Upload 13 files

Dockerfile

@@ -0,0 +1,18 @@
+
+FROM python:3.9
+
+WORKDIR /code
+
+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/ 
+
+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"]
+

README.md

@@ -1,13 +1,17 @@
+
 ---
-title: Chatpdf
-emoji: 💻
-colorFrom: indigo
-colorTo: gray
-sdk: gradio
-sdk_version: 4.24.0
-app_file: app.py
+tags: [gradio-custom-component,Documents,PDF,Document QA,gradio,gradio-template-Fallback]
+title: gradio_pdf V0.0.3
+colorFrom: green
+colorTo: pink
+sdk: docker
 pinned: false
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Name: gradio_pdf
+
+Description: Easily display PDFs in Gradio
+
+Install with: pip install gradio_pdf

_app.py

@@ -0,0 +1,30 @@
+
+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()

app.py

@@ -0,0 +1,151 @@
+
+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
+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.
+
+
+
+ ```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()

css.css

@@ -0,0 +1,157 @@
+html {
+	font-family: Inter;
+	font-size: 16px;
+	font-weight: 400;
+	line-height: 1.5;
+	-webkit-text-size-adjust: 100%;
+	background: #fff;
+	color: #323232;
+	-webkit-font-smoothing: antialiased;
+	-moz-osx-font-smoothing: grayscale;
+	text-rendering: optimizeLegibility;
+}
+
+:root {
+	--space: 1;
+	--vspace: calc(var(--space) * 1rem);
+	--vspace-0: calc(3 * var(--space) * 1rem);
+	--vspace-1: calc(2 * var(--space) * 1rem);
+	--vspace-2: calc(1.5 * var(--space) * 1rem);
+	--vspace-3: calc(0.5 * var(--space) * 1rem);
+}
+
+.app {
+	max-width: 748px !important;
+}
+
+.prose p {
+	margin: var(--vspace) 0;
+	line-height: var(--vspace * 2);
+	font-size: 1rem;
+}
+
+code {
+	font-family: "Inconsolata", sans-serif;
+	font-size: 16px;
+}
+
+h1,
+h1 code {
+	font-weight: 400;
+	line-height: calc(2.5 / var(--space) * var(--vspace));
+}
+
+h1 code {
+	background: none;
+	border: none;
+	letter-spacing: 0.05em;
+	padding-bottom: 5px;
+	position: relative;
+	padding: 0;
+}
+
+h2 {
+	margin: var(--vspace-1) 0 var(--vspace-2) 0;
+	line-height: 1em;
+}
+
+h3,
+h3 code {
+	margin: var(--vspace-1) 0 var(--vspace-2) 0;
+	line-height: 1em;
+}
+
+h4,
+h5,
+h6 {
+	margin: var(--vspace-3) 0 var(--vspace-3) 0;
+	line-height: var(--vspace);
+}
+
+.bigtitle,
+h1,
+h1 code {
+	font-size: calc(8px * 4.5);
+	word-break: break-word;
+}
+
+.title,
+h2,
+h2 code {
+	font-size: calc(8px * 3.375);
+	font-weight: lighter;
+	word-break: break-word;
+	border: none;
+	background: none;
+}
+
+.subheading1,
+h3,
+h3 code {
+	font-size: calc(8px * 1.8);
+	font-weight: 600;
+	border: none;
+	background: none;
+	letter-spacing: 0.1em;
+	text-transform: uppercase;
+}
+
+h2 code {
+	padding: 0;
+	position: relative;
+	letter-spacing: 0.05em;
+}
+
+blockquote {
+	font-size: calc(8px * 1.1667);
+	font-style: italic;
+	line-height: calc(1.1667 * var(--vspace));
+	margin: var(--vspace-2) var(--vspace-2);
+}
+
+.subheading2,
+h4 {
+	font-size: calc(8px * 1.4292);
+	text-transform: uppercase;
+	font-weight: 600;
+}
+
+.subheading3,
+h5 {
+	font-size: calc(8px * 1.2917);
+	line-height: calc(1.2917 * var(--vspace));
+
+	font-weight: lighter;
+	text-transform: uppercase;
+	letter-spacing: 0.15em;
+}
+
+h6 {
+	font-size: calc(8px * 1.1667);
+	font-size: 1.1667em;
+	font-weight: normal;
+	font-style: italic;
+	font-family: "le-monde-livre-classic-byol", serif !important;
+	letter-spacing: 0px !important;
+}
+
+#start .md > *:first-child {
+	margin-top: 0;
+}
+
+h2 + h3 {
+	margin-top: 0;
+}
+
+.md hr {
+	border: none;
+	border-top: 1px solid var(--block-border-color);
+	margin: var(--vspace-2) 0 var(--vspace-2) 0;
+}
+.prose ul {
+	margin: var(--vspace-2) 0 var(--vspace-1) 0;
+}
+
+.gap {
+	gap: 0;
+}

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+pdf2image
+pytesseract
+gradio_pdf==0.0.5