Duplicate from KayO/Webpage-Question-Answering

Co-authored-by: Kwadwo Agyapon-Ntra <KayO@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Webpage Question Answering
+emoji: ❓
+colorFrom: pink
+colorTo: pink
+sdk: gradio
+sdk_version: 3.11.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: KayO/Webpage-Question-Answering
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+import requests
+from bs4 import BeautifulSoup
+from transformers import pipeline
+
+# Load the trained model
+qa_model = pipeline("question-answering")
+
+def extract_answer(question, url):
+    """Get context from URL and use it to answer the question"""
+    
+    # Retrieve actual page content
+    html = requests.get(url).content
+    # Create BS4 object to handle HTML data
+    soup = BeautifulSoup(html, 'html.parser')
+
+    for data in soup(['style', 'script', 'meta', 'link', 'noscript']):
+        # Remove tags
+        data.decompose()
+
+    # Get and clean up plain text
+    context = soup.get_text()
+    while "\n\n" in context:
+        context = context.replace("\n\n", "\n")
+    
+    answer_dict = qa_model(question = question, context = context)
+    return answer_dict
+
+
+title = "Webpage-Based Question Answering"
+description = "Using a webpage as context for extractive question answering."
+enable_queue=True
+examples=[
+    ["Where was Messi born?", "https://en.wikipedia.org/wiki/Lionel_Messi"],
+    ["When was Cristiano Ronaldo born?", "https://en.wikipedia.org/wiki/Cristiano_Ronaldo"]
+]
+
+iface = gr.Interface(
+    fn=extract_answer, 
+    inputs=["text", "text"], 
+    outputs="text",
+    title=title,
+    description=description,
+    examples=examples
+)
+iface.launch(enable_queue=enable_queue)

requirements.txt

@@ -0,0 +1,2 @@
+transformers[torch]
+beautifulsoup4