Update app.py

app.py

@@ -9,21 +9,26 @@ import torch
 import gradio as gr
 
 # Load dataset
-dataset = pd.read_csv("dataset.csv")
+try:
+    dataset = pd.read_csv("dataset.csv")
+except FileNotFoundError:
+    raise FileNotFoundError("❌ dataset.csv not found. Please upload it alongside app.py.")
 
-# Convert to LangChain Documents
-documents = [
-    Document(
-        page_content=str(row["answer"]),
-        metadata={"question": str(row["question"])}
-    )
-    for _, row in dataset.iterrows()
-]
+# Convert dataset to LangChain Documents
+def dataframe_to_documents(df, content_col="answer", metadata_cols=["question"]):
+    return [
+        Document(
+            page_content=str(row[content_col]),
+            metadata={col: str(row[col]) for col in metadata_cols}
+        )
+        for _, row in df.iterrows()
+    ]
 
-# Setup embeddings
+documents = dataframe_to_documents(dataset)
+
+# Initialize components
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-# Load LLM
 model_name = "google/flan-t5-base"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
@@ -31,56 +36,44 @@ pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer, max_le
                 device=0 if torch.cuda.is_available() else -1)
 llm = HuggingFacePipeline(pipeline=pipe)
 
-# Create vector store
+# Create vector store & retriever
 vector_store = FAISS.from_documents(documents, embeddings)
 retriever = vector_store.as_retriever(search_kwargs={"k": 3})
 
-# Create QA chain
+# Create QA Chain
 qa_chain = RetrievalQA.from_chain_type(
     llm=llm,
     retriever=retriever,
     return_source_documents=True
 )
 
-# Chatbot function
+# Chatbot logic
 def chatbot_interface(question: str) -> str:
-    if not qa_chain:
-        return "Chatbot backend not initialized properly."
+    if not question.strip():
+        return "❗ Please enter a question."
+
     try:
         response = qa_chain.invoke({"query": question})
-        answer = response.get("result", "No answer found.")
+        answer = response.get("result", "❌ No answer found.")
         sources = response.get("source_documents", [])
         source_texts = [doc.page_content for doc in sources]
-        return f"Answer: {answer}\n\nSources:\n" + "\n".join(f"- {text}" for text in source_texts)
-    except Exception as e:
-        return f"Error: {e}"
 
-# Task 4: Gradio UI
+        # Format response
+        formatted_sources = "\n".join(f"- {src}" for src in source_texts) if source_texts else "No sources found."
+        return f"✅ **Answer:** {answer}\n\n📚 **Sources:**\n{formatted_sources}"
 
+    except Exception as e:
+        return f"❌ Error: {e}"
 
-def chatbot_interface(question: str) -> str:
-    """
-    Processes a question through the Chatbot and returns the response for Gradio.
-    
-    Args:
-        question (str): User input question.
-    
-    Returns:
-        str: Chatbot response with answer and sources.
-    """
-    if not question.strip():
-        return "Please enter a question."
-    return chatbot.ask(question)
-
-# Create Gradio interface
+# Gradio UI
 interface = gr.Interface(
     fn=chatbot_interface,
-    inputs=gr.Textbox(label="Enter your question", placeholder="e.g., What is Artificial Intelligence?"),
+    inputs=gr.Textbox(label="Ask a question", placeholder="e.g., What is Artificial Intelligence?"),
     outputs=gr.Textbox(label="Response"),
-    title="RAG Chatbot",
-    description="Ask questions about AI, chatbots,RAG",
+    title="RAG Chatbot 🤖",
+    description="Ask me anything about AI, RAG, NLP, and more!",
     theme="default"
 )
 
-# Launch the interface
-interface.launch(share=True)
+# Run the app
+interface.launch()