additional LabelStudioMLBase model initialization kwargs')
+    parser.add_argument(
+        '-d', '--debug', dest='debug', action='store_true',
+        help='Switch debug mode')
+    parser.add_argument(
+        '--log-level', dest='log_level', choices=['DEBUG', 'INFO', 'WARNING', 'ERROR'], default=None,
+        help='Logging level')
+    parser.add_argument(
+        '--model-dir', dest='model_dir', default=os.path.dirname(__file__),
+        help='Directory where models are stored (relative to the project directory)')
+    parser.add_argument(
+        '--check', dest='check', action='store_true',
+        help='Validate model instance before launching server')
+
+    args = parser.parse_args()
+
+    # setup logging level
+    if args.log_level:
+        logging.root.setLevel(args.log_level)
+
+    def isfloat(value):
+        try:
+            float(value)
+            return True
+        except ValueError:
+            return False
+
+    def parse_kwargs():
+        param = dict()
+        for k, v in args.kwargs:
+            if v.isdigit():
+                param[k] = int(v)
+            elif v == 'True' or v == 'true':
+                param[k] = True
+            elif v == 'False' or v == 'False':
+                param[k] = False
+            elif isfloat(v):
+                param[k] = float(v)
+            else:
+                param[k] = v
+        return param
+
+    kwargs = get_kwargs_from_config()
+
+    if args.kwargs:
+        kwargs.update(parse_kwargs())
+
+    if args.check:
+        print('Check "' + paddleocrLabeling.__name__ + '" instance creation..')
+        model = paddleocrLabeling(**kwargs)
+
+    app = init_app(
+        model_class=paddleocrLabeling,
+        **kwargs
+    )
+
+    app.run(host=args.host, port=args.port, debug=args.debug)
+
+else:
+    # for uWSGI use
+    app = init_app(
+        model_class=paddleocrLabeling
+    )
diff --git a/label_studio_ml/examples/paddleocr/docker-compose.yml b/label_studio_ml/examples/paddleocr/docker-compose.yml
new file mode 100644
index 00000000..e9156bd0
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/docker-compose.yml
@@ -0,0 +1,27 @@
+version: "3.8"
+
+services:
+
+  paddleocr-backend:
+    container_name: paddleocr-backend
+    build: .
+    env_file:
+      - example.env
+    ports:
+      - 9090:9090
+    volumes:
+      - "./data/server:/data"
+      - "./logs:/tmp"
+  
+  minio:
+    container_name: minio
+    image: bitnami/minio:latest
+    env_file:
+      - example.env
+    ports:
+      - 9003:9000
+      - 9004:9001
+    volumes:
+      - ".data/storage:/data"
+    command: server /data --console-address ":9001"
+
diff --git a/label_studio_ml/examples/paddleocr/example.env b/label_studio_ml/examples/paddleocr/example.env
new file mode 100644
index 00000000..dad76777
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/example.env
@@ -0,0 +1,11 @@
+LABEL_STUDIO_HOST=http://10.33.1.37:8089
+LABEL_STUDIO_ACCESS_TOKEN=9075ad7f2794f7d670a752dcf0eb1b6d177d08ff
+
+AWS_ACCESS_KEY_ID=admin
+AWS_SECRET_ACCESS_KEY=9075ad7f2
+AWS_ENDPOINT=http://10.33.1.37:9000
+
+MINIO_ROOT_USER=admin
+MINIO_ROOT_PASSWORD=9075ad7f2
+MINIO_API_CORS_ALLOW_ORIGIN=*
+MINIO_OPTS="--console-address :9001"
\ No newline at end of file
diff --git a/label_studio_ml/examples/paddleocr/paddleocr_ch.py b/label_studio_ml/examples/paddleocr/paddleocr_ch.py
new file mode 100644
index 00000000..fcb8d293
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/paddleocr_ch.py
@@ -0,0 +1,122 @@
+from PIL import Image
+import io
+from paddleocr import PaddleOCR
+from label_studio_ml.model import LabelStudioMLBase
+from label_studio_ml.utils import get_image_local_path
+import logging
+import os
+import json
+import boto3
+import numpy as np
+
+logger = logging.getLogger(__name__)
+# just for chinese
+ocr = PaddleOCR(use_angle_cls=True, lang="ch")  
+
+LABEL_STUDIO_ACCESS_TOKEN = os.environ.get("LABEL_STUDIO_ACCESS_TOKEN")
+LABEL_STUDIO_HOST         = os.environ.get("LABEL_STUDIO_HOST")
+
+AWS_ACCESS_KEY_ID     = os.environ.get("AWS_ACCESS_KEY_ID")
+AWS_SECRET_ACCESS_KEY = os.environ.get("AWS_SECRET_ACCESS_KEY")
+AWS_SESSION_TOKEN     = os.environ.get("AWS_SESSION_TOKEN")
+AWS_ENDPOINT          = os.environ.get("AWS_ENDPOINT")
+
+S3_TARGET = boto3.resource('s3',
+        endpoint_url=AWS_ENDPOINT,
+        aws_access_key_id=AWS_ACCESS_KEY_ID,
+        aws_secret_access_key=AWS_SECRET_ACCESS_KEY,
+        aws_session_token=AWS_SESSION_TOKEN,
+        config=boto3.session.Config(signature_version='s3v4'),
+        verify=False)
+
+class paddleocrLabeling(LabelStudioMLBase):
+
+    @staticmethod
+    def load_image(img_path_url):
+        # load an s3 image, this is very basic demonstration code
+        # you may need to modify to fit your own needs
+        if img_path_url.startswith("s3:"):
+            bucket_name = img_path_url.split("/")[2]
+            key = "/".join(img_path_url.split("/")[3:])
+
+            obj = S3_TARGET.Object(bucket_name, key).get()
+            data =  obj['Body'].read()
+            image = Image.open(io.BytesIO(data))
+            return image
+        else:
+            filepath = get_image_local_path(img_path_url,
+                    label_studio_access_token=LABEL_STUDIO_ACCESS_TOKEN,
+                    label_studio_host=LABEL_STUDIO_HOST)
+            return  Image.open(filepath)
+
+
+    def predict(self, tasks, **kwargs):
+        # extract task meta data: labels, from_name, to_name and other
+        task = tasks[0]
+        img_path_url = task["data"]["ocr"]
+
+
+        context = kwargs.get('context')
+        if context:
+            if not context["result"]:
+                return []
+
+            IMG = self.load_image(img_path_url)
+
+            result = context.get('result')[0]
+            meta = self._extract_meta({**task, **result})
+            x = meta["x"]*meta["original_width"]/100
+            y = meta["y"]*meta["original_height"]/100
+            w = meta["width"]*meta["original_width"]/100
+            h = meta["height"]*meta["original_height"]/100
+
+            crop_img = IMG.crop((x, y, x + w, y + h))
+
+            # 使用 PaddleOCR 进行文字识别
+            ocr_result = ocr.ocr(np.array(crop_img), cls=True)
+            # PaddleOCR 返回结果的格式是 [(区域, (文本, 置信度))], 我们只关心文本部分
+            ocr_texts = [line[1][0] for line in ocr_result[0]]  # 提取所有识别的文本行
+            result_text = "\n".join(ocr_texts).strip()  # 将文本行合并为一个字符串
+            meta["text"] = result_text
+            temp = {
+                "original_width": meta["original_width"],
+                "original_height": meta["original_height"],
+                "image_rotation": 0,
+                "value": {
+                    "x": x/meta["original_width"]*100,
+                    "y": y/meta["original_height"]*100,
+                    "width": w/meta["original_width"]*100,
+                    "height": h/meta["original_height"]*100,
+                    "rotation": 0,
+                    "text": [
+                    meta["text"]
+                    ]
+                },
+                "id": meta["id"],
+                "from_name": "transcription",
+                "to_name": meta['to_name'],
+                "type": "textarea",
+                "origin": "manual"
+            }
+            return [{
+                'result': [temp, result],
+                'score': 0
+            }]
+        else:
+            return []
+
+    @staticmethod
+    def _extract_meta(task):
+        meta = dict()
+        if task:
+            meta['id'] = task['id']
+            meta['from_name'] = task['from_name']
+            meta['to_name'] = task['to_name']
+            meta['type'] = task['type']
+            meta['x'] = task['value']['x']
+            meta['y'] = task['value']['y']
+            meta['width'] = task['value']['width']
+            meta['height'] = task['value']['height']
+            meta["original_width"] = task['original_width']
+            meta["original_height"] = task['original_height']
+        return meta
diff --git a/label_studio_ml/examples/paddleocr/requirements.txt b/label_studio_ml/examples/paddleocr/requirements.txt
new file mode 100644
index 00000000..03a4aa71
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/requirements.txt
@@ -0,0 +1,13 @@
+label-studio-ml
+Jinja2
+boto3
+click
+itsdangerous
+opencv-contrib-python-headless
+paddlepaddle==2.5.2
+paddleocr==2.7.0.3
+rq
+supervisor
+werkzeug
+gunicorn
+numpy
diff --git a/label_studio_ml/examples/paddleocr/supervisord.conf b/label_studio_ml/examples/paddleocr/supervisord.conf
new file mode 100644
index 00000000..743c5110
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/supervisord.conf
@@ -0,0 +1,24 @@
+[supervisord]
+nodaemon = true
+loglevel = info
+logfile = supervisord.log
+
+[inet_http_server]
+port=127.0.0.1:9001
+
+[supervisorctl]
+serverurl=http://127.0.0.1:9001
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
+
+
+[program:wsgi]
+command = gunicorn --preload --bind :"%(ENV_PORT)s" --workers 1 --threads 8 --timeout 0 _wsgi:app
+autostart = true
+autorestart = true
+stopsignal = QUIT
+stderr_logfile = /dev/stderr
+stderr_logfile_maxbytes = 0
+stdout_logfile = /dev/stdout
+stdout_logfile_maxbytes = 0
diff --git a/label_studio_ml/examples/paddleocr/uwsgi.ini b/label_studio_ml/examples/paddleocr/uwsgi.ini
new file mode 100644
index 00000000..5a200902
--- /dev/null
+++ b/label_studio_ml/examples/paddleocr/uwsgi.ini
@@ -0,0 +1,10 @@
+[uwsgi]
+protocol = http
+socket = 0.0.0.0:9090
+module = _wsgi:app
+master = true
+processes = 1
+vacuum = true
+die-on-term = true
+
+pidfile = /tmp/%n.pid
\ No newline at end of file

