Update app.py

app.py

@@ -1,17 +1,31 @@
+# app.py
+
+# Install necessary libraries (Run this separately in your environment if needed)
+# !pip install pandas sentence-transformers transformers datasets faiss-cpu gradio fastapi uvicorn
+
+# Import libraries
 import pandas as pd
 from sentence_transformers import SentenceTransformer
 import faiss
 from datasets import load_dataset
+from fastapi import FastAPI
+import gradio as gr
+
+# Initialize FastAPI app
+app = FastAPI()
 
-# Load the dataset
+# Load the Dataset from Hugging Face and FAQ CSV
 support_data = load_dataset("rjac/e-commerce-customer-support-qa")
+
+# Load FAQ data from uploaded file (change as needed for local path)
 faq_data = pd.read_csv("Ecommerce_FAQs.csv")
 
-# Data preparation
+# Preprocess and Clean Data
 faq_data.rename(columns={'prompt': 'Question', 'response': 'Answer'}, inplace=True)
 faq_data = faq_data[['Question', 'Answer']]
 support_data_df = pd.DataFrame(support_data['train'])
 
+# Extract question-answer pairs from the conversation field
 def extract_conversation(data):
     try:
         parts = data.split("\n\n")
@@ -21,29 +35,55 @@ def extract_conversation(data):
     except IndexError:
         return pd.Series({"Question": "", "Answer": ""})
 
+# Apply extraction function
 support_data_df[['Question', 'Answer']] = support_data_df['conversation'].apply(extract_conversation)
+
+# Combine FAQ data with support data
 combined_data = pd.concat([faq_data, support_data_df[['Question', 'Answer']]], ignore_index=True)
 
 # Initialize SBERT Model
 model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
 
-# Generate and Index Embeddings
+# Generate and Index Embeddings for Combined Data
 questions = combined_data['Question'].tolist()
 embeddings = model.encode(questions, convert_to_tensor=True)
+
+# Create FAISS index
 index = faiss.IndexFlatL2(embeddings.shape[1])
 index.add(embeddings.cpu().numpy())
 
-def get_answer(question):
+# Define Retrieval Function
+def retrieve_answer(question):
     question_embedding = model.encode([question], convert_to_tensor=True)
     question_embedding_np = question_embedding.cpu().numpy()
     _, closest_index = index.search(question_embedding_np, k=1)
     best_match_idx = closest_index[0][0]
     answer = combined_data.iloc[best_match_idx]['Answer']
-    return answer if answer else "Answer not found."
+    return answer
+
+# Gradio Interface
+def chatbot_interface(user_input):
+    response = retrieve_answer(user_input)
+    return f"Bot: {response}"
+
+# Define a route to serve the Gradio interface
+@app.get("/")
+def home():
+    return {"message": "Welcome to the E-commerce Support Chatbot!"}
+
+# Launch Gradio Interface in a separate thread
+def launch_gradio():
+    iface = gr.Interface(
+        fn=chatbot_interface,
+        inputs=gr.Textbox(lines=2, placeholder="Type your question here..."),
+        outputs="text",
+        title="E-commerce Support Chatbot",
+        description="Ask questions about order tracking, returns, account help, and more!"
+    )
+    iface.launch(share=True)
 
-# Example usage
 if __name__ == "__main__":
-    # Replace this with any input method you want, like a chatbot interface
-    user_question = input("Ask your question: ")
-    response = get_answer(user_question)
-    print("Response:", response)
+    import threading
+    threading.Thread(target=launch_gradio).start()
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)