Upload 11 files

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY --link --chown=1000 . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+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 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

@@ -1,12 +1,12 @@
 ---
-title: ASK Pdf Test
-emoji: 📚
-colorFrom: indigo
-colorTo: red
-sdk: gradio
-sdk_version: 5.1.0
-app_file: app.py
+tags:
+- gradio-custom-component
+- gradio-template-Fallback
+title: Just Ask PDF
+colorFrom: green
+colorTo: blue
+sdk: docker
 pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+license: apache-2.0
+emoji: ❓
+---

app.py

@@ -0,0 +1,29 @@
+
+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")]]
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+pdf2image
+pytesseract
+gradio_pdf-0.0.3-py3-none-any.whl