From 49bc04a7462bdddc28920e8f07230ae1b7d5a711 Mon Sep 17 00:00:00 2001
From: neozhu <neo.js.cn@gmail.com>
Date: Wed, 13 Mar 2024 13:10:47 +0000
Subject: [PATCH 2/7] =?UTF-8?q?=F0=9F=8D=92=20add=20recognition=20support?=
 =?UTF-8?q?=20for=20both=20German=20and=20Chinese=20languages.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 label_studio_ml/examples/tesseract/Dockerfile    |  3 +++
 .../examples/tesseract/docker-compose.yml        |  8 ++++----
 label_studio_ml/examples/tesseract/example.env   | 16 ++++++++--------
 .../examples/tesseract/requirements.txt          |  3 +--
 label_studio_ml/examples/tesseract/tesseract.py  |  2 +-
 5 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/label_studio_ml/examples/tesseract/Dockerfile b/label_studio_ml/examples/tesseract/Dockerfile
index 07d83eba..7dab17f2 100644
--- a/label_studio_ml/examples/tesseract/Dockerfile
+++ b/label_studio_ml/examples/tesseract/Dockerfile
@@ -11,6 +11,9 @@ ENV PYTHONUNBUFFERED=True \
 RUN apt update -y \
  && apt upgrade -y
 RUN apt install tesseract-ocr git -y
+RUN apt install tesseract-ocr-chi-sim
+RUN apt install tesseract-ocr-chi-tra
+RUN apt install tesseract-ocr-deu
 
