Create app.py

app.py

@@ -0,0 +1,60 @@
+import pandas as pd
+import gradio as gr
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.schema import Document
+
+# Initialize once when the app starts
+def initialize_system():
+    # Load dataset
+    data = pd.read_csv("qa_dataset.csv")
+    
+    # Create documents
+    documents = [
+        Document(
+            page_content=f"Q: {row['Question']}\nA: {row['Answer']}",
+            metadata={"question": row['Question'], "answer": row['Answer']}
+        ) for _, row in data.iterrows()
+    ]
+    
+    # Create vector store
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/multi-qa-mpnet-base-dot-v1"
+    )
+    
+    return FAISS.from_documents(documents, embeddings)
+
+vector_store = initialize_system()
+
+def classify_question(query: str, k: int = 3):
+    # Retrieve similar Q&A pairs
+    results = vector_store.similarity_search(query, k=k)
+    
+    # Generate category from answers
+    answers = " ".join([doc.metadata['answer'] for doc in results])
+    keywords = list(dict.fromkeys(answers.split()))[:5]
+    category = " ".join(keywords)
+    
+    # Format output
+    return {
+        "Category": category,
+        "Top Matches": "\n\n".join([f"Q: {doc.metadata['question']}\nA: {doc.metadata['answer']}" 
+                                  for doc in results]),
+        "Confidence": f"{len(results)/k:.0%}"
+    }
+
+# Gradio interface
+interface = gr.Interface(
+    fn=lambda q: classify_question(q, 3),
+    inputs=gr.Textbox(label="Input Question", placeholder="Type your question here..."),
+    outputs=[
+        gr.Textbox(label="Predicted Category"),
+        gr.Textbox(label="Supporting Q&A"),
+        gr.Textbox(label="Confidence")
+    ],
+    title="Question Classification System",
+    description="Classify questions based on existing Q&A pairs using RAG"
+)
+
+if __name__ == "__main__":
+    interface.launch()