Duplicate from dinhquangson/LORE

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,30 @@
+# Use the official Python 3.9 image
+FROM python:3.9
+ 
+# Set the working directory to /code
+WORKDIR /code
+ 
+# Copy the current directory contents into the container at /code
+COPY ./requirements.txt /code/requirements.txt
+
+RUN apt-get update && apt-get install ffmpeg libsm6 libxext6  -y
+RUN apt-get install libjpeg-dev
+# Install requirements.txt 
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+ 
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+ 
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+ 
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+ 
+# Start the FastAPI app on port 7860, the default port expected by Spaces
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,12 @@
+---
+title: Pdf2images
+emoji: 🏢
+colorFrom: green
+colorTo: purple
+sdk: docker
+pinned: false
+license: mit
+duplicated_from: dinhquangson/LORE
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,26 @@
+from fastapi import FastAPI
+from fastapi import File, UploadFile
+import shutil
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from os import makedirs,getcwd
+from os.path import join,exists,dirname
+
+lineless_table_recognition = pipeline(Tasks.lineless_table_recognition, model='damo/cv_resnet-transformer_table-structure-recognition_lore')
+    
+app = FastAPI()
+parent_path  = dirname(getcwd())
+
+temp_path = join(parent_path,'temp')
+if not exists(temp_path):
+    makedirs(temp_path)
+
+@app.post("/analyze")
+def pdf2images(file: UploadFile=File(...)):
+    file_savePath =  join(temp_path,file.filename)
+
+    with open(file_savePath,'wb') as f:
+        shutil.copyfileobj(file.file, f)
+    
+    result = lineless_table_recognition(file_savePath)
+    return result

requirements.txt

@@ -0,0 +1,8 @@
+modelscope
+torch
+torchvision
+fastapi
+uvicorn
+opencv-python
+python-multipart
+shapely