 RUN pip install --upgrade pip \
  && pip install -r requirements.txt
diff --git a/label_studio_ml/examples/tesseract/docker-compose.yml b/label_studio_ml/examples/tesseract/docker-compose.yml
index a32ddf40..62c92ed8 100644
--- a/label_studio_ml/examples/tesseract/docker-compose.yml
+++ b/label_studio_ml/examples/tesseract/docker-compose.yml
@@ -12,15 +12,15 @@ services:
     volumes:
       - "./data/server:/data"
       - "./logs:/tmp"
-
+  
   minio:
     container_name: minio
-    image: quay.io/minio/minio
+    image: bitnami/minio:latest
     env_file:
       - example.env
     ports:
-      - 9000:9000
-      - 9001:9001
+      - 9003:9000
+      - 9004:9001
     volumes:
       - ".data/storage:/data"
     command: server /data --console-address ":9001"
diff --git a/label_studio_ml/examples/tesseract/example.env b/label_studio_ml/examples/tesseract/example.env
index ac402a72..dad76777 100644
--- a/label_studio_ml/examples/tesseract/example.env
+++ b/label_studio_ml/examples/tesseract/example.env
@@ -1,11 +1,11 @@
-LABEL_STUDIO_HOST=http://host.docker.internal:8080
-LABEL_STUDIO_ACCESS_TOKEN=<access token if using local file storage>
+LABEL_STUDIO_HOST=http://10.33.1.37:8089
+LABEL_STUDIO_ACCESS_TOKEN=9075ad7f2794f7d670a752dcf0eb1b6d177d08ff
 
-AWS_ACCESS_KEY_ID=<MINIO_ROOT_USER if using minio example>
-AWS_SECRET_ACCESS_KEY=<MINIO_ROOT_PASSWORD if using minio example>
-AWS_ENDPOINT=http://host.docker.internal:9000
+AWS_ACCESS_KEY_ID=admin
+AWS_SECRET_ACCESS_KEY=9075ad7f2
+AWS_ENDPOINT=http://10.33.1.37:9000
 
