Upload folder using huggingface_hub

Dockerfile

@@ -7,12 +7,10 @@ COPY --link --chown=1000 . .
 
 RUN mkdir -p /tmp/cache/
 RUN chmod a+rwx -R /tmp/cache/
-RUN apt-get update && apt-get install -y poppler-utils tesseract-ocr chromium
-ENV TRANSFORMERS_CACHE=/tmp/cache/ 
+ENV TRANSFORMERS_CACHE=/tmp/cache/
 
 RUN pip install --no-cache-dir -r requirements.txt
 
 ENV PYTHONUNBUFFERED=1 	GRADIO_ALLOW_FLAGGING=never 	GRADIO_NUM_PORTS=1 	GRADIO_SERVER_NAME=0.0.0.0     GRADIO_SERVER_PORT=7860 	SYSTEM=spaces
 
-CMD ["python", "app.py"]
-
+CMD ["python", "space.py"]

README.md

@@ -1,17 +1,10 @@
 
 ---
-tags: [gradio-custom-component,Documents,PDF,Document QA,gradio,gradio-template-Fallback]
-title: gradio_pdf V0.0.3
+tags: [gradio-custom-component]
+title: gradio_pdf V0.0.6
 colorFrom: green
-colorTo: pink
+colorTo: gray
 sdk: docker
 pinned: false
 license: apache-2.0
 ---
-
-
-# Name: gradio_pdf
-
-Description: Easily display PDFs in Gradio
-
-Install with: pip install gradio_pdf

app.py

@@ -1,44 +1,4 @@
 
-import gradio as gr
-from _app import demo as app
-import os
-
-_docs = {'PDF': {'description': 'A base class for defining methods that all input/output components should have.', 'members': {'__init__': {'value': {'type': 'Any', 'default': 'None', 'description': None}, 'height': {'type': 'int | None', 'default': 'None', 'description': None}, 'label': {'type': 'str | None', 'default': 'None', 'description': None}, 'info': {'type': 'str | None', 'default': 'None', 'description': None}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': None}, 'container': {'type': 'bool', 'default': 'True', 'description': None}, 'scale': {'type': 'int | None', 'default': 'None', 'description': None}, 'min_width': {'type': 'int | None', 'default': 'None', 'description': None}, 'interactive': {'type': 'bool | None', 'default': 'None', 'description': None}, 'visible': {'type': 'bool', 'default': 'True', 'description': None}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': None}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': None}, 'render': {'type': 'bool', 'default': 'True', 'description': None}, 'load_fn': {'type': 'Callable[..., Any] | None', 'default': 'None', 'description': None}, 'every': {'type': 'float | None', 'default': 'None', 'description': None}}, 'postprocess': {'value': {'type': 'str | None', 'description': None}}, 'preprocess': {'return': {'type': 'str', 'description': None}, 'value': None}}, 'events': {'change': {'type': None, 'default': None, 'description': ''}, 'upload': {'type': None, 'default': None, 'description': ''}}}, '__meta__': {'additional_interfaces': {}, 'user_fn_refs': {'PDF': []}}}
-    
-abs_path = os.path.join(os.path.dirname(__file__), "css.css")
-
-with gr.Blocks(
-    css=abs_path,
-    theme=gr.themes.Default(
-        font_mono=[
-            gr.themes.GoogleFont("Inconsolata"),
-            "monospace",
-        ],
-    ),
-) as demo:
-    gr.Markdown(
-"""
-# `gradio_pdf`
-
-<div style="display: flex; gap: 7px;">
-<a href="https://pypi.org/project/gradio_pdf/" target="_blank"><img alt="PyPI - Version" src="https://img.shields.io/pypi/v/gradio_pdf"></a> <a href="https://github.com/freddyaboulton/gradio-pdf/issues" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/Issues-white?logo=github&logoColor=black"></a> <a href="https://huggingface.co/spaces/freddyaboulton/gradio_pdf/discussions" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/%F0%9F%A4%97%20Discuss-%23097EFF?style=flat&logoColor=black"></a>
-</div>
-
-Easily display PDFs in Gradio
-""", elem_classes=["md-custom"], header_links=True)
-    app.render()
-    gr.Markdown(
-"""
-## Installation
-
-```bash
-pip install gradio_pdf
-```
-
-## Usage
-
-```python
-
 import gradio as gr
 from gradio_pdf import PDF
 from pdf2image import convert_from_path
@@ -68,84 +28,3 @@ demo = gr.Interface(
 
