Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,45 @@
+
+import gradio as gr
+import joblib
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+# Load the model
+loaded_model = joblib.load("qa_model.joblib")
+vectorizer = loaded_model["vectorizer"]
+tfidf_matrix = loaded_model["tfidf_matrix"]
+paragraphs = loaded_model["paragraphs"]
+
+def answer_question(question):
+    question_vector = vectorizer.transform([question])
+    similarities = cosine_similarity(question_vector, tfidf_matrix)
+    most_similar_paragraph_index = np.argmax(similarities)
+    most_similar_paragraph = paragraphs[most_similar_paragraph_index]
+
+    paragraph_sentences = most_similar_paragraph.split(".")
+    best_sentence = ""
+    max_overlap = 0
+
+    question_words = set(question.lower().split())
+
+    for sentence in paragraph_sentences:
+        sentence = sentence.strip()
+        if not sentence:
+            continue
+        sentence_words = set(sentence.lower().split())
+        overlap = len(question_words.intersection(sentence_words))
+        if overlap > max_overlap:
+            max_overlap = overlap
+            best_sentence = sentence
+
+    return best_sentence.strip()
+
+iface = gr.Interface(
+    fn=answer_question,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your question here..."),
+    outputs="text",
+    title="Mahabharata Question Answering",
+    description="Ask a question about the Mahabharata, and the model will attempt to answer it.",
+)
+
+iface.launch()