-MINIO_ROOT_USER=<admin username>
-MINIO_ROOT_PASSWORD=<admin password>
+MINIO_ROOT_USER=admin
+MINIO_ROOT_PASSWORD=9075ad7f2
 MINIO_API_CORS_ALLOW_ORIGIN=*
-
+MINIO_OPTS="--console-address :9001"
\ No newline at end of file
diff --git a/label_studio_ml/examples/tesseract/requirements.txt b/label_studio_ml/examples/tesseract/requirements.txt
index 2167e716..c8b62aed 100644
--- a/label_studio_ml/examples/tesseract/requirements.txt
+++ b/label_studio_ml/examples/tesseract/requirements.txt
@@ -7,5 +7,4 @@ rq
 supervisor
 werkzeug
 gunicorn
-
-label-studio-ml @ git+https://github.com/heartexlabs/label-studio-ml-backend.git
+label-studio-ml
diff --git a/label_studio_ml/examples/tesseract/tesseract.py b/label_studio_ml/examples/tesseract/tesseract.py
index 7d42d13a..a5be65d0 100644
--- a/label_studio_ml/examples/tesseract/tesseract.py
+++ b/label_studio_ml/examples/tesseract/tesseract.py
@@ -10,7 +10,7 @@
 
 logger = logging.getLogger(__name__)
 global OCR_config
-OCR_config = "--psm 6"
+OCR_config = "--psm 6 -l chi_sim+eng+deu"
 
 LABEL_STUDIO_ACCESS_TOKEN = os.environ.get("LABEL_STUDIO_ACCESS_TOKEN")
 LABEL_STUDIO_HOST         = os.environ.get("LABEL_STUDIO_HOST")

From e032e5cfa226200dcdcfc46c4ab6fc1fb91c5981 Mon Sep 17 00:00:00 2001
From: neozhu <neo.js.cn@gmail.com>
Date: Thu, 14 Mar 2024 11:20:47 +0000
Subject: [PATCH 3/7] =?UTF-8?q?=E2=9C=A8=20Support=20Basic=20Auth=20suppor?=
 =?UTF-8?q?t?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 label_studio_ml/examples/paddleocr/_wsgi.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/label_studio_ml/examples/paddleocr/_wsgi.py b/label_studio_ml/examples/paddleocr/_wsgi.py
index 4b8f0e59..2718c4b1 100644
--- a/label_studio_ml/examples/paddleocr/_wsgi.py
+++ b/label_studio_ml/examples/paddleocr/_wsgi.py
@@ -68,6 +68,14 @@ def get_kwargs_from_config(config_path=_DEFAULT_CONFIG_PATH):
         '--check', dest='check', action='store_true',
         help='Validate model instance before launching server')
 
+    parser.add_argument('--basic-auth-user',
+                        default=os.environ.get('ML_SERVER_BASIC_AUTH_USER', None),
+                        help='Basic auth user')
+
+    parser.add_argument('--basic-auth-pass',
+                        default=os.environ.get('ML_SERVER_BASIC_AUTH_PASS', None),
+                        help='Basic auth pass')
+    
     args = parser.parse_args()
 
     # setup logging level
@@ -107,6 +115,8 @@ def parse_kwargs():
 
     app = init_app(
         model_class=paddleocrLabeling,
+        basic_auth_user=args.basic_auth_user, 
+        basic_auth_pass=args.basic_auth_pass,
         **kwargs
     )
 

From c85b0e8ede49a3c8f94dd1026bda78a2a0ab2f21 Mon Sep 17 00:00:00 2001
From: neozhu <neo.js.cn@gmail.com>
Date: Thu, 14 Mar 2024 11:21:08 +0000
Subject: [PATCH 4/7] =?UTF-8?q?=E2=9C=A8=20change=20readme?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 label_studio_ml/examples/paddleocr/README.md | 28 ++++++++++++++------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/label_studio_ml/examples/paddleocr/README.md b/label_studio_ml/examples/paddleocr/README.md
index 0dc24ca4..43fa3365 100644
--- a/label_studio_ml/examples/paddleocr/README.md
+++ b/label_studio_ml/examples/paddleocr/README.md
@@ -1,9 +1,9 @@
-## Interactive BBOX OCR using Tesseract
+## Interactive BBOX OCR using PaddleOCR
 Using an OCR engine for Interactive ML-Assisted Labelling, this functionality
 can speed up annotation for layout detection, classification and recognition
 models.
 
-Tesseract is used for OCR but minimal adaptation is needed to connect other OCR
+PaddleOCR is used for OCR but minimal adaptation is needed to connect other OCR
 engines or models.
 
 Tested againt Label Studio 1.10.1, with basic support for both Label Studio
@@ -36,7 +36,7 @@ Minio.
    If you're using local file serving, be sure to get a copy of the API token from
    Label Studio to connect the model.
 
-2. Create a new project for Tesseract OCR. In the project **Settings** set up the **Labeling Interface**.
+2. Create a new project for PaddleOCR OCR. In the project **Settings** set up the **Labeling Interface**.
 
