Update app.py

app.py

@@ -1,26 +1,38 @@
 import gradio as gr
 import chromadb
 from sentence_transformers import SentenceTransformer
+import pandas as pd # Make sure pandas is imported
 
 # --- 1. Load Model (No changes here) ---
 print("Loading sentence-transformer model...")
 model = SentenceTransformer('all-MiniLM-L6-v2')
 print("Model loaded.")
 
-# --- 2. Setup ChromaDB (No changes here) ---
+# --- 2. Setup ChromaDB ---
 client = chromadb.Client()
 
 try:
     collection = client.create_collection("my_documents")
     print("ChromaDB collection created.")
     
-    documents = [
-        "The Eiffel Tower is a wrought-iron lattice tower on the Champ de Mars in Paris, France.",
-        "The Great Wall of China is a series of fortifications made of stone, brick, and other materials.",
-        "ChromaDB is an open-source embedding database designed to store and retrieve vector embeddings.",
-        "Hugging Face Spaces is a platform for building, deploying, and sharing ML apps.",
-        "A chatbot is a software application used to conduct an on-line chat conversation."
-    ]
+    # --- THIS IS THE UPDATED SECTION ---
+    # Load your data from the CSV file.
+    # IMPORTANT: Change 'text' to the actual name of the column in your CSV that contains the text data.
+    try:
+        print("Loading data from my_data.csv...")
+        df = pd.read_csv('my_data.csv')
+        # Ensure you change 'text' to your column's name if it's different
+        documents = df['text'].tolist() 
+        print(f"Successfully loaded {len(documents)} documents.")
+    except FileNotFoundError:
+        print("Error: my_data.csv not found. Please upload the file to your Space.")
+        # Create a fallback document to avoid a crash
+        documents = ["Error: my_data.csv not found. Please make sure the file is uploaded to the Hugging Face Space."]
+    except KeyError:
+        print("Error: The CSV must have a column named 'text'. Please rename your column or update the code.")
+        documents = ["Error: Could not find a 'text' column in the CSV file. Please check your data."]
+
+    # --- END OF UPDATED SECTION ---
     
     embeddings = model.encode(documents)
     
@@ -38,14 +50,8 @@ except ValueError:
 
 # --- 3. Define the Chatbot Logic (No changes here) ---
 def chatbot_response(message, history):
-    """
-    This function processes the user message and returns a response.
-    'message' is the user's input, 'history' is the conversation history.
-    """
-    # 1. Create an embedding for the user's message
     query_embedding = model.encode([message]).tolist()
     
-    # 2. Query ChromaDB to find the most relevant documents
     results = collection.query(
         query_embeddings=query_embedding,
         n_results=2 
@@ -53,25 +59,23 @@ def chatbot_response(message, history):
     
     retrieved_documents = results['documents'][0]
     
-    if not retrieved_documents:
-        return "I'm sorry, I couldn't find any information on that topic. 🤔"
+    if not retrieved_documents or "Error:" in retrieved_documents[0]:
+        return "I'm sorry, I couldn't find any information on that topic, or there was an error loading my knowledge base. 🤔"
         
-    # 4. Formulate the response
     context = "\n- ".join(retrieved_documents)
-    response = f"Here's what I found related to your question:\n- {context}"
+    response = f"Based on the document, here's what I found:\n- {context}"
     
     return response
 
-# --- 4. Create the NEW Gradio Chat Interface (Corrected Section) ---
+# --- 4. Create the Gradio Interface (No changes here) ---
 iface = gr.ChatInterface(
     fn=chatbot_response,
-    title="ChromaDB Knowledge Bot 🤖",
-    description="Ask me anything! I'll search my knowledge base to find the best answer for you.",
+    title="My Custom Knowledge Bot 📚",
+    description="Ask me anything about the contents of my document.",
     theme="soft", 
     examples=[
-        "What is ChromaDB?", 
-        "Tell me about Hugging Face Spaces", 
-        "What is the Eiffel Tower made of?"
+        # Update these examples to be relevant to your data
+        "What is the main topic of the document?", 
     ],
     cache_examples=False
 )