 if __name__ == "__main__":
     demo.launch()
-
-```
-""", elem_classes=["md-custom"], header_links=True)
-
-
-    gr.Markdown("""
-## `PDF`
-
-### Initialization
-""", elem_classes=["md-custom"], header_links=True)
-
-    gr.ParamViewer(value=_docs["PDF"]["members"]["__init__"], linkify=[])
-
-
-    gr.Markdown("### Events")
-    gr.ParamViewer(value=_docs["PDF"]["events"], linkify=['Event'])
-
-
-
-
-    gr.Markdown("""
-
-### User function
-
-The impact on the users predict function varies depending on whether the component is used as an input or output for an event (or both).
-
-- When used as an Input, the component only impacts the input signature of the user function. 
-- When used as an output, the component only impacts the return signature of the user function. 
-
-The code snippet below is accurate in cases where the component is used as both an input and an output.
-
-
-
- ```python
-def predict(
-    value: str
-) -> str | None:
-    return value
-```
-""", elem_classes=["md-custom", "PDF-user-fn"], header_links=True)
-
-
-
-
-    demo.load(None, js=r"""function() {
-    const refs = {};
-    const user_fn_refs = {
-          PDF: [], };
-    requestAnimationFrame(() => {
-
-        Object.entries(user_fn_refs).forEach(([key, refs]) => {
-            if (refs.length > 0) {
-                const el = document.querySelector(`.${key}-user-fn`);
-                if (!el) return;
-                refs.forEach(ref => {
-                    el.innerHTML = el.innerHTML.replace(
-                        new RegExp("\\b"+ref+"\\b", "g"),
-                        `<a href="#h-${ref.toLowerCase()}">${ref}</a>`
-                    );
-                })
-            }
-        })
-        
-        Object.entries(refs).forEach(([key, refs]) => {
-            if (refs.length > 0) {
-                const el = document.querySelector(`.${key}`);
-                if (!el) return;
-                refs.forEach(ref => {
-                    el.innerHTML = el.innerHTML.replace(
-                        new RegExp("\\b"+ref+"\\b", "g"),
-                        `<a href="#h-${ref.toLowerCase()}">${ref}</a>`
-                    );
-                })
-            }
-        })
-    })
-}
-
-""")
-
-demo.launch()

space.py

@@ -0,0 +1,152 @@
+
+import gradio as gr
+from app import demo as app
+import os
+
+_docs = {'PDF': {'description': 'A base class for defining methods that all input/output components should have.', 'members': {'__init__': {'value': {'type': 'typing.Any', 'default': 'None', 'description': None}, 'height': {'type': 'int | None', 'default': 'None', 'description': None}, 'label': {'type': 'str | None', 'default': 'None', 'description': None}, 'info': {'type': 'str | None', 'default': 'None', 'description': None}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': None}, 'container': {'type': 'bool', 'default': 'True', 'description': None}, 'scale': {'type': 'int | None', 'default': 'None', 'description': None}, 'min_width': {'type': 'int | None', 'default': 'None', 'description': None}, 'interactive': {'type': 'bool | None', 'default': 'None', 'description': None}, 'visible': {'type': 'bool', 'default': 'True', 'description': None}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': None}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': None}, 'render': {'type': 'bool', 'default': 'True', 'description': None}, 'load_fn': {'type': 'Callable[Ellipsis, typing.Any] | None', 'default': 'None', 'description': None}, 'every': {'type': 'float | None', 'default': 'None', 'description': None}}, 'postprocess': {'value': {'type': 'str | None', 'description': "The output data received by the component from the user's function in the backend."}}, 'preprocess': {'return': {'type': 'str', 'description': "The preprocessed input data sent to the user's function in the backend."}, 'value': None}}, 'events': {'change': {'type': None, 'default': None, 'description': ''}, 'upload': {'type': None, 'default': None, 'description': ''}}}, '__meta__': {'additional_interfaces': {}, 'user_fn_refs': {'PDF': []}}}