    Fill in the following template code. It's important to specify `smart="true"` in RectangleLabels.
    ```
@@ -61,7 +61,7 @@ Minio.
 3. Download the Label Studio Machine Learning backend backend repository.
    ```
    git clone https://github.com/humansignal/label-studio-ml-backend
-   cd label-studio-ml-backend/label_studio_ml/examples/tesseract
+   cd label-studio-ml-backend/label_studio_ml/examples/paddleocr
    ```
 
 4. Configure the backend and the Minio server by editing the `example.env` file. If you opted to use Label Studio
@@ -69,7 +69,7 @@ Minio.
    using the Minio storage example, set the `MINIO_ROOT_USER` AND `MINIO_ROOT_PASSWORD` variables, and make the 
    `AWS_ACCESS_KEY_ID` AND `AWS_SECRET_ACCESS_KEY` variables equal to those values. You may optionally connect to your
    own AWS cloud storage by setting those variables. Note that you may need to make additional software changes to the
-   `tesseract.py` file to match your particular infrastructure configuration.
+   `paddleocr_ch.py` file to match your particular infrastructure configuration.
 
    ```
    LABEL_STUDIO_HOST=http://host.docker.internal:8080
@@ -84,10 +84,22 @@ Minio.
    MINIO_API_CORS_ALLOW_ORIGIN=*
    ```
 
-5. Start the Tesseract and minio servers.
+5. Start the PaddleOCR and minio servers.
 
    ```
-   docker compose up
+   # build image
+   sudo docker build . -t paddleocr-backend:latest
+   # or
+   sudo docker compose build .
+
+   # only start paddleocr-backend
+   sudo docker compose up paddleocr-backend
+   # or and start with minio
+   docker compose up -d
+   # shutdown container
+   docker compose down 
+
+
    ```
 
 6. Upload tasks.
@@ -118,7 +130,7 @@ Minio.
 
 Example below :
 
-![ls_demo_ocr](https://user-images.githubusercontent.com/17755198/165186574-05f0236f-a5f2-4179-ac90-ef11123927bc.gif)
+![ls_demo_ocr](https://github.com/HumanSignal/label-studio-ml-backend/assets/1549611/fcc44c8b-12fd-495c-b0b4-9d5c0ceb2ed2)
 
 Reference links : 
 - https://labelstud.io/blog/Improve-OCR-quality-with-Tesseract-and-Label-Studio.html

From 6038a7eb07d0df9bbe2fb1e564b3f299ce79feb8 Mon Sep 17 00:00:00 2001
From: neozhu <neo.js.cn@gmail.com>
Date: Wed, 20 Mar 2024 13:27:35 +0000
Subject: [PATCH 5/7] =?UTF-8?q?=F0=9F=90=9B=20fixed=20comments=20and=20ref?=
 =?UTF-8?q?actoring=20code?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 label_studio_ml/examples/paddleocr/Dockerfile |  6 +--
 label_studio_ml/examples/paddleocr/README.md  |  7 ++-
 .../examples/paddleocr/docker-compose.yml     |  6 +--
 .../examples/paddleocr/example.env            | 17 +++----
 .../examples/paddleocr/paddleocr_ch.py        | 45 +++++++++++--------
 5 files changed, 46 insertions(+), 35 deletions(-)

diff --git a/label_studio_ml/examples/paddleocr/Dockerfile b/label_studio_ml/examples/paddleocr/Dockerfile
index 983e1d57..04643910 100644
--- a/label_studio_ml/examples/paddleocr/Dockerfile
+++ b/label_studio_ml/examples/paddleocr/Dockerfile
@@ -1,4 +1,4 @@
-FROM python:3.10
+FROM python:3.10-slim-bullseye
 
 WORKDIR /tmp
 COPY requirements.txt .
@@ -9,9 +9,7 @@ ENV PYTHONUNBUFFERED=True \
 
 # Installing libGL
 RUN apt-get update && apt-get install -y \
-    libgl1-mesa-dev
-
-RUN apt-get install -y poppler-utils libpoppler-cpp-dev libglib2.0-0
+    libgl1 libgomp1 libglib2.0-0 libsm6 libxrender1 libxext6
 
 
 RUN pip install --upgrade pip \
diff --git a/label_studio_ml/examples/paddleocr/README.md b/label_studio_ml/examples/paddleocr/README.md
index 43fa3365..e54d46d5 100644
--- a/label_studio_ml/examples/paddleocr/README.md
+++ b/label_studio_ml/examples/paddleocr/README.md
@@ -36,7 +36,7 @@ Minio.
    If you're using local file serving, be sure to get a copy of the API token from
    Label Studio to connect the model.
 
-2. Create a new project for PaddleOCR OCR. In the project **Settings** set up the **Labeling Interface**.
+2. Create a new project for PaddleOCR. In the project **Settings** set up the **Labeling Interface**.
 
    Fill in the following template code. It's important to specify `smart="true"` in RectangleLabels.
    ```
@@ -82,6 +82,8 @@ Minio.
    MINIO_ROOT_USER=<username>
    MINIO_ROOT_PASSWORD=<password>
    MINIO_API_CORS_ALLOW_ORIGIN=*
+
+   OCR_LANGUAGE=<Language Abbreviation ch,en,fr,japan>
    ```
 
 5. Start the PaddleOCR and minio servers.
@@ -100,6 +102,9 @@ Minio.
    docker compose down 
 
 
+   # or docker pull image from docker-hub
+   docker pull blazordevlab/paddleocr-backend:latest
+   
    ```
 
