V1 ready

.gitignore

@@ -0,0 +1,10 @@
+# Ignore Python cache files
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+
+# Ignore flagged folder
+flagged/
+
+# Add other files or directories you want to ignore below

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+import pymupdf4llm as pdf
+
+with gr.Blocks(theme="soft", analytics_enabled=True, title="PDF to Text") as demo:
+    gr.Markdown("""
+    # PDF to Text
+    Convert your PDF files to text with ease.
+    """)
+    
+    pdf_file = gr.File(label="Upload your PDF file")
+    text_output = gr.Code(label="Extracted text", language="markdown")
+
+    button = gr.Button("Extract text")
+
+    def extract_text(file):
+        return pdf.to_markdown(file)
+    
+    button.click(extract_text, inputs=pdf_file, outputs=text_output)
+
+demo.launch()
+

requirements.txt

@@ -0,0 +1,60 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.3.0
+cycler==0.12.1
+fastapi==0.115.0
+ffmpy==0.4.0
+filelock==3.16.1
+fonttools==4.54.1
+fsspec==2024.9.0
+gradio==4.44.1
+gradio_client==1.3.0
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.25.1
+idna==3.10
+importlib_resources==6.4.5
+Jinja2==3.1.4
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+numpy==2.1.1
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+pillow==10.4.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+PyMuPDF==1.24.10
+pymupdf4llm==0.0.17
+PyMuPDFb==1.24.10
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.9.1
+ruff==0.6.8
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+tomlkit==0.12.0
+tqdm==4.66.5
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.31.0
+websockets==12.0