Upload 2 files

main.py

@@ -0,0 +1,86 @@
+import streamlit as st
+import subprocess
+
+#=======================================================================================================================#
+
+def clear_submit():
+    st.session_state["submit"] = False
+
+if 'clicked' not in st.session_state:
+    st.session_state.clicked = False
+
+def click_button():
+    st.session_state.clicked = True
+
+st.set_page_config(page_title='OCR App', page_icon=':pencil:', layout='wide', initial_sidebar_state='auto')
+
+#=======================================================================================================================#
+
+#--------------------------Sidebar--------------------------#
+
+with st.sidebar:
+    # Add a title
+    st.title('Load document')
+
+    # Add a file uploader
+    uploaded_file = st.file_uploader(
+            "Upload file", type=["pdf"], 
+            help="Only PDF files are supported", 
+            on_change=clear_submit)
+
+    # Add a button
+    if uploaded_file:
+        st.markdown('---')
+        st.title('Extract text from PDF')
+        extract_text = st.button('Extract', help='Extract text from the document')
+    
+#=======================================================================================================================#
+
+#--------------------------Main Page--------------------------#
+
+if uploaded_file:
+
+    # Create a temporary folder
+    input_path = f'./files/{uploaded_file.name}'
+    # Create output file
+    output_file = f'{uploaded_file.name}'.replace('.pdf', '.mmd')
+    output_path = f'./files/'
+
+    # mmd path
+    mmd_path = f'./files/{output_file}'
+
+    with open(input_path, 'wb') as f:
+        f.write(uploaded_file.getbuffer())
+
+    # Load the model
+    @st.cache_resource(show_spinner=False)
+    def load_model(input_path, output_path):
+        subprocess.run(['nougat', input_path, '-o', output_path])
+
+    
+    if extract_text:
+        with st.spinner('Extracting text...'):
+            load_model(input_path, output_path)
+
+        with open(mmd_path, 'r') as f:
+            mmd = f.read()
+            # move mmd to the session state
+            st.session_state["mmd"] = mmd
+
+    try:
+        st.write(st.session_state["mmd"])
+        
+        with st.sidebar:
+            st.success('Text extracted successfully!')
+            st.markdown('---')
+            st.title('Download file')
+            download_output = st.download_button(label='Download', 
+                                                data=st.session_state["mmd"], 
+                                                file_name=output_file.replace('.mmd', '.md'),
+                                                mime='text/markdown')
+    
+    except:
+        pass
+
+
+                

requirements.txt

@@ -0,0 +1,94 @@
+aiohttp==3.9.3
+aiosignal==1.3.1
+albumentations==1.3.1
+altair==5.2.0
+async-timeout==4.0.3
+attrs==23.2.0
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cryptography==42.0.2
+datasets==2.16.1
+filelock==3.13.1
+frozenlist==1.4.1
+fsspec==2023.10.0
+gitdb==4.0.11
+GitPython==3.1.41
+huggingface-hub==0.20.3
+idna==3.6
+imageio==2.33.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+lazy_loader==0.3
+Levenshtein==0.24.0
+lightning==2.1.4
+lightning-utilities==0.10.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.5
+multiprocess==0.70.15
+munch==4.0.0
+networkx==3.2.1
+nltk==3.8.1
+nougat-ocr==0.1.17
+numpy==1.26.4
+opencv-python-headless==4.9.0.80
+orjson==3.9.13
+pandas==2.2.0
+pillow==10.2.0
+protobuf==4.25.2
+pyarrow==15.0.0
+pyarrow-hotfix==0.6
+pycparser==2.21
+pycryptodome==3.20.0
+pydeck==0.8.1b0
+pypdf==4.0.1
+pypdfium2==4.26.0
+python-Levenshtein==0.24.0
+pytorch-lightning==2.1.4
+pytz==2024.1
+PyYAML==6.0.1
+qudida==0.0.4
+rapidfuzz==3.6.1
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.17.1
+ruamel.yaml==0.18.5
+ruamel.yaml.clib==0.2.8
+safetensors==0.4.2
+scikit-image==0.22.0
+scikit-learn==1.4.0
+scipy==1.12.0
+sconf==0.2.5
+sentencepiece==0.1.99
+smmap==5.0.1
+streamlit==1.31.0
+sympy==1.12
+tenacity==8.2.3
+threadpoolctl==3.2.0
+tifffile==2024.1.30
+timm==0.5.4
+tokenizers==0.15.1
+toml==0.10.2
+toolz==0.12.1
+torch==2.2.0
+torchmetrics==1.3.0.post0
+torchvision==0.17.0
+tqdm==4.66.1
+transformers==4.37.2
+tzdata==2023.4
+tzlocal==5.2
+urllib3==2.2.0
+validators==0.22.0
+xxhash==3.4.1
+yarl==1.9.4
+