 6. Upload tasks.
diff --git a/label_studio_ml/examples/paddleocr/docker-compose.yml b/label_studio_ml/examples/paddleocr/docker-compose.yml
index e9156bd0..dff7552d 100644
--- a/label_studio_ml/examples/paddleocr/docker-compose.yml
+++ b/label_studio_ml/examples/paddleocr/docker-compose.yml
@@ -4,7 +4,7 @@ services:
 
   paddleocr-backend:
     container_name: paddleocr-backend
-    build: .
+    image: paddleocr-backend:latest
     env_file:
       - example.env
     ports:
@@ -19,8 +19,8 @@ services:
     env_file:
       - example.env
     ports:
-      - 9003:9000
-      - 9004:9001
+      - 9000:9000
+      - 9001:9001
     volumes:
       - ".data/storage:/data"
     command: server /data --console-address ":9001"
diff --git a/label_studio_ml/examples/paddleocr/example.env b/label_studio_ml/examples/paddleocr/example.env
index dad76777..5577d5ea 100644
--- a/label_studio_ml/examples/paddleocr/example.env
+++ b/label_studio_ml/examples/paddleocr/example.env
@@ -1,11 +1,12 @@
-LABEL_STUDIO_HOST=http://10.33.1.37:8089
-LABEL_STUDIO_ACCESS_TOKEN=9075ad7f2794f7d670a752dcf0eb1b6d177d08ff
+LABEL_STUDIO_HOST=http://host.docker.internal:8080
+LABEL_STUDIO_ACCESS_TOKEN=<access token if using local file storage>
 
-AWS_ACCESS_KEY_ID=admin
-AWS_SECRET_ACCESS_KEY=9075ad7f2
-AWS_ENDPOINT=http://10.33.1.37:9000
+AWS_ACCESS_KEY_ID=<MINIO_ROOT_USER if using minio example>
+AWS_SECRET_ACCESS_KEY=<MINIO_ROOT_PASSWORD if using minio example>
+AWS_ENDPOINT=http://host.docker.internal:9000
 
-MINIO_ROOT_USER=admin
-MINIO_ROOT_PASSWORD=9075ad7f2
+MINIO_ROOT_USER=<admin username>
+MINIO_ROOT_PASSWORD=<admin password>
 MINIO_API_CORS_ALLOW_ORIGIN=*
-MINIO_OPTS="--console-address :9001"
\ No newline at end of file
+
+OCR_LANGUAGE=<Language Abbreviation ch,en,fr,japan>
\ No newline at end of file
diff --git a/label_studio_ml/examples/paddleocr/paddleocr_ch.py b/label_studio_ml/examples/paddleocr/paddleocr_ch.py
index fcb8d293..82747127 100644
--- a/label_studio_ml/examples/paddleocr/paddleocr_ch.py
+++ b/label_studio_ml/examples/paddleocr/paddleocr_ch.py
@@ -8,10 +8,13 @@
 import json
 import boto3
 import numpy as np
+from botocore.exceptions import BotoCoreError, ClientError
 
 logger = logging.getLogger(__name__)
-# just for chinese
-ocr = PaddleOCR(use_angle_cls=True, lang="ch")  
+# Obtain language for OCR from an environment variable
+OCR_LANGUAGE = os.environ.get("OCR_LANGUAGE", "ch")
+# Initialize PaddleOCR with language and angle classification settings
+ocr = PaddleOCR(use_angle_cls=True, lang=OCR_LANGUAGE)
 
 LABEL_STUDIO_ACCESS_TOKEN = os.environ.get("LABEL_STUDIO_ACCESS_TOKEN")
 LABEL_STUDIO_HOST         = os.environ.get("LABEL_STUDIO_HOST")
@@ -35,19 +38,23 @@ class paddleocrLabeling(LabelStudioMLBase):
     def load_image(img_path_url):
         # load an s3 image, this is very basic demonstration code
         # you may need to modify to fit your own needs
-        if img_path_url.startswith("s3:"):
-            bucket_name = img_path_url.split("/")[2]
-            key = "/".join(img_path_url.split("/")[3:])
-
-            obj = S3_TARGET.Object(bucket_name, key).get()
-            data =  obj['Body'].read()
-            image = Image.open(io.BytesIO(data))
-            return image
-        else:
-            filepath = get_image_local_path(img_path_url,
-                    label_studio_access_token=LABEL_STUDIO_ACCESS_TOKEN,
-                    label_studio_host=LABEL_STUDIO_HOST)
-            return  Image.open(filepath)
+        try:
+            if img_path_url.startswith("s3:"):
+                bucket_name = img_path_url.split("/")[2]
+                key = "/".join(img_path_url.split("/")[3:])
+    
+                obj = S3_TARGET.Object(bucket_name, key).get()
+                data =  obj['Body'].read()
+                image = Image.open(io.BytesIO(data))
+                return image
+            else:
+                filepath = get_image_local_path(img_path_url,
+                        label_studio_access_token=LABEL_STUDIO_ACCESS_TOKEN,
+                        label_studio_host=LABEL_STUDIO_HOST)
+                return  Image.open(filepath)
+        except (BotoCoreError, ClientError, IOError) as e:
+            logger.error(f"Failed to load image {img_path_url}: {e}")
+            return None
 
 
     def predict(self, tasks, **kwargs):
@@ -72,11 +79,11 @@ def predict(self, tasks, **kwargs):
 
             crop_img = IMG.crop((x, y, x + w, y + h))
 