+
+abs_path = os.path.join(os.path.dirname(__file__), "css.css")
+
+with gr.Blocks(
+    css=abs_path,
+    theme=gr.themes.Default(
+        font_mono=[
+            gr.themes.GoogleFont("Inconsolata"),
+            "monospace",
+        ],
+    ),
+) as demo:
+    gr.Markdown(
+"""
+# `gradio_pdf`
+
+<div style="display: flex; gap: 7px;">
+<a href="https://pypi.org/project/gradio_pdf/" target="_blank"><img alt="PyPI - Version" src="https://img.shields.io/pypi/v/gradio_pdf"></a>  
+</div>
+
+Easily display PDFs in Gradio
+""", elem_classes=["md-custom"], header_links=True)
+    app.render()
+    gr.Markdown(
+"""
+## Installation
+
+```bash
+pip install gradio_pdf
+```
+
+## Usage
+
+```python
+
+import gradio as gr
+from gradio_pdf import PDF
+from pdf2image import convert_from_path
+from transformers import pipeline
+from pathlib import Path
+
+dir_ = Path(__file__).parent
+
+p = pipeline(
+    "document-question-answering",
+    model="impira/layoutlm-document-qa",
+)
+
+def qa(question: str, doc: str) -> str:
+    img = convert_from_path(doc)[0]
+    output = p(img, question)
+    return sorted(output, key=lambda x: x["score"], reverse=True)[0]['answer']
+
+
+demo = gr.Interface(
+    qa,
+    [gr.Textbox(label="Question"), PDF(label="Document")],
+    gr.Textbox(),
+    examples=[["What is the total gross worth?", str(dir_ / "invoice_2.pdf")],
+              ["Whos is being invoiced?", str(dir_ / "sample_invoice.pdf")]]
+)
+
+if __name__ == "__main__":
+    demo.launch()
+
+```
+""", elem_classes=["md-custom"], header_links=True)
+
+
+    gr.Markdown("""
+## `PDF`
+
+### Initialization
+""", elem_classes=["md-custom"], header_links=True)
+
+    gr.ParamViewer(value=_docs["PDF"]["members"]["__init__"], linkify=[])
+
+
+    gr.Markdown("### Events")
+    gr.ParamViewer(value=_docs["PDF"]["events"], linkify=['Event'])
+
+
+
+
+    gr.Markdown("""
+
+### User function
+
+The impact on the users predict function varies depending on whether the component is used as an input or output for an event (or both).
+
+- When used as an Input, the component only impacts the input signature of the user function.
+- When used as an output, the component only impacts the return signature of the user function.
+
+The code snippet below is accurate in cases where the component is used as both an input and an output.
+
+- **As input:** Is passed, the preprocessed input data sent to the user's function in the backend.
+- **As output:** Should return, the output data received by the component from the user's function in the backend.
+
+ ```python
+def predict(
+    value: str
+) -> str | None:
+    return value
+```
+""", elem_classes=["md-custom", "PDF-user-fn"], header_links=True)
+
+
+
+
+    demo.load(None, js=r"""function() {
+    const refs = {};
+    const user_fn_refs = {
+          PDF: [], };
+    requestAnimationFrame(() => {
+
+        Object.entries(user_fn_refs).forEach(([key, refs]) => {
+            if (refs.length > 0) {
+                const el = document.querySelector(`.${key}-user-fn`);
+                if (!el) return;
+                refs.forEach(ref => {
+                    el.innerHTML = el.innerHTML.replace(
+                        new RegExp("\\b"+ref+"\\b", "g"),
+                        `<a href="#h-${ref.toLowerCase()}">${ref}</a>`
+                    );
+                })
+            }
+        })
+
+        Object.entries(refs).forEach(([key, refs]) => {
+            if (refs.length > 0) {
+                const el = document.querySelector(`.${key}`);
+                if (!el) return;
+                refs.forEach(ref => {
+                    el.innerHTML = el.innerHTML.replace(
+                        new RegExp("\\b"+ref+"\\b", "g"),
+                        `<a href="#h-${ref.toLowerCase()}">${ref}</a>`
+                    );
+                })
+            }
+        })
+    })
+}
+
+""")
+
+demo.launch()