-            # 使用 PaddleOCR 进行文字识别
+            # Perform OCR with PaddleOCR
             ocr_result = ocr.ocr(np.array(crop_img), cls=True)
-            # PaddleOCR 返回结果的格式是 [(区域, (文本, 置信度))], 我们只关心文本部分
-            ocr_texts = [line[1][0] for line in ocr_result[0]]  # 提取所有识别的文本行
-            result_text = "\n".join(ocr_texts).strip()  # 将文本行合并为一个字符串
+            # PaddleOCR's result format is [(region, (text, confidence))]; we're interested in the text
+            ocr_texts = [line[1][0] for line in ocr_result[0]]  # Extract all recognized text lines
+            result_text = "\n".join(ocr_texts).strip()  # Join text lines into a single string
             meta["text"] = result_text
             temp = {
                 "original_width": meta["original_width"],

From 44c8efc948342a666e72eabc27072c1a1da1680f Mon Sep 17 00:00:00 2001
From: neozhu <neo.js.cn@gmail.com>
Date: Wed, 20 Mar 2024 13:30:59 +0000
Subject: [PATCH 6/7] reverted

---
 .../examples/tesseract/docker-compose.yml       |  4 ++--
 label_studio_ml/examples/tesseract/example.env  | 17 ++++++++---------
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/label_studio_ml/examples/tesseract/docker-compose.yml b/label_studio_ml/examples/tesseract/docker-compose.yml
index 62c92ed8..56121328 100644
--- a/label_studio_ml/examples/tesseract/docker-compose.yml
+++ b/label_studio_ml/examples/tesseract/docker-compose.yml
@@ -19,8 +19,8 @@ services:
     env_file:
       - example.env
     ports:
-      - 9003:9000
-      - 9004:9001
+      - 9000:9000
+      - 9001:9001
     volumes:
       - ".data/storage:/data"
     command: server /data --console-address ":9001"
diff --git a/label_studio_ml/examples/tesseract/example.env b/label_studio_ml/examples/tesseract/example.env
index dad76777..bf6b7c2d 100644
--- a/label_studio_ml/examples/tesseract/example.env
+++ b/label_studio_ml/examples/tesseract/example.env
@@ -1,11 +1,10 @@
-LABEL_STUDIO_HOST=http://10.33.1.37:8089
-LABEL_STUDIO_ACCESS_TOKEN=9075ad7f2794f7d670a752dcf0eb1b6d177d08ff
+LABEL_STUDIO_HOST=http://host.docker.internal:8080
+LABEL_STUDIO_ACCESS_TOKEN=<access token if using local file storage>
 
-AWS_ACCESS_KEY_ID=admin
-AWS_SECRET_ACCESS_KEY=9075ad7f2
-AWS_ENDPOINT=http://10.33.1.37:9000
+AWS_ACCESS_KEY_ID=<MINIO_ROOT_USER if using minio example>
+AWS_SECRET_ACCESS_KEY=<MINIO_ROOT_PASSWORD if using minio example>
+AWS_ENDPOINT=http://host.docker.internal:9000
 
-MINIO_ROOT_USER=admin
-MINIO_ROOT_PASSWORD=9075ad7f2
-MINIO_API_CORS_ALLOW_ORIGIN=*
-MINIO_OPTS="--console-address :9001"
\ No newline at end of file
+MINIO_ROOT_USER=<admin username>
+MINIO_ROOT_PASSWORD=<admin password>
+MINIO_API_CORS_ALLOW_ORIGIN=*
\ No newline at end of file

From d8a5dad636e5a7df5763e886a7eb9c99f8f019f7 Mon Sep 17 00:00:00 2001
From: "neo.zhu" <neo.js.cn@gmail.com>
Date: Thu, 21 Mar 2024 09:41:59 +0800
Subject: [PATCH 7/7] Update README.md

---
 label_studio_ml/examples/paddleocr/README.md | 81 ++++++++++++++++++--
 1 file changed, 76 insertions(+), 5 deletions(-)

diff --git a/label_studio_ml/examples/paddleocr/README.md b/label_studio_ml/examples/paddleocr/README.md
index e54d46d5..1e18dab0 100644
--- a/label_studio_ml/examples/paddleocr/README.md
+++ b/label_studio_ml/examples/paddleocr/README.md
@@ -6,6 +6,8 @@ models.
 PaddleOCR is used for OCR but minimal adaptation is needed to connect other OCR
 engines or models.
 
+PaddleOCR supports 80 languages. refer to https://github.com/Mushroomcat9998/PaddleOCR/blob/main/doc/doc_en/multi_languages_en.md#language_abbreviations
+
 Tested againt Label Studio 1.10.1, with basic support for both Label Studio
 Local File Storage and S3-compatible storage, with a example data storage with
 Minio.
@@ -83,7 +85,7 @@ Minio.
    MINIO_ROOT_PASSWORD=<password>
    MINIO_API_CORS_ALLOW_ORIGIN=*
 
-   OCR_LANGUAGE=<Language Abbreviation ch,en,fr,japan>
+   OCR_LANGUAGE=<Language Abbreviation ch,en,fr,japan> # support 80 languages. refer to https://github.com/Mushroomcat9998/PaddleOCR/blob/main/doc/doc_en/multi_languages_en.md#language_abbreviations
    ```
 
 5. Start the PaddleOCR and minio servers.
@@ -106,8 +108,77 @@ Minio.
    docker pull blazordevlab/paddleocr-backend:latest
    
    ```
+   below is my docker-compose file include label-studio,minio and paddleocr-backend
+
+   ```
+   version: "3.9"
+
+   x-logging:
+     logging: &default-logging
+       driver: "local"
+       options:
+         max-size: "10m"
+         max-file: "3"
+
+   services:
+     label-studio:
+       container_name: label-studio
+       image: heartexlabs/label-studio:latest
+       restart: unless-stopped
+       ports:
+         - "8080:8080"
+       depends_on:
+         - minio
+       environment:
+         - JSON_LOG=1
+         - LOG_LEVEL=DEBUG
+       volumes:
+         - label-studio-data:/label-studio/data
+
+     # not replicated setup for test setup, use a proper aws S3 compatible cluster in production
+     minio:
+       container_name: minio
+       image: bitnami/minio:latest
+       restart: unless-stopped
+       logging: *default-logging
+       ports:
+         - "9000:9000"
+         - "9001:9001"
+       volumes:
+         - minio-data:/data
+         - minio-certs:/certs
+       # configure env vars in .env file or your systems environment
+       environment:
+         - MINIO_ROOT_USER=${MINIO_ROOT_USER:-minio_admin_do_not_use_in_production}
+         - MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-minio_admin_do_not_use_in_production}
+         - MINIO_PROMETHEUS_AUTH_TYPE=${MINIO_PROMETHEUS_AUTH_TYPE:-public}
+     paddleocr-backend:
+       container_name: paddleocr-backend
+       image: blazordevlab/paddleocr-backend:latest
+       environment:
+         - LABEL_STUDIO_HOST=${LABEL_STUDIO_HOST:-http://label-studio:8080}
+         - LABEL_STUDIO_ACCESS_TOKEN=${LABEL_STUDIO_ACCESS_TOKEN}
+         - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
+         - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
+         - AWS_ENDPOINT=${AWS_ENDPOINT:-http://minio:9000}
+         - MINIO_ROOT_USER=${MINIO_ROOT_USER:-minio_admin_do_not_use_in_production}
+         - MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-minio_admin_do_not_use_in_production}
+         - MINIO_API_CORS_ALLOW_ORIGIN=${MINIO_API_CORS_ALLOW_ORIGIN:-*}
+         - OCR_LANGUAGE=${OCR_LANGUAGE:-ch}
+       ports:
+         - 9090:9090
+       volumes:
+         - paddleocr-backend-data:/data
+         - paddleocr-backend-logs:/tmp
+   volumes:
+     label-studio-data:
+     minio-data:
+     minio-certs:
+     paddleocr-backend-data:
+     paddleocr-backend-logs:
+   ```
 
-6. Upload tasks.
+7. Upload tasks.
 
    If you're using the Label Studio Local File Storage option, upload images
    directly to Label Studio using the Label Studio interface.
@@ -119,7 +190,7 @@ Minio.
    tutorial, and you will want to configure your storage according to your
    particular needs. 
 
-7. If using minio, In the project **Settings**, set up the **Cloud storage**.
+8. If using minio, In the project **Settings**, set up the **Cloud storage**.
 
    Add your source S3 storage by connecting to the S3 Endpoint
    `http://host.docker.internal:9000`, using the bucket name from the previous
@@ -127,11 +198,11 @@ Minio.
    steps. For the minio example, uncheck **Use pre-signed URLS**. Check the
    connection and save the storage.
 
-8. Open the **Machine Learning** settings and click **Add Model**.
+9. Open the **Machine Learning** settings and click **Add Model**.
 
    Add the URL `http://host.docker.internal:9090` and save the model as an ML backend.
 
-9. To use this functionality, activate `Auto-Annotation` and use `Autotdetect` rectangle for drawing boxes
+10. To use this functionality, activate `Auto-Annotation` and use `Autotdetect` rectangle for drawing boxes
 
 Example below :